ZIPlegged-gym包 14.87MB

m0_58400126

资源文件列表:

legged_gym-master.zip 大约有148个文件
  1. legged_gym-master/
  2. legged_gym-master/.gitattributes 148B
  3. legged_gym-master/.github/
  4. legged_gym-master/.github/ISSUE_TEMPLATE/
  5. legged_gym-master/.github/ISSUE_TEMPLATE/bug_report.md 654B
  6. legged_gym-master/.gitignore 690B
  7. legged_gym-master/LICENSE 1.69KB
  8. legged_gym-master/README.md 7.08KB
  9. legged_gym-master/legged_gym/
  10. legged_gym-master/legged_gym/__init__.py 1.79KB
  11. legged_gym-master/legged_gym/envs/
  12. legged_gym-master/legged_gym/envs/__init__.py 2.71KB
  13. legged_gym-master/legged_gym/envs/a1/
  14. legged_gym-master/legged_gym/envs/a1/a1_config.py 3.62KB
  15. legged_gym-master/legged_gym/envs/anymal_b/
  16. legged_gym-master/legged_gym/envs/anymal_b/anymal_b_config.py 2.2KB
  17. legged_gym-master/legged_gym/envs/anymal_c/
  18. legged_gym-master/legged_gym/envs/anymal_c/anymal.py 4.05KB
  19. legged_gym-master/legged_gym/envs/anymal_c/flat/
  20. legged_gym-master/legged_gym/envs/anymal_c/flat/anymal_c_flat_config.py 3.17KB
  21. legged_gym-master/legged_gym/envs/anymal_c/mixed_terrains/
  22. legged_gym-master/legged_gym/envs/anymal_c/mixed_terrains/anymal_c_rough_config.py 3.8KB
  23. legged_gym-master/legged_gym/envs/base/
  24. legged_gym-master/legged_gym/envs/base/base_config.py 2.56KB
  25. legged_gym-master/legged_gym/envs/base/base_task.py 5.99KB
  26. legged_gym-master/legged_gym/envs/base/legged_robot.py 47.26KB
  27. legged_gym-master/legged_gym/envs/base/legged_robot_config.py 9.82KB
  28. legged_gym-master/legged_gym/envs/cassie/
  29. legged_gym-master/legged_gym/envs/cassie/cassie.py 2.05KB
  30. legged_gym-master/legged_gym/envs/cassie/cassie_config.py 4.6KB
  31. legged_gym-master/legged_gym/scripts/
  32. legged_gym-master/legged_gym/scripts/play.py 5.57KB
  33. legged_gym-master/legged_gym/scripts/train.py 2.14KB
  34. legged_gym-master/legged_gym/tests/
  35. legged_gym-master/legged_gym/tests/test_env.py 2.38KB
  36. legged_gym-master/legged_gym/utils/
  37. legged_gym-master/legged_gym/utils/__init__.py 1.85KB
  38. legged_gym-master/legged_gym/utils/helpers.py 8.86KB
  39. legged_gym-master/legged_gym/utils/logger.py 5.89KB
  40. legged_gym-master/legged_gym/utils/math.py 2.36KB
  41. legged_gym-master/legged_gym/utils/task_registry.py 7.46KB
  42. legged_gym-master/legged_gym/utils/terrain.py 9.09KB
  43. legged_gym-master/licenses/
  44. legged_gym-master/licenses/assets/
  45. legged_gym-master/licenses/assets/ANYmal_b_license.txt 1.42KB
  46. legged_gym-master/licenses/assets/ANYmal_c_license.txt 1.44KB
  47. legged_gym-master/licenses/assets/a1_license.txt 16.33KB
  48. legged_gym-master/licenses/assets/cassie_license.txt 1.06KB
  49. legged_gym-master/licenses/dependencies/
  50. legged_gym-master/licenses/dependencies/matplotlib_license.txt 2.31KB
  51. legged_gym-master/resources/
  52. legged_gym-master/resources/actuator_nets/
  53. legged_gym-master/resources/actuator_nets/anydrive_v3_lstm.pt 16.26KB
  54. legged_gym-master/resources/robots/
  55. legged_gym-master/resources/robots/a1/
  56. legged_gym-master/resources/robots/a1/a1_license.txt 16.33KB
  57. legged_gym-master/resources/robots/a1/meshes/
  58. legged_gym-master/resources/robots/a1/meshes/calf.dae 1.68MB
  59. legged_gym-master/resources/robots/a1/meshes/hip.dae 653.32KB
  60. legged_gym-master/resources/robots/a1/meshes/thigh.dae 1.1MB
  61. legged_gym-master/resources/robots/a1/meshes/thigh_mirror.dae 1.13MB
  62. legged_gym-master/resources/robots/a1/meshes/trunk.dae 4.05MB
  63. legged_gym-master/resources/robots/a1/meshes/trunk_A1.png 70.15KB
  64. legged_gym-master/resources/robots/a1/urdf/
  65. legged_gym-master/resources/robots/a1/urdf/a1.urdf 17.83KB
  66. legged_gym-master/resources/robots/anymal_b/
  67. legged_gym-master/resources/robots/anymal_b/ANYmal_b_license.txt 1.42KB
  68. legged_gym-master/resources/robots/anymal_b/meshes/
  69. legged_gym-master/resources/robots/anymal_b/meshes/anymal_base.dae 8.81MB
  70. legged_gym-master/resources/robots/anymal_b/meshes/anymal_foot.dae 460.54KB
  71. legged_gym-master/resources/robots/anymal_b/meshes/anymal_hip_l.dae 2.37MB
  72. legged_gym-master/resources/robots/anymal_b/meshes/anymal_hip_r.dae 2.37MB
  73. legged_gym-master/resources/robots/anymal_b/meshes/anymal_shank_l.dae 565.5KB
  74. legged_gym-master/resources/robots/anymal_b/meshes/anymal_shank_r.dae 564.31KB
  75. legged_gym-master/resources/robots/anymal_b/meshes/anymal_thigh_l.dae 2.56MB
  76. legged_gym-master/resources/robots/anymal_b/meshes/anymal_thigh_r.dae 2.59MB
  77. legged_gym-master/resources/robots/anymal_b/meshes/base_uv_texture.jpg 648.08KB
  78. legged_gym-master/resources/robots/anymal_b/meshes/carbon_uv_texture.jpg 164.64KB
  79. legged_gym-master/resources/robots/anymal_b/urdf/
  80. legged_gym-master/resources/robots/anymal_b/urdf/anymal_b.urdf 23.81KB
  81. legged_gym-master/resources/robots/anymal_c/
  82. legged_gym-master/resources/robots/anymal_c/ANYmal_c_license.txt 1.44KB
  83. legged_gym-master/resources/robots/anymal_c/meshes/
  84. legged_gym-master/resources/robots/anymal_c/meshes/base.dae 272.28KB
  85. legged_gym-master/resources/robots/anymal_c/meshes/base.jpg 193.8KB
  86. legged_gym-master/resources/robots/anymal_c/meshes/battery.dae 5.21KB
  87. legged_gym-master/resources/robots/anymal_c/meshes/battery.jpg 110.88KB
  88. legged_gym-master/resources/robots/anymal_c/meshes/bottom_shell.dae 1.38MB
  89. legged_gym-master/resources/robots/anymal_c/meshes/bottom_shell.jpg 165.25KB
  90. legged_gym-master/resources/robots/anymal_c/meshes/depth_camera.dae 5.3KB
  91. legged_gym-master/resources/robots/anymal_c/meshes/depth_camera.jpg 185.66KB
  92. legged_gym-master/resources/robots/anymal_c/meshes/drive.dae 27.23KB
  93. legged_gym-master/resources/robots/anymal_c/meshes/drive.jpg 173.85KB
  94. legged_gym-master/resources/robots/anymal_c/meshes/face.dae 812.01KB
  95. legged_gym-master/resources/robots/anymal_c/meshes/face.jpg 294.88KB
  96. legged_gym-master/resources/robots/anymal_c/meshes/foot.dae 115.34KB
  97. legged_gym-master/resources/robots/anymal_c/meshes/foot.jpg 185.21KB
  98. legged_gym-master/resources/robots/anymal_c/meshes/handle.dae 22.14KB
  99. legged_gym-master/resources/robots/anymal_c/meshes/handle.jpg 166.52KB
  100. legged_gym-master/resources/robots/anymal_c/meshes/hatch.dae 9.43KB
  101. legged_gym-master/resources/robots/anymal_c/meshes/hatch.jpg 102.86KB
  102. legged_gym-master/resources/robots/anymal_c/meshes/hip.jpg 226.57KB
  103. legged_gym-master/resources/robots/anymal_c/meshes/hip_l.dae 36.12KB
  104. legged_gym-master/resources/robots/anymal_c/meshes/hip_r.dae 36.24KB
  105. legged_gym-master/resources/robots/anymal_c/meshes/lidar.dae 35.54KB
  106. legged_gym-master/resources/robots/anymal_c/meshes/lidar.jpg 180.25KB
  107. legged_gym-master/resources/robots/anymal_c/meshes/lidar_cage.dae 65.05KB
  108. legged_gym-master/resources/robots/anymal_c/meshes/lidar_cage.jpg 276.1KB
  109. legged_gym-master/resources/robots/anymal_c/meshes/remote.dae 42.31KB
  110. legged_gym-master/resources/robots/anymal_c/meshes/remote.jpg 107.39KB
  111. legged_gym-master/resources/robots/anymal_c/meshes/shank.jpg 164.99KB
  112. legged_gym-master/resources/robots/anymal_c/meshes/shank_l.dae 231.49KB
  113. legged_gym-master/resources/robots/anymal_c/meshes/shank_r.dae 233.65KB
  114. legged_gym-master/resources/robots/anymal_c/meshes/thigh.dae 259.62KB
  115. legged_gym-master/resources/robots/anymal_c/meshes/thigh.jpg 230.57KB
  116. legged_gym-master/resources/robots/anymal_c/meshes/top_shell.dae 1.27MB
  117. legged_gym-master/resources/robots/anymal_c/meshes/top_shell.jpg 213.05KB
  118. legged_gym-master/resources/robots/anymal_c/meshes/wide_angle_camera.dae 20.24KB
  119. legged_gym-master/resources/robots/anymal_c/meshes/wide_angle_camera.jpg 152.19KB
  120. legged_gym-master/resources/robots/anymal_c/urdf/
  121. legged_gym-master/resources/robots/anymal_c/urdf/anymal_c.urdf 53.17KB
  122. legged_gym-master/resources/robots/cassie/
  123. legged_gym-master/resources/robots/cassie/cassie_license.txt 1.06KB
  124. legged_gym-master/resources/robots/cassie/meshes/
  125. legged_gym-master/resources/robots/cassie/meshes/abduction.stl 127.43KB
  126. legged_gym-master/resources/robots/cassie/meshes/abduction_mirror.stl 127.82KB
  127. legged_gym-master/resources/robots/cassie/meshes/achilles-rod.stl 15.02KB
  128. legged_gym-master/resources/robots/cassie/meshes/hip.stl 58.04KB
  129. legged_gym-master/resources/robots/cassie/meshes/hip_mirror.stl 58.04KB
  130. legged_gym-master/resources/robots/cassie/meshes/knee-output.stl 66.63KB
  131. legged_gym-master/resources/robots/cassie/meshes/knee-output_mirror.stl 66.59KB
  132. legged_gym-master/resources/robots/cassie/meshes/pelvis.stl 177.43KB
  133. legged_gym-master/resources/robots/cassie/meshes/plantar-rod.stl 12.58KB
  134. legged_gym-master/resources/robots/cassie/meshes/shin-bone.stl 125.86KB
  135. legged_gym-master/resources/robots/cassie/meshes/shin-bone_mirror.stl 126.25KB
  136. legged_gym-master/resources/robots/cassie/meshes/tarsus.stl 112.97KB
  137. legged_gym-master/resources/robots/cassie/meshes/tarsus_mirror.stl 112.53KB
  138. legged_gym-master/resources/robots/cassie/meshes/thigh.stl 241.15KB
  139. legged_gym-master/resources/robots/cassie/meshes/thigh_mirror.stl 241.15KB
  140. legged_gym-master/resources/robots/cassie/meshes/toe-output-crank.stl 28.06KB
  141. legged_gym-master/resources/robots/cassie/meshes/toe.stl 39.68KB
  142. legged_gym-master/resources/robots/cassie/meshes/toe_mirror.stl 39.68KB
  143. legged_gym-master/resources/robots/cassie/meshes/torso.stl 1.31MB
  144. legged_gym-master/resources/robots/cassie/meshes/yaw.stl 134.46KB
  145. legged_gym-master/resources/robots/cassie/meshes/yaw_mirror.stl 134.6KB
  146. legged_gym-master/resources/robots/cassie/urdf/
  147. legged_gym-master/resources/robots/cassie/urdf/cassie.urdf 16.53KB
  148. legged_gym-master/setup.py 405B

资源介绍:

legged-gym包
# Isaac Gym Environments for Legged Robots # This repository provides the environment used to train ANYmal (and other robots) to walk on rough terrain using NVIDIA's Isaac Gym. It includes all components needed for sim-to-real transfer: actuator network, friction & mass randomization, noisy observations and random pushes during training. **Maintainer**: Nikita Rudin **Affiliation**: Robotic Systems Lab, ETH Zurich **Contact**: rudinn@ethz.ch --- ### :bell: Announcement (09.01.2024) ### With the shift from Isaac Gym to Isaac Sim at NVIDIA, we have migrated all the environments from this work to [Isaac Lab](https://github.com/isaac-sim/IsaacLab). Following this migration, this repository will receive limited updates and support. We encourage all users to migrate to the new framework for their applications. Information about this work's locomotion-related tasks in Isaac Lab is available [here](https://isaac-sim.github.io/IsaacLab/source/features/environments.html#locomotion). --- ### Useful Links ### Project website: https://leggedrobotics.github.io/legged_gym/ Paper: https://arxiv.org/abs/2109.11978 ### Installation ### 1. Create a new python virtual env with python 3.6, 3.7 or 3.8 (3.8 recommended) 2. Install pytorch 1.10 with cuda-11.3: - `pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html` 3. Install Isaac Gym - Download and install Isaac Gym Preview 3 (Preview 2 will not work!) from https://developer.nvidia.com/isaac-gym - `cd isaacgym/python && pip install -e .` - Try running an example `cd examples && python 1080_balls_of_solitude.py` - For troubleshooting check docs `isaacgym/docs/index.html`) 4. Install rsl_rl (PPO implementation) - Clone https://github.com/leggedrobotics/rsl_rl - `cd rsl_rl && git checkout v1.0.2 && pip install -e .` 5. Install legged_gym - Clone this repository - `cd legged_gym && pip install -e .` ### CODE STRUCTURE ### 1. Each environment is defined by an env file (`legged_robot.py`) and a config file (`legged_robot_config.py`). The config file contains two classes: one containing all the environment parameters (`LeggedRobotCfg`) and one for the training parameters (`LeggedRobotCfgPPo`). 2. Both env and config classes use inheritance. 3. Each non-zero reward scale specified in `cfg` will add a function with a corresponding name to the list of elements which will be summed to get the total reward. 4. Tasks must be registered using `task_registry.register(name, EnvClass, EnvConfig, TrainConfig)`. This is done in `envs/__init__.py`, but can also be done from outside of this repository. ### Usage ### 1. Train: ```python legged_gym/scripts/train.py --task=anymal_c_flat``` - To run on CPU add following arguments: `--sim_device=cpu`, `--rl_device=cpu` (sim on CPU and rl on GPU is possible). - To run headless (no rendering) add `--headless`. - **Important**: To improve performance, once the training starts press `v` to stop the rendering. You can then enable it later to check the progress. - The trained policy is saved in `issacgym_anymal/logs/<experiment_name>/<date_time>_<run_name>/model_<iteration>.pt`. Where `<experiment_name>` and `<run_name>` are defined in the train config. - The following command line arguments override the values set in the config files: - --task TASK: Task name. - --resume: Resume training from a checkpoint - --experiment_name EXPERIMENT_NAME: Name of the experiment to run or load. - --run_name RUN_NAME: Name of the run. - --load_run LOAD_RUN: Name of the run to load when resume=True. If -1: will load the last run. - --checkpoint CHECKPOINT: Saved model checkpoint number. If -1: will load the last checkpoint. - --num_envs NUM_ENVS: Number of environments to create. - --seed SEED: Random seed. - --max_iterations MAX_ITERATIONS: Maximum number of training iterations. 2. Play a trained policy: ```python legged_gym/scripts/play.py --task=anymal_c_flat``` - By default, the loaded policy is the last model of the last run of the experiment folder. - Other runs/model iteration can be selected by setting `load_run` and `checkpoint` in the train config. ### Adding a new environment ### The base environment `legged_robot` implements a rough terrain locomotion task. The corresponding cfg does not specify a robot asset (URDF/ MJCF) and has no reward scales. 1. Add a new folder to `envs/` with `'<your_env>_config.py`, which inherit from an existing environment cfgs 2. If adding a new robot: - Add the corresponding assets to `resources/`. - In `cfg` set the asset path, define body names, default_joint_positions and PD gains. Specify the desired `train_cfg` and the name of the environment (python class). - In `train_cfg` set `experiment_name` and `run_name` 3. (If needed) implement your environment in <your_env>.py, inherit from an existing environment, overwrite the desired functions and/or add your reward functions. 4. Register your env in `isaacgym_anymal/envs/__init__.py`. 5. Modify/Tune other parameters in your `cfg`, `cfg_train` as needed. To remove a reward set its scale to zero. Do not modify parameters of other envs! ### Troubleshooting ### 1. If you get the following error: `ImportError: libpython3.8m.so.1.0: cannot open shared object file: No such file or directory`, do: `sudo apt install libpython3.8`. It is also possible that you need to do `export LD_LIBRARY_PATH=/path/to/libpython/directory` / `export LD_LIBRARY_PATH=/path/to/conda/envs/your_env/lib`(for conda user. Replace /path/to/ to the corresponding path.). ### Known Issues ### 1. The contact forces reported by `net_contact_force_tensor` are unreliable when simulating on GPU with a triangle mesh terrain. A workaround is to use force sensors, but the force are propagated through the sensors of consecutive bodies resulting in an undesirable behaviour. However, for a legged robot it is possible to add sensors to the feet/end effector only and get the expected results. When using the force sensors make sure to exclude gravity from the reported forces with `sensor_options.enable_forward_dynamics_forces`. Example: ``` sensor_pose = gymapi.Transform() for name in feet_names: sensor_options = gymapi.ForceSensorProperties() sensor_options.enable_forward_dynamics_forces = False # for example gravity sensor_options.enable_constraint_solver_forces = True # for example contacts sensor_options.use_world_frame = True # report forces in world frame (easier to get vertical components) index = self.gym.find_asset_rigid_body_index(robot_asset, name) self.gym.create_asset_force_sensor(robot_asset, index, sensor_pose, sensor_options) (...) sensor_tensor = self.gym.acquire_force_sensor_tensor(self.sim) self.gym.refresh_force_sensor_tensor(self.sim) force_sensor_readings = gymtorch.wrap_tensor(sensor_tensor) self.sensor_forces = force_sensor_readings.view(self.num_envs, 4, 6)[..., :3] (...) self.gym.refresh_force_sensor_tensor(self.sim) contact = self.sensor_forces[:, :, 2] > 1. ```
100+评论
captcha
    相关资源
    类型标题大小时间
    ZIPDev C++ 6.7.5 red panda 调过77.18MB4月前
    ZIPwow.js+animate.css11.35KB4月前
    ZIPppt截圖asddfffgsdffdfg599.13KB4月前
    ZIPbisai.zip1456789332.29KB4月前
    ZIPWindows端USB设备监控163.79KB4月前
    ZIP122221111111113.48MB4月前
    ZIPACS400-2.2KW变频器图纸115.82KB4月前
    ZIP303009557022761DRV8825步进电机驱动器板-3D打印机（1个）MK658.zip184.14KB4月前