mirror of
https://github.com/huggingface/lerobot.git
synced 2026-06-03 20:31:25 +00:00
12525242ce
- Added `lerobot/scripts/server/find_joint_limits.py` to test the min and max angles of the motion you wish the robot to explore during RL training. - Added logic in `manipulator.py` to limit the maximum possible joint angles to allow motion within a predefined joint position range. The limits are specified in the yaml config for each robot. Checkout the so100.yaml. Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
101 lines
4.0 KiB
Python
101 lines
4.0 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
import einops
|
|
import numpy as np
|
|
import torch
|
|
from torch import Tensor
|
|
|
|
|
|
def preprocess_observation(observations: dict[str, np.ndarray]) -> dict[str, Tensor]:
|
|
"""Convert environment observation to LeRobot format observation.
|
|
Args:
|
|
observation: Dictionary of observation batches from a Gym vector environment.
|
|
Returns:
|
|
Dictionary of observation batches with keys renamed to LeRobot format and values as tensors.
|
|
"""
|
|
# map to expected inputs for the policy
|
|
return_observations = {}
|
|
# TODO: You have to merge all tensors from agent key and extra key
|
|
# You don't keep sensor param key in the observation
|
|
# And you keep sensor data rgb
|
|
for key, img in observations.items():
|
|
if "images" not in key:
|
|
continue
|
|
|
|
if img.ndim == 3:
|
|
img = img.unsqueeze(0)
|
|
# sanity check that images are channel last
|
|
_, h, w, c = img.shape
|
|
assert c < h and c < w, f"expect channel last images, but instead got {img.shape=}"
|
|
|
|
# sanity check that images are uint8
|
|
assert img.dtype == torch.uint8, f"expect torch.uint8, but instead {img.dtype=}"
|
|
|
|
# convert to channel first of type float32 in range [0,1]
|
|
img = einops.rearrange(img, "b h w c -> b c h w").contiguous()
|
|
img = img.type(torch.float32)
|
|
img /= 255
|
|
|
|
return_observations[key] = img
|
|
# obs state agent qpos and qvel
|
|
# image
|
|
|
|
if "environment_state" in observations:
|
|
return_observations["observation.environment_state"] = torch.from_numpy(
|
|
observations["environment_state"]
|
|
).float()
|
|
|
|
# TODO(rcadene): enable pixels only baseline with `obs_type="pixels"` in environment by removing
|
|
# requirement for "agent_pos"
|
|
# return_observations["observation.state"] = torch.from_numpy(observations["agent_pos"]).float()
|
|
return_observations["observation.state"] = observations["observation.state"].float()
|
|
return return_observations
|
|
|
|
|
|
def preprocess_maniskill_observation(observations: dict[str, np.ndarray]) -> dict[str, Tensor]:
|
|
"""Convert environment observation to LeRobot format observation.
|
|
Args:
|
|
observation: Dictionary of observation batches from a Gym vector environment.
|
|
Returns:
|
|
Dictionary of observation batches with keys renamed to LeRobot format and values as tensors.
|
|
"""
|
|
# map to expected inputs for the policy
|
|
return_observations = {}
|
|
# TODO: You have to merge all tensors from agent key and extra key
|
|
# You don't keep sensor param key in the observation
|
|
# And you keep sensor data rgb
|
|
q_pos = observations["agent"]["qpos"]
|
|
q_vel = observations["agent"]["qvel"]
|
|
tcp_pos = observations["extra"]["tcp_pose"]
|
|
img = observations["sensor_data"]["base_camera"]["rgb"]
|
|
|
|
_, h, w, c = img.shape
|
|
assert c < h and c < w, f"expect channel last images, but instead got {img.shape=}"
|
|
|
|
# sanity check that images are uint8
|
|
assert img.dtype == torch.uint8, f"expect torch.uint8, but instead {img.dtype=}"
|
|
|
|
# convert to channel first of type float32 in range [0,1]
|
|
img = einops.rearrange(img, "b h w c -> b c h w").contiguous()
|
|
img = img.type(torch.float32)
|
|
img /= 255
|
|
|
|
state = torch.cat([q_pos, q_vel, tcp_pos], dim=-1)
|
|
|
|
return_observations["observation.image"] = img
|
|
return_observations["observation.state"] = state
|
|
return return_observations
|