LearningHumanoidWalking
Code for the papers:
-
Learning Bipedal Walking On Planned Footsteps For Humanoid Robots (Humanoids2022)
Rohan P. Singh, Mehdi Benallegue, Mitsuharu Morisawa, Rafael Cisneros, Fumio Kanehiro -
Learning Bipedal Walking for Humanoids with Current Feedback (arxiv)
Rohan P. Singh, Zhaoming Xie, Pierre Gergondet, Fumio Kanehiro
(WIP on branchtopic/omnidirectional-walk)
Code structure:
A rough outline for the repository that might be useful for adding your own robot:
LearningHumanoidWalking/
βββ envs/ <-- Actions and observation space, PD gains, simulation step, control decimation, init, ...
βββ tasks/ <-- Reward function, termination conditions, and more...
βββ rl/ <-- Code for PPO, actor/critic networks, observation normalization process...
βββ models/ <-- MuJoCo model files: XMLs/meshes/textures
βββ trained/ <-- Contains pretrained model for JVRC
βββ scripts/ <-- Utility scripts, etc.
Requirements:
- Python version: 3.7.11
- Pytorch
- pip install:
- mujoco==2.2.0
- mujoco-python-viewer
- ray==1.9.2
- transforms3d
- matplotlib
- scipy
Usage:
Environment names supported:
| Task Description | Environment name |
|---|---|
| Basic Walking Task | 'jvrc_walk' |
| Stepping Task (using footsteps) | 'jvrc_step' |
To train:
$ python run_experiment.py train --logdir <path_to_exp_dir> --num_procs <num_of_cpu_procs> --env <name_of_environment>
To play:
We need to write a script specific to each environment.
For example, debug_stepper.py can be used with the jvrc_step environment.
$ PYTHONPATH=.:$PYTHONPATH python scripts/debug_stepper.py --path <path_to_exp_dir>
What you should see:
Ascending stairs:
Descending stairs:
Walking on curves:
Citation
If you find this work useful in your own research:
@inproceedings{singh2022learning,
title={Learning Bipedal Walking On Planned Footsteps For Humanoid Robots},
author={Singh, Rohan P and Benallegue, Mehdi and Morisawa, Mitsuharu and Cisneros, Rafael and Kanehiro, Fumio},
booktitle={2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)},
pages={686--693},
year={2022},
organization={IEEE}
}