mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-30 18:31:25 +00:00
9f437d86b6d74982c26b1ef499fa32d71cbe115f
389 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Haoming Song
|
b74a551d38 |
fix(pi0, pi05): stabilize torch.compile and expand test coverage (#3610)
* chore(gr00t): sync with #3606 for fixing gr00t config crash * fix(pi0&pi05): fix graph break caused by deepcopy of past_key_values in sample_actions * fix(pi0&pi05): fix frequent recompile caused by compute_layer_complete * feat(test): add compile test and benchamrk for pi0 and pi05 * feat(test): add comprehensive testing for pi0 and pi05. Including processor, forward, sample action, etc. |
||
|
Virgileboat
|
f4b834844e |
Feat/clean can bus (#3526)
* change timeout for handshake * enforce last state read when querry * change import order * fix(motors): flush stale robstride RX and harden feedback drain * robstride: remove redundant timeout and max_messages casts * bugfix + %-style * update exception catch |
||
|
Roham Z. Nobari
|
dfdc48a7f1 |
fix(datasets): bound VideoDecoderCache to prevent OOM on large datasets (#3614)
VideoDecoderCache used an unbounded dict keyed on absolute path, with no eviction in the standard LeRobotDataset path. With shuffled iteration over datasets that have many distinct mp4 files, every DataLoader worker accumulated one cached (VideoDecoder, fsspec file handle) pair per distinct path it had ever touched. Per-entry cost is ~3-5 MB of host RAM plus one open FD; at ~8 k entries this is roughly 30 GB per worker. This was hit in the wild during a SmolVLA training run on a 4,195-episode SO-101 dataset (8,390 mp4s, two cameras per episode). dmesg showed anon-rss climbing to 34.9 GB on a single pt_data_worker before the OOM killer fired ~30 min into training; with --num_workers=8 the per-worker peak halved to 17.9 GB, which is the expected inverse-scaling signature when the leak is per-decode and the workload is split across workers. The working workaround on the affected platform was --dataset.video_backend=pyav, because the pyav path opens/closes per call and never touches this cache. Switch the backing store to an OrderedDict and evict LRU entries when the cap is reached, closing the evicted file handle inside the lock so we do not leak FDs either. Default cap is DEFAULT_DECODER_CACHE_SIZE = 100, overridable via LEROBOT_VIDEO_DECODER_CACHE_SIZE or by passing max_size= to the constructor; max_size=None restores the legacy unbounded behaviour for callers that need it. Validation on the original failing workload (decode_video_frames_torchcodec called over real mp4s from the affected SO-101 dataset): unbounded: 300 files -> +1087 MB host RSS, cache=300, still climbing cap=50: 500 files -> +266 MB host RSS, cache=50, stable cap=50: 2000 calls -> +312 MB host RSS, cache=50, stable cap=100: 1000 calls -> +470 MB host RSS, cache=100, stable Three independent seeded runs at cap=50 agreed to within 1% (263 / 266 / 265 MB delta), and the 2000-call multi-pass run shows RSS plateaus after the cap is reached instead of drifting. Tests in tests/datasets/test_video_decoder_cache.py cover: default-is-bounded, size cap, LRU ordering, FD close on eviction, FD close on clear(), cache-hit invariance, max_size=None fallback, and env-var override. No regressions in test_video_encoding.py, test_streaming.py, or test_dataset_reader.py (73 prior tests still pass alongside the 8 new ones). |
||
|
四七
|
6a8878a639 |
fix(datasets): normalize shape=(1,) numeric values before HF encoding (#3344)
* fix(datasets): normalize shape=(1,) numeric values before save * test(datasets): cover shape=(1,) int/bool and finalize Co-authored-by: Copilot <copilot@github.com> |
||
|
Caroline Pascal
|
d38eb89f71 |
feat(video re-encoding): Adding utility and dataset edition tool for video re-encoding (#3611)
* feat(utility): adding video re-encode utility * feat(edit): adding a new lerobot-edit-dataset tool to re-encode all the videos of a dataset * chore(format): formatting code * chore(review): fix Claude reviews * test(reencode dataset): adding missing test for reencode dataset |
||
|
Pepijn
|
7ab4936b1b |
Add extensive language support (#3467)
* Add extensive language support * Address review: split persistent/event schemas, drop event timestamps - recipe.py: derive _VALID_ROLES/_VALID_STREAMS from MessageRole/MessageStream Literals - dataset_metadata.py: keep CODEBASE_VERSION at v3.0 - language.py: remove RESERVED_STYLES; split arrow/feature schemas into persistent (with timestamp) and event (without timestamp); add docstrings - language_render.py: events use frame-row timestamp implicitly; no per-event timestamp filtering or sorting - converters.py: drop unused subtask_key passthrough - add docstrings to new public APIs (recipe, render_messages_processor, collate) - update tests for split schemas; revert uv.lock Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Add docstrings to all new helpers; revert uv.lock Covers private helpers in recipe.py, language.py, language_render.py, and render_messages_processor.py. Also reverts uv.lock to main (it was re-generated by `uv run` during local checks). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): add motion (persistent) and trace (event-only) styles Promote the previously-reserved motion/trace styles to first-class core styles. motion routes to language_persistent (it tracks robot state over time); trace routes to language_events (single-moment annotations). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): per-camera tagging on view-dependent styles Adds a nullable `camera` field to the language row struct (both persistent and event variants) so view-dependent styles like `vqa` can carry which `observation.images.*` view they were grounded against. Without this, multi-camera datasets ended up with multiple `(vqa, role)` rows at the same timestamp that the resolver could not disambiguate. - `language.py`: add `camera` to PERSISTENT_ROW_FIELDS / EVENT_ROW_FIELDS, to both Arrow struct types and the HF datasets feature mappings; introduce VIEW_DEPENDENT_STYLES = {vqa, motion, trace} plus `is_view_dependent_style` and `validate_camera_field` helpers (camera required iff style is view-dependent). - `language_render.py`: thread an optional `camera=` kwarg through every resolver (`active_at`, `emitted_at`, `nth_prev`, `nth_next`) and through `_matching_rows` / `_select_*`, so recipes can disambiguate per-camera VQA with `emitted_at(t, style=vqa, role=assistant, camera=...)`. Without a `camera` filter, multi-row matches keep raising the existing ambiguity error — which is the desired behaviour on multi-camera data. - `recipes/pi05_hirobot.yaml`: replace the single `ask_vqa` branch with `ask_vqa_top` and `ask_vqa_wrist` per-camera sub-recipes (each carrying the matching image block), keeping the original 0.20 budget and documenting the customization point for datasets with different cameras. - Tests: schema test asserts the new field order; new tests cover `is_view_dependent_style`, `validate_camera_field` (both required and forbidden directions), per-camera `emitted_at` filtering, and the ambiguity error when two cameras emit `(vqa, assistant)` at the same timestamp without a `camera=` filter. RenderMessagesStep + dataset passthrough fixtures updated to include the new field. - `docs/source/language_and_recipes.mdx`: document the `camera` field, the per-camera resolver pattern, and the canonical recipe convention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): drop motion from VIEW_DEPENDENT_STYLES Motion primitives are described in robot-frame (joint / Cartesian) terms, not pixel space, so they are camera-agnostic. Only `vqa` (event) and `trace` (event, pixel-trajectory) are view-dependent. The `camera` field stays on PERSISTENT_ROW_FIELDS for schema symmetry — the validator, resolver, and HF feature mapping behave identically across the two columns regardless of which styles populate `camera` today — but persistent rows now always have `camera=None` in practice. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): task_aug style + automatic ${task} rephrasing rotation Adds task-prompt diversity (Xiao 2022 / CAST) without touching ``meta/tasks.parquet`` or forcing recipes to opt in. The plan reserved ``task_aug`` as a future style; this lands it now. - ``language.py``: add ``task_aug`` to ``CORE_STYLES`` and ``PERSISTENT_STYLES``. ``column_for_style("task_aug")`` returns ``language_persistent`` so PR 2 writers route it correctly. - ``language_render.py``: ``_resolve_task`` now consults the persistent slice for rows of ``style="task_aug", role="user"``. When any exist it picks one deterministically by ``sample_idx`` (blake2b-keyed, not Python's randomized hash) so an epoch sees every rephrasing of every episode while the same sample still resolves identically across reruns. Falls back to the canonical ``meta/tasks.parquet`` task when no rephrasings are present, so existing datasets and unannotated runs keep their behaviour. Explicit ``task=`` overrides still win. - Tests: rephrasing coverage across samples, determinism on repeat ``sample_idx``, fallback when persistent has no ``task_aug`` rows, and explicit override priority. Recipes get this for free: any ``${task}`` placeholder rotates through the available rephrasings. Recipes that want the literal canonical task can override the binding. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): tool catalog in meta/info.json + LeRobotDatasetMetadata.tools Stores OpenAI-style function schemas at ``meta/info.json["tools"]`` so datasets can declare which tools are available (today: just ``say``; tomorrow: per-dataset extensions). The ``DEFAULT_TOOLS`` constant fills in for unannotated datasets so chat-template consumers don't have to special-case anything. Three pieces: - ``language.py``: ``SAY_TOOL_SCHEMA`` and ``DEFAULT_TOOLS`` constants. Single source of truth — PR 2's writer and PR 3's runtime tool registry will both import from here instead of duplicating the dict. - ``dataset_metadata.py``: ``LeRobotDatasetMetadata.tools`` property reads ``info.json["tools"]`` and falls back to ``DEFAULT_TOOLS``. Returns deep-copied dicts so callers can mutate the result safely. - ``docs/source/tools.mdx``: spec page covering the catalog, per-row invocations, and the three-step "how to add a new tool" workflow (declare schema, implement, register). Linked from the docs toctree under the Datasets section. This lays the groundwork for PR 2's pipeline writing the catalog out during annotation, and PR 3's ``src/lerobot/tools/`` package shipping runnable implementations (one file per tool — first up: ``say.py`` wrapping Kyutai's pocket-tts). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Apply ruff and prettier formatting after merge Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(language): unify resolver dispatch and prune redundant test scaffolding * Drop the unused `events` kwarg from `active_at`/`nth_prev`/`nth_next`; only `emitted_at` actually consults events. The dispatcher in `_resolve_spec` now passes events conditionally. * Replace the dual `_persistent_sort_key`/`_event_sort_key` pair with a single `_row_sort_key` and drop the `sort_key` parameter from `_select_one`. Event rows lack `timestamp` (it is implicit in the frame) and now default to `0.0` for sort purposes — the `(style, role)` tiebreaker is unchanged. * Inline `_select_latest` into `active_at` (its only caller). * Collapse `emitted_at`'s dual-branch into one `_select_one` call. * Tighten `_validate_persistent_resolver` to a single `column_for_style(style) != LANGUAGE_PERSISTENT` check. * Parameterize `test_per_camera_blend_renders_both_views` over the two cameras and factor the sub-recipe builder into `_vqa_subrecipe` so the test no longer hand-rolls two near-identical recipe blocks. Net -98 LOC; behavior, public resolver names, and test expectations unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): always raise on ambiguous resolver matches `_select_one` previously skipped its ambiguity check whenever any of `role`/`tool_name`/`camera` was set, on the assumption that the caller had already pinned down a unique row. That left a real ambiguity hole for VQA: with two cameras emitting `(vqa, assistant)` at the same frame, `emitted_at(..., role="assistant")` silently picked the first sorted row instead of telling the recipe to add `camera=...`. The existing `test_emitted_at_raises_on_ambiguous_per_camera_vqa` test already encoded the desired behavior. Tighten the check: any time `len(rows) > 1` we now raise with the selectors echoed back, so users see exactly which fields they passed and that more is needed to disambiguate. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: fix CI — collapse short ValueError to one line, refresh uv.lock * `ruff format` on CI (newer version) wants the short `camera=None` ValueError on a single line. * `uv.lock` was stale relative to `pyproject.toml`'s `datasets>=4.7.0` pin (and picked up upstream `s390x` marker fixes for cuda packages). CI runs `uv sync --locked` which rejected the divergence. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): keep base install green — drop processor re-export, gate dataset-extra tests `lerobot.processor` re-exported `RenderMessagesStep` at the package level, so importing anything from `lerobot.processor` pulled in `lerobot.datasets.language` → `lerobot.datasets/__init__.py` → `require_package("datasets")`, which fails in the Tier 1 base install that intentionally omits the `[dataset]` extra. The chain bricked collection for unrelated suites (`tests/policies/pi0_pi05/...`, `tests/envs/...`, etc.). * Stop re-exporting `RenderMessagesStep` from `lerobot.processor`. The only consumer (the test) already imports from the submodule. Document the deliberate omission in the module docstring. * Add `pytest.importorskip("datasets", ...)` (and `pandas` where needed) at the top of the four PR-added tests that exercise the language stack: - tests/datasets/test_language.py - tests/datasets/test_language_render.py - tests/processor/test_render_messages_processor.py - tests/utils/test_collate.py Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): address review — tools accessor, motion docs, conditional collate * **`meta.tools` actually reads `info.json["tools"]`.** `DatasetInfo` had no `tools` field, so `from_dict` silently dropped the key (it warned about unknown fields then discarded them) and the property always returned `DEFAULT_TOOLS`. Added `tools: list[dict] | None` to the dataclass; `to_dict()` drops it when unset so existing datasets keep a clean `info.json`. Fixed the accessor to read `self.info.tools` (the previous `.get(...)` would have raised AttributeError on the dataclass anyway). Added regression tests: fallback when absent, round-trip from disk, and round-trip through `DatasetInfo.from_dict` / `to_dict`. * **`motion` is not view-dependent — fix the docs.** The mdx claimed rows of style `motion` must carry `camera`, but `VIEW_DEPENDENT_STYLES = {"vqa", "trace"}` and the validator agrees: motion primitives are joint/Cartesian-frame, not pixel-space. Updated both call-out paragraphs in `language_and_recipes.mdx`. * **Conditional `collate_fn` swap.** Added `meta.has_language_columns` and gate the `lerobot_collate_fn` swap in `lerobot_train.py` on it, so non-language datasets keep PyTorch's `default_collate`. Also added a pass-through test in `test_collate.py` that asserts on a plain tensor batch the custom collate matches `default_collate` key-for-key, plus a test for the `None`-sample drop path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: dedupe regex, centralize column names, harden collate, more tests * **#2 — dedupe `_PLACEHOLDER_RE`.** The same regex was compiled in `recipe.py` and `language_render.py`. Promote to module-level `PLACEHOLDER_RE` in `recipe.py` (its primary owner — declares template syntax) and import from `language_render.py`. * **#3 — centralize language column names.** `io_utils.py` had hardcoded `{"language_persistent", "language_events"}` literals at two sites. Replace with `LANGUAGE_COLUMNS` import so a future column rename can't silently desync. * **#4 — defensive collate preserved-keys.** `lerobot_collate_fn` silently filtered language fields from samples that didn't have them, which would hand downstream consumers a preserved list shorter than the tensor batch. Now: if any sample carries a key, every sample in the batch must carry it; otherwise raise a `ValueError` so the upstream rendering bug surfaces at the boundary. * **#5 — `_scalar` rejects non-singleton lists.** Previously a zero- or multi-element list fell through and triggered confusing `float([])` errors downstream. Now raises `ValueError` with the actual length. * **#6 — refactor `_extract_complementary_data`.** Replace 11 lines of `key = {... if ... else {}}` plus an 11-line splat dict with a single `_COMPLEMENTARY_KEYS` tuple iterated once. * **#7 — document `EXTENDED_STYLES`.** Was an empty `set()` with no comment. Add a docstring explaining it's an intentional extension point: downstream modules append project-local styles before `column_for_style` is called. * **#9 — `tools.mdx` notes the runtime layer is future work.** The page referenced `src/lerobot/tools/`, `registry.py`, and `get_tools(meta)` — none exist in this PR. Added a callout at the start of "How to add your own tool" plus a note on the implementations paragraph. * **#10 — tests for YAML round-trip, malformed rows, blend validation.** `test_recipe.py` grew from 1 case to 12 covering: blend-or-messages exclusivity, target-turn requirement, blend emptiness, weight presence/positivity, nested-blend rejection, `from_dict` with nested blends, `from_yaml` / `load_recipe` agreement, top-level non-mapping rejection. Added a malformed-row test for `_normalize_rows` that asserts non-dict entries raise `TypeError`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: emitted_at uses 0.1s tolerance; MessageTurn requires stream at construction * **Float tolerance in `emitted_at` for persistent styles.** The ``_timestamp(row) == t`` exact-equality check silently missed any caller that derived ``t`` arithmetically (e.g. ``frame_idx / fps``) even though the parquet timestamp would only differ by ULPs. Added ``EMITTED_AT_TOLERANCE_S = 0.1`` and check ``abs(...) <= tolerance`` instead, with a docstring explaining why exact equality wasn't enough and why 0.1 s is safe at typical 30–100 Hz control rates. Test asserts the new behavior at half-window (matches) and double-window (no match) using the constant so it stays in sync. * **`MessageTurn.stream` is required at construction.** It was typed ``MessageStream | None = None`` so YAML could omit ``stream:`` and pass the dataclass invariant — but ``_validate_rendered`` rejected ``None`` streams later, surfacing the error at the first sample instead of at recipe load. Now ``__post_init__`` raises ``ValueError`` if ``stream`` is ``None``, with the list of valid streams in the message. The redundant late-stage check in ``_validate_rendered`` is replaced with a one-line comment that cites the upstream invariant. Test pins the new construction-time rejection. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(tools): drop follow-up-PR references Reword the two callouts in `tools.mdx` to describe the runtime layer in present tense ("not part of the catalog layer shipped today", "those modules don't yet exist in the tree") instead of pointing at a specific follow-up PR. Keeps the doc honest about what works now without coupling it to a particular release order. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: address CarolinePascal feedback - language timestamps: float64 -> float32 to match LeRobotDataset frame timestamps (Arrow struct + HF feature) - dataset_metadata: hoist `.language` imports to module top — language.py has no lerobot imports, so there is no circular-import risk - dataset_metadata: add a `meta.tools` setter that persists the catalog to info.json and reloads `meta.info` - feature_utils: validate the `language` dtype instead of returning "" — warn (non-fatal) when a non-empty value is written at record time - centralize the scalar-unwrap helper as `lerobot.utils.utils.unwrap_scalar`, shared by render_messages_processor and language_render - docs: move `## Layer 2 — recipe anatomy` ahead of the resolver sections, which describe recipe bindings rather than dataset layout - language_render: note in EMITTED_AT_TOLERANCE_S that persistent rows change on a human-action timescale, not the camera frame rate Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
von Neumann 101
|
ca8c60a0ed |
Set OpenCV fourcc after size and fps (#3620)
* Set OpenCV fourcc after size and fps * Set OpenCV fourcc last on Windows * Add comment explaining DSHOW fourcc ordering |
||
|
Pepijn
|
3c15fd8537 |
feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624)
* feat(robots): natively integrate Seeed Studio reBot B601-DM arm Add first-class LeRobot support for the Seeed Studio reBot arm, replacing the out-of-tree `lerobot-robot-seeed-b601` / `lerobot-teleoperator-rebot-arm-102` plugin packages. New devices: - robot `rebot_b601_follower` — single-arm B601-DM follower (6-DOF + gripper, Damiao CAN motors via `motorbridge`) - robot `bi_rebot_b601_follower` — bimanual follower composing two single arms - teleoperator `rebot_102_leader` — single-arm StarArm102 / reBot Arm 102 leader (FashionStar UART servos via `motorbridge-smart-servo`) - teleoperator `bi_rebot_102_leader` — bimanual leader composing two single arms The bimanual variants reuse the single-arm classes and namespace each arm's observation/action keys with `left_` / `right_` prefixes, so a bimanual StarArm102 leader can teleoperate a bimanual reBot B601 follower. Optional SDK imports are guarded; a `rebot` extra installs `motorbridge` and `motorbridge-smart-servo`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: add reBot B601-DM calibration & dual-arm teleoperation guide Add docs/source/rebot_b601.mdx covering single-arm and bimanual calibration and teleoperation for the reBot B601-DM follower and reBot Arm 102 leader, with zero-position reference images from the Seeed Studio wiki. Register the page in the docs toctree. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: fix reBot B601 MDX build (move JSON example out of <Tip>) The doc-builder parses `{...}` inside MDX component children as a Svelte expression, so the joint_directions JSON example broke the build. Move it into a top-level fenced code block. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: apply prettier formatting to reBot B601 page Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: remove duplicate colocated reBot B601 page docs/source/rebot_b601.mdx is the canonical, toctree-registered page; the colocated rebot_b601.md was a redundant thinner copy. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: clarify 6-DOF leader fallback comment in reBot B601 follower Explain that holding wrist_yaw at zero is what lets a 6-DOF leader (e.g. so100_leader / so101_leader) teleoperate the 7-DOF follower. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: address Caroline's PR review on reBot B601 integration - leader: remove _validate_config (no other lerobot device validates its config; a key mismatch now surfaces as a plain KeyError) - leader: simplify _round_to_valid_range to direct modular arithmetic instead of a bidirectional search loop - leader: inline the single-use _clamp helper - follower & leader: write MotorCalibration range_min/range_max from the configured joint_limits / joint_ranges instead of a fixed [-90, 90] - docs: add a "Find the USB ports" section (lerobot-find-port) and move the brltty/permissions tip there; link the OpenArm page for SocketCAN adapter configuration Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Khalil Meftah
|
6e035fb169 | Update reward config and model card template (#3625) | ||
|
Haoming Song
|
01dcb4c292 | fix(pi05): update pi05 with transformers v5.4.0 interface (#3603) | ||
|
Caroline Pascal
|
bd9619dfc3 |
feat(encoding parameters): adding support for user provided video encoding parameters (#3455)
* chore(video backend): renaming codec into video_backend in get_safe_default_video_backend() * feat(pyav utils): adding suport for PyAV encoding parameters validation * feat(VideoEncoderConfig): creating a VideoEncoderConfig to encapsulate encoding parameters * feat(VideoEncoderConfig): propagating the VideoEncoderConfig in the codebase * chore(docs): updating the docs * feat(metadata): adding encoding parameters in dataset metadata * fix(concatenation compatibility): adding compatibility check when concatenating video files * feat(VideoEncoderConfig init): making VideoEncoderConfig more robust and adaptable to multiple backends * feat(pyav checks): making pyav parameters checks more robust * chore(duplicate): removing duplicate get_codec_options definition * test(existing): adapting existing tests * test(new): adding new tests for encoding related features * chore(format): fixing formatting issues * chore(PyAV): cleaning up PyAV utils and encoding parameters checks to stick to the minimun required tooling. * chore(format): formatting code * chore(doctrings): updating docstrings * fix(camera_encoder_config): Removing camera_encoder_config from LeRobotDataset, as it's only required in LeRobotDatasetWriter. * feat(default values): applying a consistent naming convention for default RGB cameras video encoder parameters * fix(rollout): propagating VideoEncoderConfig to the latest recording modes * chore(format): formatting code, fixing error messages and variable names * fix(arguments order): reverting changes in arguments order in StreamingVideoEncoder * chore(relative imports): switching to relative local imports within lerobot.datasets * test(artifacts): cleaning up artifacts for the video encoding tests * chore(docs): updating docs * chore(fromat): formatting code * fix(imports): refactoring the file architecture to avoid circular imports. VideoEncoderConfig is now defined in lerobot.configs and lazily imports av at runtime. * fix(typos): fixing typos and small mistakes * test(factories): updating factories * feat(aggregate): updating dataset aggregation procedure. Encoding tuning paramters (crf, g,...) are ignored for validation and changed to None in the aggregated dataset if incompatible. * docs(typos): fixing typos * fix(deletion): reverting unwanted deletion * fix(typos): fixing multiple typos * feat(codec options): passing codec options to lerobot_edit_dataset episode deletion tool * typo(typo): typo * fix(typos): fixing remaining typos * chore(rename): renaming camera_encoder_config to camera_encoder * docs(clean): cleaning and formating docs * docs(dataset): addind details about datasets * chore(format): formatting code * docs(warning): adding warning regarding encoding parameters modification * fix(re-encoding): removing inconsistent re-encoding option in lerobot_edit_dataset * typos(typos): typos * chore(format): resolving prettier issues * fix(h264_nvenc): fixing crf handling for h264_nvenc * docs(clean): removing too technical parts of the docs * fix(imports): fixing imports at the __init__ level * fix(imports): fixing not very pretty imports in video config file |
||
|
Cheng Yin
|
9db9c35cb4 |
fix(config): add lora_alpha to PeftConfig (#3573)
* fix(config): add lora_alpha to PeftConfig PeftConfig was missing the lora_alpha field, causing the PEFT library to default to alpha=8 regardless of the LoRA rank, which dampens the adaptation signal for high-rank adapters (e.g., r=128). This adds lora_alpha: int | None = None to PeftConfig, allowing users to specify --peft.lora_alpha <value> on the CLI. Closes #3551 * fix(docs): add lora_alpha to peft training example + clarify scaling formula - Add --peft.lora_alpha=64 to docs/source/peft_training.mdx example to prevent new users from hitting the alpha=8 default dampening bug - Clarify lora_alpha comment in default.py with scaling = lora_alpha / r * docs: mention both --peft.r and --peft.lora_alpha in LoRA description --------- Co-authored-by: Cheng Yin <yin@users.noreply.github.com> |
||
|
Jash Shah
|
fe96b28c74 |
Fix policy.path not working in YAML config files (#3145)
* fix(config): support policy.path in YAML config files policy.path was only handled via CLI args (filtered from sys.argv before draccus, then retrieved in validate()). When specified in YAML, draccus would crash because 'path' is not a valid field on PreTrainedConfig. Extract path fields from the YAML/JSON config before draccus processes it, store them in a module-level dict, and fall back to it in get_path_arg() when the CLI doesn't have the path. Fixes #2957 * fix(parser): preserve YAML policy overrides when loading from pretrained When policy.path is set in YAML, validate() was calling from_pretrained with only CLI overrides, discarding any YAML policy fields (e.g. lr, batch_size) that draccus had already parsed. Fix by capturing the remaining YAML fields as CLI-style args in _config_yaml_overrides and merging them into the overrides passed to from_pretrained in train.py, eval.py, and lerobot_record.py (CLI args still take precedence). Also fix the NamedTemporaryFile SIM115 ruff warning and add types-PyYAML to the mypy pre-commit hook. * fix(parser): serialize bool/None values correctly in YAML policy overrides Bool values from YAML configs (e.g. push_to_hub: true) were passed as Python "True"/"False" strings instead of lowercase "true"/"false" that draccus expects. Also skip None values to avoid passing "None" strings. * revert: remove types-PyYAML from .pre-commit-config.yaml * chore: fix quality check caused by untyped YAML import Co-authored-by: masato-ka <jp6uzv@gmail.com> Signed-off-by: Khalil Meftah <khalil.meftah@huggingface.co> --------- Signed-off-by: Khalil Meftah <khalil.meftah@huggingface.co> Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co> Co-authored-by: masato-ka <jp6uzv@gmail.com> |
||
|
Caroline Pascal
|
f218d5ab30 |
feat(episodes): adding support for metadata based episodes filtering (#3530)
* feat(episode filtering): adding support for episodes filtering at initialization time in LeRobotDataset * test(tests): adding tests * chore(format): formatting code * feat(performance): improving implementation for better performances on big datasets * chores(warning): improving warnings and errors for episodes filtering * test(invalid key): adding test for invalid filtering key * chore(format): formatting code |
||
|
Steven Palma
|
04125492e4 |
fix(datasets): expand torchcodec platform coverage + rewrite pyav fallback for torchvision >0.26 (#3588)
* fix(deps): better versioning control for torchcodec * refactor(video_utils): replace torchvision with pyav * adding Torchcodec version to lerobot-info * chore(benchmarks): delete video benchmark --------- Co-authored-by: Maximellerbach <maxime.ellerbach@huggingface.co> |
||
|
Khalil Meftah
|
e963e5a0c4 |
RL stack refactoring (#3075)
* refactor: RL stack refactoring — RLAlgorithm, RLTrainer, DataMixer, and SAC restructuring * chore: clarify torch.compile disabled note in SACAlgorithm * fix(teleop): keyboard EE teleop not registering special keys and losing intervention state Fixes #2345 Co-authored-by: jpizarrom <jpizarrom@gmail.com> * fix: remove leftover normalization calls from reward classifier predict_reward Fixes #2355 * fix: add thread synchronization to ReplayBuffer to prevent race condition between add() and sample() * refactor: update SACAlgorithm to pass action_dim to _init_critics and fix encoder reference * perf: remove redundant CPU→GPU→CPU transition move in learner * Fix: add kwargs in reward classifier __init__() * fix: include IS_INTERVENTION in complementary_info sent to learner for offline replay buffer * fix: add try/finally to control_loop to ensure image writer cleanup on exit * fix: use string key for IS_INTERVENTION in complementary_info to avoid torch.load serialization error * fix: skip tests that require grpc if not available * fix(tests): ensure tensor stats comparison accounts for reshaping in normalization tests * fix(tests): skip tests that require grpc if not available * refactor(rl): expose public API in rl/__init__ and use relative imports in sub-packages * fix(config): update vision encoder model name to lerobot/resnet10 * fix(sac): clarify torch.compile status * refactor(rl): update shutdown_event type hints from 'any' to 'Any' for consistency and clarity * refactor(sac): simplify optimizer return structure * perf(rl): use async iterators in OnlineOfflineMixer.get_iterator * refactor(sac): decouple algorithm hyperparameters from policy config * update losses names in tests * fix docstring * remove unused type alias * fix test for flat dict structure * refactor(policies): rename policies/sac → policies/gaussian_actor * refactor(rl/sac): consolidate hyperparameter ownership and clean up discrete critic * perf(observation_processor): add CUDA support for image processing * fix(rl): correctly wire HIL-SERL gripper penalty through processor pipeline (cherry picked from commit |
||
|
Jash Shah
|
9e83510c99 |
fix(datasets): close file handle on VideoDecoder init failure in cache (#3542)
If VideoDecoder() raises during initialization, the fsspec file handle was leaked since it was opened via __enter__() but never closed on the exception path. Now explicitly closes the handle before re-raising. |
||
|
Anthony Shoumikhin
|
1f7b03f5f2 |
chore(deps): allow torch 2.11/2.12 and fix autocast deprecation (#3435)
* chore(deps): allow torch 2.11/2.12 and fix autocast deprecation
- Bump torch to >=2.7,<2.13 (was <2.11), torchvision to <0.28 (was <0.26),
and torchcodec to <0.13 (was <0.11) to allow installs against the latest
stable torch 2.11 and the upcoming 2.12 line.
- Replace removed torch.get_autocast_gpu_dtype() with torch.get_autocast_dtype("cuda")
in Florence2 and Qwen2.5-VL-MoE FlashAttention paths (the former is removed in 2.11+).
- Refresh uv.lock for the new resolution (torch 2.11.0+cu130, torchvision 0.26.0+cu130,
torchcodec 0.11.1, full CUDA 13 stack).
Verified locally with `uv sync --locked` from a clean .venv and the lerobot
test suite (pytest -n 8 --dist=loadfile --timeout=300). Failure set is
identical to the pre-bump baseline: 18 pre-existing failures
(test_sac_policy*, test_pi0_rtc*, test_pi05_rtc*, test_replay_buffer*),
0 new, 0 fixed.
AI assistance: this change was authored with Claude Code per AI_POLICY.md.
* fix(policies): use device-agnostic autocast dtype lookup
Pass query_states.device.type to torch.get_autocast_dtype() instead of
hardcoding 'cuda', so the cast matches the active autocast context when
running under CPU/MPS/XPU autocast.
---------
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
|
||
|
masato-ka
|
0e6114ac36 |
fix(train): restrict legacy RA-BC migration to JSON checkpoints only (#3490)
* fix(train): restrict legacy RA-BC migration to JSON checkpoints only
_migrate_legacy_rabc_fields was called for all config files, causing
json.load to raise DecodeError when a YAML/TOML config was passed to
lerobot-train for a new training run. Guard the block with an
.endswith(".json") check so migration only runs when resuming from
a JSON checkpoint.
|
||
|
Steven Palma
|
c8ce413d73 | fix(robots): allign lekiwi default with so100 use_degrees (#3531) | ||
|
Ville Kuosmanen
|
eaf0218bc8 |
feat(policy): use pretrained vision encoder weights by default for diffusion and vqbet (#3202)
* feat: add pretrained vision encoder weights for diffusion and vqbet * fix test by re-generating artifacts --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> |
||
|
Haoming Song
|
e99c55af4b |
feat(policies): add EO-1 model (#3403)
* feat(policies): add EO-1 model * chore(eo1): adjust policy_eo1_README.md to to avoid duplicate with eo1.mdx * chore(eo1): remove policy_eo1_README.md, link eo1.mdx in policy folder --------- Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> |
||
|
Steven Palma
|
408e0ca763 | fix(robots): openarm features with openarmmini (#3524) | ||
|
Maxime Ellerbach
|
ce24063efd |
feat(dagger): adding smooth handover (#3506)
* feat(dagger): adding smooth handover * update docstring * small phase fix and documenting potential issues * cleaning up |
||
|
Steven Palma
|
82934719db |
chore(dep): bump transformers to 5.4.0 (#3374)
* fix(deps): breaking change from transformers 5.4.0 * Update src/lerobot/policies/xvla/modeling_florence2.py Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> * Update src/lerobot/policies/wall_x/qwen_model/qwen2_5_vl_moe.py Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> * removing dataclass * bumping transformers 5.4.0 * weird i can't even pass the test on main * oops, typo * chore(style): fix pre-commit run * chore: update uv.lock * seems like a weird numerical precision issue, lets check in runners * chore: update uv.lock * chore(dependecies): adjust transformers version * chore: update uv.lock --------- Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> Co-authored-by: Maximellerbach <maxime.ellerbach@huggingface.co> Co-authored-by: raushan <raushan@huggingface.co> |
||
|
Jash Shah
|
fdbfc015a2 | fix(peft): fix LoRA resume from Hub (PosixPath + double wrap) (#3485) | ||
|
Haoming Song
|
d656da8ccc |
fix(pi): keep training sampling outside compiled forwards (#3487)
Move PI0 and PI0.5 noise/time sampling into the policy wrappers so the compiled PyTorch cores receive them as tensor inputs. This keeps Beta sampling out of torch.compile on MPS, avoiding aten::_sample_dirichlet compilation errors while preserving the CUDA training path. Validation: .venv/bin/python -m pre_commit run --files src/lerobot/policies/pi0/modeling_pi0.py src/lerobot/policies/pi05/modeling_pi05.py; .venv/bin/python -m pytest -sv -rs tests/policies/pi0_pi05/test_pi0.py tests/policies/pi0_pi05/test_pi05.py tests/policies/pi0_pi05/test_pi0_rtc.py tests/policies/pi0_pi05/test_pi05_rtc.py Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> |
||
|
Khalil Meftah
|
b5f65e5332 |
Expose sarm package API and ship reward model card template (#3477)
* chore: List lerobot_rewardmodel_modelcard_template.md in MANIFEST.in * chore: export SARMConfig, SARMRewardModel, and make_sarm_pre_post_processors from rewards.sarm. |
||
|
Khalil Meftah
|
cd6b43ea7a | fix(train): migrate legacy RA-BC fields in train config loading (#3480) | ||
|
Steven Palma
|
2236bbe7a3 |
fix(rollout): propagate policy-specific CLI config paramaters (#3483)
Co-authored-by: Maxime Ellerbach <maxime.ellerbach@huggingface.co> |
||
|
Maxime Ellerbach
|
cb0a944941 |
refactor(datasets): replace untyped dict with typed DatasetInfo dataclass (#3472)
* refactor(datasets): replace untyped dict with typed DatasetInfo dataclass Introduce typed DatasetInfo dataclass to replace untyped dict representation of info.json. Changes: - Add DatasetInfo dataclass with explicit fields and validation - Implement __post_init__ for shape conversion (list ↔ tuple) - Add dict-style compatibility layer (__getitem__, __setitem__, .get()) - Add from_dict() and to_dict() for JSON serialization - Update io_utils to use load_info/write_info with DatasetInfo - Update dataset utilities and metadata to use attribute access - Remove aggregate.py dict-style field access - Add tests fixture support for DatasetInfo Benefits: - Type safety with IDE auto-completion - Validation at construction time - Explicit schema documentation * fix pre-commit * update docstring inside DatasetInfo.from_dict() * sorts the unknown to have deterministic output Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> * refactoring the last few old fieds * fix crop dataset roi type mismatch * use consistantly int for data and video_files_size_in_mb --------- Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> Co-authored-by: jjolla93 <jjolla93@gmail.com> |
||
|
Khalil Meftah
|
8a3d64033f |
Reward models refactor (#3142)
* feat(rewards): add RewardModelConfig and PreTrainedRewardModel base classes * refactor(rewards): migrate Classifier from policies/sac/reward_model/ to rewards/classifier/ * refactor(rewards): migrate SARM from policies/sarm/ to rewards/sarm/ * refactor(rewards): add rewards/factory.py and remove reward model code from policies/factory.py * refactor(rewards): update imports and delete old reward model locations * test(rewards): add reward model tests and update existing test imports * fix(rewards): restore full Classifier and SARM implementations * test(rewards): restore missing CUDA and mixed precision classifier processor tests * refactor(lerobot_train.py): remove rabc specific configuration and replace it with a generic samplerweight class in lerobot_train * refactor(lerobot_train.py): add missing sampling weight script * linter + missing files * add testing for sampl weighter * revert some useless changes, improve typing * update docs * add automatic detection of the progress path * remove type exp * improve comment * fix: move rabc.py to rewards/sarm/ and update import paths * refactor(imports): update reward model imports to new module structure * refactor(imports): update reward model imports to reflect new module structure * refactor(imports): conditionally import pandas based on availability * feat(configs): add reward_model field to TrainPipelineConfig and Hub fields to RewardModelConfig * refactor(policies): remove reward model branches from policy factory and __init__ * refactor(rewards): expand __init__ facade and fix SARMConfig __post_init__ crash * feat(train): route reward model training through rewards/factory instead of policies/factory * refactor(train): streamline reward model training logic * fix(rewards): ensure FileNotFoundError is raised for missing config_file * refactor(train): update __get_path_fields__ to include reward_model for config loading * refactor(classifier): remove redundant input normalization in predict_reward method * fix(train): raise ValueError for non-trainable reward models in train function * refactor(pretrained_rm): add model card template * refactor(tests): reward models * refactor(sarm): update reset method and remove unused action prediction methods * refactor(wandb): differentiate tags for reward model and policy training in cfg_to_group function * fix(train): raise ValueError for PEFT usage in reward model training * refactor(rewards): enhance RewardModelConfig with device handling and delta indices properties --------- Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> |
||
|
Steven Palma
|
ca87ccd941 |
feat(rollout): decouple policy deployment from data recording with new lerobot-rollout CLI (#3413)
* feat(scripts): lerobot-rollout * fix(rollout) require dataset in dagger + use duration too * fix(docs): dagger num_episodes * test(rollout): fix expectations * fix(rollout): features check * fix(rollout): device and task propagation + feature pos + warn fps + move rename_map config * docs(rollout): edit rename_map instructions * chore(rollout): multiple minor improvements * chore(rollout): address coments + minor improvements * fix(rollout): enable default * fix(tests): default value RTCConfig * fix(rollout): robot_observation_processor and notify_observation at policy frequency instead of interpolator rate Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): prevent relativeactions with sync inference engine Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): rtc reanchor to non normalized state Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): fixing the episode length to use hwc (#3469) also reducing default length to 5 minutes * feat(rollout): go back to initial position is now a config * fix(rollout): properly propagating video_files_size_in_mb to lerobot_dataset (#3470) * chore(rollout): note about dagger correction stage * chore(docs): update comments and docstring * fix(test): move rtc relative out of rollout module * fix(rollout): address the review comments --------- Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: Maxime Ellerbach <maxime.ellerbach@huggingface.co> |
||
|
Steven Palma
|
05a5223885 |
fix(pi): avoid peak RAM in PiGemma construction by freeing replaced submodules (#3454)
Co-Authored-By: Daiki Kamata <daiki.kamata@access-company.com> Co-Authored-By: Jack Vial <jackvial@users.noreply.github.com> Co-Authored-By: Ajay Anubolu <AjAnubolu@users.noreply.github.com> Co-Authored-By: Finn F. <F-Fer@users.noreply.github.com> |
||
|
Steven Palma
|
580d818aa9 | fix(dataset): no default overwrite in lerobot tool recompute stats (#3452) | ||
|
Steven Palma
|
587aa82021 | fix(imports): realsense import name is platform dependent (#3451) | ||
|
Chuyao Shen
|
12b88fce02 |
not use dataclass (#3414)
Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> |
||
|
masato-ka
|
fc6c94c82a |
fix(sarm): handle BaseModelOutputWithPooling from transformers 5.x in… (#3419)
* fix(sarm): handle BaseModelOutputWithPooling from transformers 5.x in CLIP encoding In transformers 5.x, CLIPModel.get_image_features() and get_text_features() return BaseModelOutputWithPooling instead of a plain torch.FloatTensor. Added isinstance check to extract pooler_output when the return value is not a tensor, maintaining backward compatibility with transformers 4.x. Fixes AttributeError: 'BaseModelOutputWithPooling' object has no attribute 'detach' * Adding assertion check for pooler_output of CLIP. This change is response to below comment. https://github.com/huggingface/lerobot/pull/3419#discussion_r3112594387 * Adding assertion check for pooler_output of CLIP. This change is response to below comment. Change to simple check and rise https://github.com/huggingface/lerobot/pull/3419#discussion_r3126953776 --------- Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> |
||
|
Steven Palma
|
1add460678 |
fix(policy): loss normalization for padded actions in ACT, Diffusion, and MultiTaskDiT (#3442)
* Fix loss normalization for padded actions in ACT, Diffusion, and MultiTaskDiT When action_is_pad masks out padded timesteps, the subsequent .mean() still divides by the total element count (including zeroed-out padding), underestimating the loss. With 60-70% padding this can cut the effective gradient signal by 2-3x. Replace mask-then-mean with mask-then-sum / valid-count for all three affected policies. TDMPC is not affected because it sums over time before averaging over batch. Fixes #3353 * linting Co-authored-by: whats2000 <60466660+whats2000@users.noreply.github.com> Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> * Update src/lerobot/policies/diffusion/modeling_diffusion.py Co-authored-by: whats2000 <60466660+whats2000@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * Update src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py Co-authored-by: whats2000 <60466660+whats2000@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * Update src/lerobot/policies/multi_task_dit/modeling_multi_task_dit.py Co-authored-by: whats2000 <60466660+whats2000@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * apply ACT loss normalization suggestion from review Divide by num_valid (timesteps * action_dim) instead of just timesteps, matching the diffusion/multi_task_dit fix. Addresses review from @whats2000 (https://github.com/huggingface/lerobot/pull/3377#discussion_r3106845791). * fix(test): update safetensor act --------- Signed-off-by: Maxime Ellerbach <maxime@ellerbach.net> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com> Co-authored-by: Maxime Ellerbach <maxime@ellerbach.net> Co-authored-by: whats2000 <60466660+whats2000@users.noreply.github.com> |
||
|
whats2000
|
2236cdb302 |
fix(smolvla): correct loss normalization for padded actions (#3434)
Apply the same per-scalar-mean fix to SmolVLA that #3377 landed for ACT / Diffusion / MultiTaskDiT. The pre-patch form applies the `action_is_pad` mask to zero out padded timesteps, then calls `.mean()` (or `.mean(dim=(1, 2))`). Because `.mean()` divides by the total number of elements including the zeroed padding, the loss is diluted by the padding fraction. Fixed by normalizing only over valid (non-padded) scalar entries: num_valid = ((~actions_is_pad).sum(...) * losses.shape[-1]).clamp_min(1) loss = losses.sum(...) / num_valid `clamp_min(1)` preserves the all-padded-batch edge case (0/1 = 0). Both reduction paths are updated. Behavior when `action_is_pad` is missing is unchanged (`losses.mean()`). Empirical A/B on aloha_sim_transfer_cube_human (chunk_size=40, batch=2, 30 steps, fixed seed, GB200) shows `loss_A / loss_B = 0.9672 (±0.088)` — same direction and magnitude as PR #3377's `loss_A / loss_C ≈ 0.96` for ACT. Heavier-padding recipes will see a larger gap. Refs: #3353 (original report for ACT), #3377 (fix for the other three policies). |
||
|
Pepijn
|
5adad11128 |
feat(sim): VLABench benchmark integration (#3396)
feat(sim): add VLABench benchmark integration Add VLABench as a new simulation benchmark in LeRobot, following the existing LIBERO and MetaWorld patterns. This PR wires VLABench end-to-end across environment integration, Docker setup, CI smoke evaluation, and documentation. It also fixes a number of upstream packaging and runtime issues required to make VLABench usable and reproducible in CI. What’s included Benchmark integration Add VLABench as a new simulation benchmark. Expose supported VLABench tasks through the LeRobot env interface. Follow the established LIBERO / MetaWorld factory patterns. Preserve lazy async-env metadata so env.unwrapped.metadata["render_fps"] continues to work. CI smoke evaluation Add a VLABench smoke-eval job using lerobot/smolvla_vlabench. Use the correct rename_map for the 3-camera dataset layout. Expand smoke coverage from 1 to 10 primitive tasks. Extract task descriptions after eval so metrics artifacts include per-task labels. Skip Docker Hub login when secrets are unavailable (e.g. fork PRs). Docker / install fixes Install VLABench from GitHub rather than PyPI. Use uv pip, not pip, in the base image. Fail loudly on install errors instead of masking them. Clone VLABench into the non-root user’s home directory. Use shallow editable installs for VLABench and rrt-algorithms to work around missing __init__.py issues. Pin upstream clones to exact commit SHAs for reproducibility. Add undeclared runtime dependencies required by VLABench (open3d, colorlog, scikit-learn, openai). Unpin open3d so Python 3.12 wheels resolve. Assets Support downloading VLABench assets from a Hugging Face Hub mirror via VLABENCH_ASSETS_REPO. Keep Google Drive download support as fallback. Install huggingface_hub[hf_xet] so Xet-backed assets download correctly. Validate required mesh/XML asset subtrees at build time. Patch VLABench constants to tolerate missing asset directories at import time. Runtime / env correctness Import VLABench robots and tasks explicitly so decorator-based registry population happens. Resize and normalize camera observations so they always match the declared (H, W, 3) uint8 observation space. Reinstall LeRobot editably inside the image so the new env code is actually used. Coerce agent_pos / ee_state to the expected shape. Pad actions when needed to match data.ctrl. Replace zero-padding fallback with proper dm_control IK for 7D end-effector actions. Refetch dm_control physics on each step instead of caching weakrefs. Retry unstable resets with reseeding and handle PhysicsError gracefully at step time. Dataset / policy alignment Align VLABench observations and actions with Hugging Face dataset conventions used by lerobot/vlabench_unified: convert EE position between world frame and robot-base frame at the env boundary, expose / consume Euler XYZ instead of raw quaternion layout, align gripper semantics with dataset convention (1 = open, 0 = closed). This fixes policy/env mismatches that previously caused incorrect IK targets and unstable behavior at evaluation time. Docs Add a full docs/source/vlabench.mdx page aligned with the standard benchmark template. Document task selection forms (single task, comma list, suite shortcut). Document installation, evaluation, training, and result reproduction. Point examples at lerobot/smolvla_vlabench. Add a benchmark banner image. Remove outdated / misleading references to upstream evaluation tracks. Document manual install flow instead of a broken vlabench extra. Packaging cleanup Remove the unresolvable vlabench extra from pyproject.toml. Remove the no-op VLABench processor step. Remove the obsolete env unit test that only covered the dropped gripper remap helper. Apply formatting / logging / style cleanup from review feedback. Why this is needed VLABench is not currently consumable as a normal Python dependency and requires several upstream workarounds: no PyPI release, missing package declarations, undeclared runtime deps, SSH-only submodule references, asset downloads outside normal package install flow, registry population that depends on import side effects, env outputs that do not always match declared observation shapes, task resets that can diverge under some random layouts. This PR makes the benchmark usable in LeRobot despite those constraints, and ensures CI runs are reproducible and informative. If you want a much shorter squash commit message, I’d use this: feat(sim): integrate VLABench benchmark with CI, Docker, and docs Add VLABench as a new LeRobot simulation benchmark, following the existing LIBERO / MetaWorld patterns. This includes: LeRobot env integration and task exposure, CI smoke eval with lerobot/smolvla_vlabench, Docker install and asset-download fixes, runtime fixes for registry loading, assets, camera obs, action handling, dm_control IK, and PhysicsError recovery, alignment of obs/action semantics with HF VLABench datasets, docs and packaging cleanup. The PR also incorporates review feedback, improves reproducibility by pinning upstream commits, and makes VLABench usable in CI despite upstream packaging and asset-management issues. |
||
|
Pepijn
|
a07f22e22c |
feat(envs): add LIBERO-plus robustness benchmark (#3313)
* feat(envs): add LIBERO-plus robustness benchmark integration
- LiberoPlusEnv config (subclass of LiberoEnv, same gym interface)
- Docker image installing LIBERO-plus fork via PYTHONPATH
- CI workflow: 1-episode smoke eval with pepijn223/smolvla_libero_plus
- pyproject.toml: libero_plus extra
* fix(libero): use suite's perturbation-aware init_states loader
LIBERO-plus's Benchmark class exposes a `get_task_init_states(i)` method that
strips perturbation suffixes (`_table_N`, `_tb_N`, `_view_`, `_language_`,
`_light_`, `_add_`, `_level`) and loads the underlying base `.pruned_init`
file — the on-disk name for a perturbation variant doesn't exist as a file,
only the base does. lerobot's loader was bypassing that logic and trying to
read the suffix-bearing filename directly, which failed for every non-zero
task id and killed the eval before any rollout video could be written.
Delegate to the suite's method when it exists; fall back to the path-based
loader for vanilla LIBERO (which does not provide the method).
Also drop the hf-libero install + init_files copy from the LIBERO-plus
Dockerfile — the LIBERO-plus clone already ships both `bddl_files/` and
`init_files/` for all five suites, so the copy was unnecessary and the
`cp -r` into an existing dir produced a confusing nested layout.
* fix(libero): resolve LIBERO-plus perturbation init_states path ourselves
Delegating to `task_suite.get_task_init_states(i)` works for path resolution
but LIBERO-plus's method calls `torch.load(path)` without `weights_only=False`,
which fails on PyTorch 2.6+ because the pickled init_states contains numpy
objects not in the default allowlist:
_pickle.UnpicklingError: Weights only load failed.
WeightsUnpickler error: Unsupported global:
GLOBAL numpy.core.multiarray._reconstruct was not an allowed global.
Mirror LIBERO-plus's suffix-stripping logic (`_table_N`, `_tb_N`, `_view_`,
`_language_`, `_light_`, `_add_`, `_level`) in our own helper so we can pass
`weights_only=False` ourselves. Vanilla LIBERO task names don't contain any
of these patterns except for `_table_` when followed by the word `center`
(e.g. `pick_up_the_black_bowl_from_table_center_...`), and the regex
requires `_table_\\d+` so semantic uses are preserved.
* fix(libero-plus): download perturbation assets from Sylvest/LIBERO-plus
LIBERO-plus's bddl_base_domain.py resolves scene XMLs with
`os.path.join(DIR_PATH, "../assets")`, so the `assets` key in config.yaml
has no effect on scene lookup — MuJoCo always opens
`<clone>/libero/libero/assets/scenes/...`. With no such directory present,
every perturbation task fails on:
FileNotFoundError: No such file or directory:
.../libero-plus/libero/libero/assets/scenes/tabletop_table_Cobblestone01_GLOSS_6K.xml
These textures, views, and extra objects ship only in the 6.4 GB `assets.zip`
published at `Sylvest/LIBERO-plus` (the LIBERO-plus README explicitly says
to download and unzip it into the package dir). Fetch it via `hf_hub_download`,
unzip into `${LIBERO_PLUS_ROOT}/`, install `unzip`, and point config.yaml at
the extracted dir so everything stays consistent. The download lives in its
own Docker layer so subsequent rebuilds reuse the cached assets.
Drops the lerobot/libero-assets snapshot_download — that mirror only has
vanilla LIBERO textures and is ignored for scene loading anyway.
* fix(libero-plus): flatten deep path prefix from Sylvest/LIBERO-plus assets.zip
The 6.4 GB zip ships with every entry prefixed by
`inspire/hdd/project/embodied-multimodality/public/syfei/libero_new/release/dataset/LIBERO-plus-0/assets/...`
(the author's internal filesystem layout, not the layout the LIBERO-plus
README promises), so the previous `unzip -d ${LIBERO_PLUS_ROOT}/` created
`${LIBERO_PLUS_ROOT}/inspire/.../assets/` — robosuite still opened
`${LIBERO_PLUS_ROOT}/assets/scenes/tabletop_table_Cobblestone01_GLOSS_6K.xml`
and hit the same FileNotFoundError.
Extract to a scratch dir, then `mv` the nested `assets/` subtree to the
expected location. Verified the target file exists in the zip central
directory under that exact prefix.
* refactor(libero): inline init_states resolver behind single regex
Collapse the three-style suffix stripper (split/re.sub/in) into one
compiled regex, drop the (Path, bool) tuple return, and move the
`_add_`/`_level` reshape branch into the caller so each branch loads
its own file and returns directly. Net: -11 lines, one fewer helper.
* refactor(libero-plus): rebase docker image on huggingface/lerobot-gpu
Mirror the libero/metaworld/robomme pattern: start from the nightly GPU
image (apt deps, python, uv, venv, lerobot[all] already there) and only
layer on what LIBERO-plus uniquely needs — its wand/ImageMagick build
deps, the non-extra runtime pips (robosuite==1.4.1, bddl, …), the
PYTHONPATH-shadowed fork, and the 6.4 GB assets.zip.
Drops ~50 lines of duplicated base setup (CUDA FROM, apt python, uv
install, user creation, venv init) the nightly already provides.
123 → 73 lines.
Also:
- Add libero_plus to docs/source/_toctree.yml under Benchmarks so
doc-builder's TOC integrity check stops failing.
- Repoint the docs dataset link from pepijn223/libero_plus_lerobot to
the canonical lerobot/libero_plus.
- Revert the stray uv.lock churn (revision/marker diff that crept in
from an unrelated resolve — unrelated to LIBERO-plus).
* fix(libero-plus): stop touching pyproject + uv.lock
The fast-tests job was rejecting the branch because pyproject.toml had a
[libero_plus] extra whose git dep wasn't represented in uv.lock.
The Docker image no longer needs the extra — it clones LIBERO-plus
directly and PYTHONPATH-shadows hf-libero. Drop [libero_plus] from
pyproject and restore pyproject.toml + uv.lock to exactly what's on
origin/main, so `uv sync --locked --extra test` is a no-op for this PR.
Also repoint the doc/CI/env comments that still mentioned the extra at
the Docker install path.
* fix(libero-plus): strip perturbation metadata from task descriptions
LIBERO-plus builds task.language by space-joining the perturbation-variant
filename, so every non-_language_ variant inherits a trailing blob like
"view 0 0 100 0 0 initstate 0 noise 45" or "add 16". That shows up in the
dashboard video labels and no longer matches the base instruction stored
in the training dataset.
Strip those tokens in extract_task_descriptions.py with an end-anchored
regex over the {view,initstate,noise,add,tb,table,light,level}(+digits)
vocabulary. The anchor preserves mid-sentence literal uses of those words
(e.g. "from table center and place it on the plate") — only the trailing
metadata chain is removed. _language_ variants carry real BDDL-sourced
text and are left untouched.
* ci: point benchmark eval checkpoints at the lerobot/ org mirrors
pepijn223/smolvla_* → lerobot/smolvla_* across every benchmark job in
this branch (libero, metaworld, and the per-branch benchmark). The
checkpoints were mirrored into the lerobot/ org and that's the canonical
location going forward.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: integrate PR #3313 review feedback
- docs: fix paper link to arxiv, add benchmark image, add suite descriptions,
add LIBERO-plus replacement warning, restructure eval section to match
LIBERO doc style, fix policy I/O section, remove false try/except claim
- docker: fix shell grouping for hf-libero uninstall, replace hardcoded
asset path with dynamic find
- ci: add Docker Hub login step, add HF_USER_TOKEN guard on eval step
- envs: add is_libero_plus param to get_task_init_states so vanilla LIBERO
always takes the simple path
* fix(docs): use correct LIBERO-plus teaser image URL
* ci(libero-plus): drop redundant hf auth login step
The standalone login step ran `hf auth login` in a throwaway
`docker run --rm` container, so no credentials persisted. Auth is
already performed inside the eval step's container. Removing the
redundant step per PR #3313 review feedback.
* fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs
Port of #3416 onto this branch. Without these attributes eval crashes
when calling `env.unwrapped.metadata["render_fps"]` with async vector
envs. Adds `metadata` / `unwrapped` to `_LazyAsyncVectorEnv` and
caches the metadata alongside obs/action spaces in the LIBERO and
MetaWorld factories.
* ci: gate Docker Hub login on secret availability
Fork PRs cannot access `secrets.DOCKERHUB_LEROBOT_{USERNAME,PASSWORD}`,
which made every benchmark job fail at the login step before any of
the actual build/eval work could run. Gate the login on the env-var
expansion of the username so the step is skipped (not failed) when
secrets are absent. Mirrors the existing pattern in the VLABench job.
* Update .github/workflows/benchmark_tests.yml
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update scripts/ci/extract_task_descriptions.py
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update .github/workflows/benchmark_tests.yml
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update docker/Dockerfile.benchmark.libero_plus
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* Update .github/workflows/benchmark_tests.yml
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
* fix(libero-plus): address review feedback
* ci(libero-plus): fix YAML indentation in upload-artifact steps
The `uses:` key on two upload-artifact steps was at column 0 instead
of nested under the step, causing `pre-commit run check-yaml` to fail
with "expected <block end>, but found '<block mapping start>'".
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
|
||
|
Pepijn
|
282c31cfef |
feat(envs): add RoboMME benchmark (#3311)
* feat(envs): add RoboMME benchmark integration - RoboMME env wrapper with image/wrist_image/state observations - Docker image with Vulkan, SAPIEN, mani-skill deps - CI workflow: 1-episode smoke eval with pepijn223/smolvla_robomme - preprocess_observation: handle image/wrist_image/state keys - pyproject.toml: robomme extra Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor(docker): rebase RoboMME image on huggingface/lerobot-gpu Mirror the libero/metaworld pattern: start from the nightly GPU image (which already has apt deps, uv, venv, and lerobot[all] preinstalled) and only layer on what RoboMME uniquely needs — the Vulkan libs ManiSkill/SAPIEN requires, plus the robomme extra with the gymnasium/numpy overrides. Drops 48 lines of duplicated base setup (CUDA FROM, python install, user creation, venv init, base apt deps) that the nightly image already provides. Net: 102 → 54 lines. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs(robomme): drop prototype-branch note and move dataset to lerobot/robomme - Remove the "Related work" block referencing the prototype branch feat/robomme-integration; the PR stands on its own. - Point all dataset references at lerobot/robomme (docs, env module docstring, RoboMMEEnvConfig docstring) — this is the canonical HF location once the dataset is mirrored. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(robomme): make docs build + fast tests green 1. Docs: add robomme to _toctree.yml under Benchmarks so doc-builder's TOC integrity check stops rejecting the new page. 2. Fast tests: robomme's mani-skill transitively pins numpy<2 which is unsatisfiable against the project's numpy>=2 base pin, so `uv sync` couldn't resolve a universal lockfile. Drop robomme as a pyproject extra entirely — it truly cannot coexist with the rest of the dep tree. The Dockerfile installs robomme directly from its git URL via `uv pip install --override`, which was already the runtime path. pyproject, docs, env docstrings, and the CI job comment all now point to the docker-only install. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(robomme): realign unit tests with current env API The tests were written against an earlier env layout and never updated when the wrapper was refactored, so CI's fast-test job was failing with: - KeyError: 'front_rgb' / 'wrist_rgb' — these were renamed to the lerobot-canonical 'image' / 'wrist_image' keys (matching the dataset columns and preprocess_observation's built-in fallbacks). - AssertionError: 'robomme' not in result — create_robomme_envs now returns {task_name: {task_id: env}}, not {'robomme': {...}}, so comma-separated task lists work. - ModuleNotFoundError: lerobot.envs.lazy_vec_env — LazyVectorEnv was removed; create_robomme_envs is straightforward synchronous now. Rewrite the 7 failing cases against the current API, drop the three LazyVectorEnv tests, and add a multi-task test so the new comma-separated task parsing is covered. Stub install/teardown is moved into helpers (`_install_robomme_stub` / `_uninstall_robomme_stub`) so individual tests stop repeating six boilerplate lines. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ci: point benchmark eval checkpoints at the lerobot/ org mirrors pepijn223/smolvla_* → lerobot/smolvla_* across every benchmark job in this branch (libero, metaworld, and the per-branch benchmark). The checkpoints were mirrored into the lerobot/ org and that's the canonical location going forward. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: integrate PR #3311 review feedback - envs: rename obs keys to pixels/image, pixels/wrist_image, agent_pos - envs: add __post_init__ for dynamic action_dim in RoboMMEEnv config - envs: remove special-case obs conversion in utils.py (no longer needed) - ci: add Docker Hub login, HF_USER_TOKEN guard, --env.task_ids=[0] - scripts: extract_task_descriptions supports multiple task_ids - docs: title to # RoboMME, add image, restructure eval section - tests: update all key assertions to match new obs naming Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(docs): use correct RoboMME teaser image URL Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ci(robomme): smoke-eval 10 tasks instead of 5 Broader coverage on the RoboMME benchmark CI job: bump the smoke eval from 5 tasks to 10 (one episode each), all drawn from ROBOMME_TASKS. Tasks now run: PickXtimes, BinFill, StopCube, MoveCube, InsertPeg, SwingXtimes, VideoUnmask, ButtonUnmask, PickHighlight, PatternLock. Updated the parse_eval_metrics.py `--task` label from the single `PickXtimes` stub to the full comma list so the metrics artifact reflects what was actually run. `parse_eval_metrics.py` already reads `overall` for multi-task runs, so no parser change is needed. Made-with: Cursor * fix(robomme): nest `pixels` as a dict so preprocess_observation picks it up `_convert_obs` was returning flat keys (`pixels/image`, `pixels/wrist_image`). `preprocess_observation()` in envs/utils.py keys off the top-level `"pixels"` entry and, not finding it, silently dropped every image from the batch. The policy then saw zero image features and raised ValueError: All image features are missing from the batch. Match the LIBERO layout: return `{"pixels": {"image": ..., "wrist_image": ...}, "agent_pos": ...}` and declare the same shape in `observation_space`. Made-with: Cursor * fix(robomme): align docs and tests with nested pixels obs layout Addresses PR #3311 review feedback: - Docs: correct observation keys to `pixels/image` / `pixels/wrist_image` (mapped to `observation.images.image` / `observation.images.wrist_image`) and drop the now-obsolete column-rename snippet. - Tests: assert `result["pixels"]["image"]` instead of flat `pixels/image`, matching the nested layout required by `preprocess_observation()`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs Port of #3416 onto this branch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ci: gate Docker Hub login on secret availability Fork PRs cannot access `secrets.DOCKERHUB_LEROBOT_{USERNAME,PASSWORD}`, which made every benchmark job fail at the login step. Gate the login on the env-var expansion of the username so the step is skipped (not failed) when secrets are absent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(robomme): address review feedback --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Pepijn
|
0f1c9b0851 |
feat(envs): add RoboTwin 2.0 benchmark (#3315)
* feat(envs): add RoboTwin 2.0 benchmark integration
- RoboTwinEnvConfig with 4-camera setup (head/front/left_wrist/right_wrist)
- Docker image with SAPIEN, mplib, CuRobo, pytorch3d (Python 3.12)
- CI workflow: 1-episode smoke eval with pepijn223/smolvla_robotwin
- RoboTwinProcessorStep for state float32 casting
- Camera rename_map: head_camera/front_camera/left_wrist -> camera1/2/3
* fix(robotwin): re-enable autograd for CuRobo planner warmup and take_action
lerobot_eval wraps the full rollout in torch.no_grad() (lerobot_eval.py:566),
but RoboTwin's setup_demo → load_robot → CuroboPlanner(...) runs
motion_gen.warmup(), which invokes Newton's-method trajectory optimization.
That optimizer calls cost.backward() internally, which raises
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
when autograd is disabled. take_action() hits the same planner path at every
step. Wrap both setup_demo and take_action in torch.enable_grad() so CuRobo's
optimizer can build its computation graph. Policy inference is unaffected —
rollout()'s inner torch.inference_mode() block around select_action() is
untouched, so we still don't allocate grad buffers during policy forward.
* fix(robotwin): read nested get_obs() output and use aloha-agilex camera names
RoboTwin's base_task.get_obs() returns a nested dict:
{"observation": {cam: {"rgb": ..., "intrinsic_matrix": ...}},
"joint_action": {"left_arm": ..., "left_gripper": ...,
"right_arm": ..., "right_gripper": ...,
"vector": np.ndarray},
"endpose": {...}}
Our _get_obs was reading raw["{cam}_rgb"] / raw["{cam}"] and raw["joint_action"]
as if they were flat, so np.asarray(raw["joint_action"], dtype=float64) tripped
on a dict and raised
TypeError: float() argument must be a string or a real number, not 'dict'
Fix:
- Pull images from raw["observation"][cam]["rgb"]
- Pull joint state from raw["joint_action"]["vector"] (the flat array)
- Update the default camera tuple to (head_camera, left_camera, right_camera)
to match RoboTwin's actual wrist-camera names (envs/camera/camera.py:135-151)
* refactor(robotwin): drop defensive dict guards, cache black fallback frame
_get_obs was guarding every dict access with isinstance(..., dict) in case
RoboTwin's get_obs returned something else — but the API contract
(envs/_base_task.py:437) always returns a dict, so the guards were silently
masking real failures behind plausible-looking zero observations. Drop them.
Also:
- Cache a single black fallback frame in __init__ instead of allocating
a fresh np.zeros((H, W, 3), uint8) for every missing camera on every
step — the "camera not exposed" set is static per env.
- Only allocate the zero joint_state on the fallback path (not unconditionally
before the real value overwrites it).
- Replace .flatten() with .ravel() (no copy when already 1-D).
- Fold the nested-dict schema comment and two identical torch.enable_grad()
rationales into a single Autograd section in the class docstring.
- Fix stale `left_wrist` camera name in the observation docstring.
* fix(robotwin): align observation_space dims with D435 camera output
lerobot_eval crashed in gym.vector's SyncVectorEnv.reset with:
ValueError: Output array is the wrong shape
because RoboTwinEnvConfig declared observation_space = (480, 640, 3) but
task_config/demo_clean.yml specifies head_camera_type=D435, which renders
(240, 320, 3). gym.vector.concatenate pre-allocates a buffer from the
declared space, so the first np.stack raises on shape mismatch.
Changes:
- Config defaults now 240×320 (the D435 dims in _camera_config.yml), with
a comment pointing at the source of truth.
- RoboTwinEnv.__init__ accepts observation_height/width as Optional and
falls back to setup_kwargs["head_camera_h/w"] so the env is self-consistent
even if the config is not in sync.
- Config camera_names / features_map use the actual aloha-agilex camera
names (head_camera, left_camera, right_camera). Drops the stale
"front_camera" and "left_wrist"/"right_wrist" entries that never matched
anything RoboTwin exposes.
- CI workflow's rename_map updated to match the new camera names.
* fix(robotwin): expose _max_episode_steps for lerobot_eval.rollout
rollout() does `env.call("_max_episode_steps")` (lerobot_eval.py:157) to
know when to stop stepping. LiberoEnv and MetaworldEnv set this attribute;
RoboTwinEnv was tracking the limit under `episode_length` only, so the call
raised AttributeError once CuRobo finished warming up.
* fix(robotwin): install av-dep so lerobot_eval can write rollout MP4s
write_video (utils/io_utils.py:53) lazily imports PyAV via require_package
and raises silently inside the video-writing thread when the extra is not
installed — so the eval itself succeeds with pc_success=100 but no MP4
ever lands in videos/, and the artifact upload reports "No files were
found". Add av-dep to the install line (same pattern as the RoboMME image).
* feat(robotwin): eval 5 diverse tasks per CI run with NL descriptions
Widen the smoke eval from a single task (beat_block_hammer) to five:
click_bell, handover_block, open_laptop, stack_blocks_two on top of the
original. Each gets its own rollout video in videos/<task>_0/ so the
dashboard can surface visually distinct behaviours.
extract_task_descriptions.py now has a RoboTwin branch that reads
`description/task_instruction/<task>.json` (already shipped in the clone
at /opt/robotwin) and pulls the `full_description` field. CI cds into
the clone before invoking the script so the relative path resolves.
parse_eval_metrics.py is invoked with the same 5-task list so the
metrics.json embeds one entry per task.
* ci: point benchmark eval checkpoints at the lerobot/ org mirrors
pepijn223/smolvla_* → lerobot/smolvla_* across every benchmark job in
this branch (libero, metaworld, and the per-branch benchmark). The
checkpoints were mirrored into the lerobot/ org and that's the canonical
location going forward.
* refactor(robotwin): rebase docker image on huggingface/lerobot-gpu
Mirror the libero/metaworld/libero_plus/robomme pattern: start from the
nightly GPU image (apt deps, python, uv, venv, lerobot[all] already
there) and layer on only what RoboTwin 2.0 uniquely needs —
cuda-nvcc + cuda-cudart-dev (CuRobo builds from source), Vulkan libs +
NVIDIA ICD (SAPIEN renderer), sapien/mplib/open3d/pytorch3d/curobo
installs, the mplib + sapien upstream patches, and the TianxingChen
asset download.
Drops ~90 lines of duplicated base setup (CUDA FROM, apt python, uv
install, user creation, venv init, base lerobot install). 199 → 110.
Also repoint the docs + env docstring dataset link from
hxma/RoboTwin-LeRobot-v3.0 to the canonical lerobot/robotwin_unified.
* docs(robotwin): add robotwin to _toctree.yml under Benchmarks
doc-builder's TOC integrity check was rejecting the branch because
docs/source/robotwin.mdx existed but wasn't listed in _toctree.yml.
* fix(robotwin): defer YAML lookup and realign tests with current API
__init__ was eagerly calling _load_robotwin_setup_kwargs just to read
head_camera_h/w from the YAML. That import (`from envs import CONFIGS_PATH`)
required a real RoboTwin install, so constructing the env — and thus every
test in tests/envs/test_robotwin.py — blew up with ModuleNotFoundError
on fast-tests where RoboTwin isn't installed.
Replace the eager lookup with DEFAULT_CAMERA_H/W constants (240×320, the
D435 dims baked into task_config/demo_clean.yml). reset() still resolves
the full setup_kwargs lazily — that's fine because reset() is only
called inside the benchmark Docker image where RoboTwin is present.
Also resync the test file with the current env API:
- mock get_obs() as the real nested {"observation": {cam: {"rgb": …}},
"joint_action": {"vector": …}} shape
- patch both _load_robotwin_task and _load_robotwin_setup_kwargs
(_patch_load → _patch_runtime)
- drop `front_camera` / `left_wrist` from assertions — aloha-agilex
exposes head_camera + left_camera + right_camera, not those
- black-frame test now uses left_camera as the missing camera
- setup_demo call check loosened to the caller-provided seed/is_test
bits (full kwargs include the YAML-derived blob)
* fix: integrate PR #3315 review feedback
- ci: add Docker Hub login step, add HF_USER_TOKEN guard on eval step
- docker: tie patches to pinned versions with removal guidance, remove
unnecessary HF_TOKEN for public dataset, fix hadolint warnings
- docs: fix paper link to arxiv, add teaser image, fix camera names
(4→3 cameras), fix observation dims (480x640→240x320)
* fix(docs): correct RoboTwin 2.0 paper arxiv link
* fix(docs): use correct RoboTwin 2.0 teaser image URL
* fix(docs): use plain markdown image to fix MDX build
* ci(robotwin): smoke-eval 10 tasks instead of 5
Broader coverage on the RoboTwin 2.0 benchmark CI job: bump the smoke
eval from 5 tasks to 10 (one episode each). Added tasks are all drawn
from ROBOTWIN_TASKS and mirror the shape/complexity of the existing
set (simple single-object or single-fixture manipulations).
Tasks now run: beat_block_hammer, click_bell, handover_block,
open_laptop, stack_blocks_two, click_alarmclock, close_laptop,
close_microwave, open_microwave, place_block.
`parse_eval_metrics.py` reads `overall` for multi-task runs so no
parser change is needed. Bumped the step name and the metrics label
to reflect the 10-task layout.
* fix(ci): swap 4 broken RoboTwin tasks in smoke eval
The smoke eval hit two upstream issues:
- `open_laptop`: bug in OpenMOSS/RoboTwin main — `check_success()` uses
`self.arm_tag`, but that attribute is only set inside `play_once()`
(the scripted-expert path). During eval `take_action()` calls
`check_success()` directly, hitting `AttributeError: 'open_laptop'
object has no attribute 'arm_tag'`.
- `close_laptop`, `close_microwave`, `place_block`: not present in
upstream RoboTwin `envs/` at all — our ROBOTWIN_TASKS tuple drifted
from upstream and these names leaked into CI.
Replace the four broken tasks with upstream-confirmed equivalents
that exist both in ROBOTWIN_TASKS and in RoboTwin's `envs/`:
`adjust_bottle`, `lift_pot`, `stamp_seal`, `turn_switch`.
New 10-task smoke set: beat_block_hammer, click_bell, handover_block,
stack_blocks_two, click_alarmclock, open_microwave, adjust_bottle,
lift_pot, stamp_seal, turn_switch.
* fix(robotwin): sync ROBOTWIN_TASKS + doc with upstream (50 tasks)
The local ROBOTWIN_TASKS tuple drifted from upstream
RoboTwin-Platform/RoboTwin. Users passing names like `close_laptop`,
`close_microwave`, `dump_bin`, `place_block`, `pour_water`,
`fold_cloth`, etc. got past our validator (the names were in the
tuple) but then crashed inside robosuite with a confusing error,
because those tasks don't exist in upstream `envs/`.
- Replace ROBOTWIN_TASKS with a verbatim mirror of upstream's
`envs/` directory: 50 tasks as of main (was 60 with many
stale entries). Added a `gh api`-based one-liner comment so
future bumps are mechanical.
- Update the `60 tasks` claims in robotwin.mdx and
RoboTwinEnvConfig's docstring to `50`.
- Replace the stale example-task table in robotwin.mdx with ten
upstream-confirmed examples, and flag `open_laptop` as
temporarily broken (its `check_success()` uses `self.arm_tag`
which is only set inside `play_once()`; eval-mode callers hit
AttributeError).
- Rebuild the "Full benchmark" command with the actual 50-task
list, omitting `open_laptop`.
* test(robotwin): lower task-count floor from 60 to 50
ROBOTWIN_TASKS was trimmed to 50 tasks (see comment in
`src/lerobot/envs/robotwin.py:48`), but the assertion still
required ≥60, causing CI failures. Align the test with the
current upstream task count.
* fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs
Port of #3416 onto this branch.
* ci: gate Docker Hub login on secret availability
* fix: integrate PR #3315 review feedback
- envs(robotwin): default `observation_height/width` in
`create_robotwin_envs` to `DEFAULT_CAMERA_H/W` (240/320) so they
match the D435 dims baked into `task_config/demo_clean.yml`.
- envs(robotwin): resolve `task_config/demo_clean.yml` via
`CONFIGS_PATH` instead of a cwd-relative path; works regardless
of where `lerobot-eval` is invoked.
- envs(robotwin): replace `print()` calls in `create_robotwin_envs`
with `logger.info(...)` (module-level `logger = logging.getLogger`).
- envs(robotwin): use `_LazyAsyncVectorEnv` for the async path so
async workers start lazily (matches LIBERO / RoboCasa / VLABench).
- envs(robotwin): cast `agent_pos` space + joint-state output to
float32 end-to-end (was mixed float64/float32).
- envs(configs): use the existing `_make_vec_env_cls(use_async,
n_envs)` helper in `RoboTwinEnvConfig.create_envs`; drop the
`get_env_processors` override so RoboTwin uses the identity
processor inherited from `EnvConfig`.
- processor: delete `RoboTwinProcessorStep` — the float32 cast now
happens in the wrapper itself, so the processor is redundant.
- tests: drop the `TestRoboTwinProcessorStep` suite; update the
mock obs fixture to use float32 `joint_action.vector`.
- ci: hoist `ROBOTWIN_POLICY` and `ROBOTWIN_TASKS` to job-level
env vars so the task list and policy aren't duplicated across
eval / extract / parse steps.
- docker: pin RoboTwin + CuRobo upstream clones to commit SHAs
(`RoboTwin@0aeea2d6`, `curobo@ca941586`) for reproducibility.
|
||
|
Pepijn
|
e699e52388 |
feat(envs): add RoboCasa365 benchmark integration (#3375)
* feat(envs): add RoboCasa365 benchmark integration Add RoboCasa365 (arXiv:2603.04356) as a new simulation benchmark with 365 everyday kitchen manipulation tasks across 2,500 diverse environments. New files: - src/lerobot/envs/robocasa.py: gym.Env wrapper with deferred env creation, flat 12D action / 16D state vectors, 3-camera support - docs/source/robocasa.mdx: user-facing documentation - docker/Dockerfile.benchmark.robocasa: CI benchmark image Modified files: - src/lerobot/envs/configs.py: RoboCasaEnv config (--env.type=robocasa) - pyproject.toml: robocasa optional dependency group - docs/source/_toctree.yml: sidebar entry - .github/workflows/benchmark_tests.yml: integration test job Refs: https://arxiv.org/abs/2603.04356, https://robocasa.ai Related: huggingface/lerobot#321 * fix(docker): use uv pip to install robocasa in benchmark image The huggingface/lerobot-gpu base image uses `uv` with a venv at /lerobot/.venv — `pip` is not on PATH, so `pip install` fails with "pip: not found". Switch to `uv pip install` which installs into the existing venv. Also drop the @v1.0.0 tag pin from the robocasa git URL since the upstream repo may not have that tag; use default branch instead. * fix(robocasa): editable install + switch to lerobot/smolvla_robocasa - pip install from git omits data files like box_links_assets.json (not declared in package_data). Clone and install editable so the source tree is used at runtime. - Download only tex + fixtures_lw asset types (smoke test doesn't need objaverse/aigen objects). Pipe 'y' to auto-accept download prompt. - Switch CI policy from pepijn223/smolvla_robocasa to lerobot/smolvla_robocasa. * fix(docker): re-install lerobot editably after COPY The nightly huggingface/lerobot-gpu image predates the RoboCasaEnv registration — so `lerobot-eval --env.type=robocasa` fails at argparse with "invalid choice" even after COPY . . overlays the new source. Force an editable reinstall so the venv picks up the current configs.py. * fix(ci): add rename_map for robocasa eval (image* -> camera*) Policy lerobot/smolvla_robocasa expects observation.images.camera1/2/3, but RoboCasaEnv produces observation.images.image/image2/image3. * fix(robocasa): override RoboCasaGymEnv default split (test -> all) RoboCasaGymEnv defaults split="test", but create_env only accepts {None, "all", "pretrain", "target"}, so the out-of-the-box default crashes with ValueError. Always pass "all" when split is None. * fix(docker): also download objs_lw (lightwheel objects) for robocasa Kitchen tasks (e.g. CloseFridge) reference lightwheel object meshes like Stool022/model.xml. fixtures_lw alone isn't enough — we also need objs_lw. Still skipping objaverse/aigen to keep image size down. Made-with: Cursor * feat(robocasa): raw camera names + benchmark-group task shortcuts Align the LeRobot env with RoboCasa's native conventions so policies trained on the upstream datasets don't need a --rename_map at eval time, and expose the standard task groups as first-class --env.task values. - Preserve raw RoboCasa camera names (e.g. robot0_agentview_left) as observation.images.<name> end-to-end. Drops camera_name_mapping and DEFAULT_CAMERA_NAME_MAPPING; features/features_map are now built dynamically from the parsed camera list. - Accept benchmark-group names as --env.task: atomic_seen, composite_seen, composite_unseen, pretrain50/100/200/300. Expanded lazily via robocasa.utils.dataset_registry and auto-sets the split ("target" | "pretrain"). - Update CI smoke-eval rename_map to map raw cam names to the camera1/2/3 keys expected by lerobot/smolvla_robocasa. * docs(robocasa): single-task smolvla train+eval recipe on pepijn223/robocasa_CloseFridge - Rewrite observation section to use raw RoboCasa camera keys (observation.images.robot0_agentview_{left,right}, observation.images.robot0_eye_in_hand). - Add a "Training on a single task" section with a full smolvla training command on pepijn223/robocasa_CloseFridge, plus matching single-task eval command. - Document benchmark-group task shortcuts (atomic_seen, composite_seen, composite_unseen, pretrain50/100/200/300) as valid --env.task values. * fix(robocasa): restrict obj_registries to lightwheel by default CloseFridge (and most kitchen tasks) crashed at reset with `ValueError: Probabilities contain NaN` coming out of `sample_kitchen_object_helper`. RoboCasa's upstream default `obj_registries=("objaverse", "lightwheel")` normalizes per-registry candidate counts as probabilities; when a sampled category has zero mjcf paths in every configured registry (because the objaverse asset pack isn't on disk — ~30GB, skipped by our Docker build), the 0/0 divide yields NaNs and `rng.choice` raises. - Add `obj_registries: list[str] = ["lightwheel"]` to `RoboCasaEnv` config; thread it through `create_robocasa_envs`, `_make_env_fns`, and the gym.Env wrapper to the underlying `RoboCasaGymEnv` (which forwards to `create_env` → `robosuite.make` → kitchen env). - Default matches what `download_kitchen_assets --type objs_lw` actually ships, so the env works out of the box without a 30GB objaverse download. - Document the override (`--env.obj_registries='[objaverse,lightwheel]'`) for users who have downloaded the full asset set. * fix(docker): also download tex_generative for robocasa benchmark RoboCasa's lightwheel kitchen fixtures embed references to `generative_textures/wall/tex*.png` directly in their MuJoCo XML, so `MjModel.from_xml_string` errors out at reset time with "No such file or directory" even when the env is constructed with `generative_textures=None`. The generative textures live under a separate asset registry key (`tex_generative`) in `download_kitchen_assets`, distinct from the base `tex` pack we were already fetching. - Add `tex_generative` to the download list so the fixture XMLs resolve. - Document the remaining omissions (objaverse/aigen, ~30GB) and how the runtime side pairs this with obj_registries=["lightwheel"] to avoid sampling from categories whose assets aren't on disk. * ci(robocasa): smoke-eval 10 atomic tasks instead of 1 Broader coverage in the benchmark CI job: evaluate SmolVLA on ten fixture-centric atomic RoboCasa tasks (one episode each) instead of just CloseFridge. The tasks are all drawn from TARGET_TASKS.atomic_seen and selected to avoid object-manipulation categories that would require the objaverse/aigen asset packs (we only ship objs_lw in the Docker image, paired with obj_registries=["lightwheel"] on the runtime side). Tasks: CloseFridge, OpenCabinet, OpenDrawer, TurnOnMicrowave, TurnOffStove, CloseToasterOvenDoor, SlideDishwasherRack, TurnOnSinkFaucet, NavigateKitchen, TurnOnElectricKettle. `scripts/ci/parse_eval_metrics.py` already handles multi-task output via the `overall` key, so no parser changes needed. Bumped the metrics artifact's task label to `atomic_smoke_10` to reflect the grouping. * fix(pyproject): drop unresolvable robocasa extra robocasa's upstream setup.py hardcodes `lerobot==0.3.3` in install_requires. Exposing it as the `lerobot[robocasa]` extra made uv's dep resolver cycle: `lerobot[robocasa]` -> robocasa -> lerobot (a different version) -> unsolvable. This broke every `uv sync` — even invocations with an unrelated extra like `--extra test` — because uv validates the whole lockfile graph. - Remove the `robocasa` extra from pyproject.toml. Installation instructions in docs/source/robocasa.mdx now walk users through the manual `git clone` + `pip install --no-deps` flow, which matches what the Docker image already does and sidesteps the cyclic dep entirely. - Dockerfile: `uv pip install -e ~/robocasa --no-deps` so the shadowed lerobot==0.3.3 never lands in the image; install robocasa's actual runtime deps (numpy, numba, scipy, mujoco, tianshou, etc.) explicitly. * docs(robocasa): align page with adding_benchmarks template Rework docs/source/robocasa.mdx to follow the standard benchmark doc structure: intro + links + available tasks (with family breakdown and first-class benchmark-group shortcuts) + installation + eval + recommended episodes + policy I/O + training + reproducing results. - Fix the paper link (was pointing at a non-existent arxiv ID). - Surface lerobot/smolvla_robocasa and pepijn223/robocasa_CloseFridge in the top-of-page links so they're findable without reading the training section. - Add an explicit "Object registries" subsection explaining the `--env.obj_registries=[objaverse,lightwheel]` override path. - Add an explicit "Reproducing published results" section pointing at the CI smoke eval. * fix: integrate PR #3375 review feedback - envs(robocasa): hoist the duplicated `_parse_camera_names` helper out of `libero.py` and `robocasa.py` into `envs/utils.py` as the public `parse_camera_names`; call sites updated. - envs(robocasa): give each factory a distinct `episode_index` (`0..n_envs-1`) and derive a per-worker seed series in `reset()` so n_envs workers don't all roll the same scene under a shared outer seed. - envs(robocasa): drop the unused `**kwargs` on `_make_env`; declare `visualization_height` / `visualization_width` on both the wrapper and the `RoboCasaEnv` config + propagate via `gym_kwargs`. - envs(robocasa): emit `info["final_info"]` on termination (matching MetaWorld) so downstream vector-env auto-reset keeps the terminal task/success flags. - docs(robocasa): add `--rename_map` (robot0_agentview_left/ eye_in_hand/agentview_right → camera1/2/3) plus CI-parity flags to all three eval snippets. - docker(robocasa): pin robocasa + robosuite git SHAs and the pip dep versions (pygame, Pillow, opencv-python, pyyaml, pynput, tqdm, termcolor, imageio, h5py, lxml, hidapi, gymnasium) for reproducible benchmark images. - ci(robocasa): update the workflow comment — there is no `lerobot[robocasa]` extra; robocasa/robosuite are installed manually because upstream's `lerobot==0.3.3` pin shadows ours. * docs(robocasa): add benchmark banner image * fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs Port of #3416 onto this branch. Also threads the cached metadata through the RoboCasa factory so async eval on `--env.type=robocasa` keeps the same improvement. * fix: integrate PR #3375 review feedback (round 2) - envs(robocasa): when the caller passes `seed=None` to `reset()`, fall back to `self.episode_index` for the inner env seed so each worker still samples a distinct trajectory instead of all workers inheriting the same global RNG state. - envs(robocasa): replace the two module-level `print()` calls in `create_robocasa_envs` with `logger.info(...)` via a module-level `logger = logging.getLogger(__name__)`. - ci(robocasa): run `scripts/ci/extract_task_descriptions.py` after the eval so `metrics.json` carries per-task natural-language labels, matching LIBERO / MetaWorld / VLABench jobs. Added a `_robocasa_descriptions()` extractor that splits CamelCase task names into word-level labels keyed by `<task>_0`. |
||
|
Haoming Song
|
b2765b39b8 |
Cache lazy async env metadata for eval (#3416)
Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> |
||
|
Defalt
|
5c43fa1cce |
fix(policies): replace deprecated torch.cuda.amp.autocast with torch.amp.autocast (#3167)
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> |
||
|
k1000dai
|
3f16d98a9b |
episods→episodes (#3410)
Fixing typo |
||
|
whats2000
|
52f508c51c | fix(dataset): cleanup_interrupted_episode wipes image temp dirs (#3405) | ||
|
Steven Palma
|
a8b72d9615 |
feat(dataset): 2x faster dataloader via parallel decode, uint8 transport, and persistent workers (#3406)
* feat(dataset): 2xfaster dataloader * fix(dataset): streaming return uint8 decode * fix(tests): adjust normalization step comparison * fix(dataset): with threadexecutor + False default * chore(dataset): make it a config * fix(test): account for uint8 in training path testing |