Name		Name	Last commit message	Last commit date
__pycache__		__pycache__
legged_gym		legged_gym
licenses		licenses
rsl_rl		rsl_rl
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
adaptivity.py		adaptivity.py
all_radar_adaptivity.jpg		all_radar_adaptivity.jpg
dual_hist_encoder.py		dual_hist_encoder.py
radar_adaptivity.jpg		radar_adaptivity.jpg
radar_adaptivity.png		radar_adaptivity.png
rough_radar_adaptivity.jpg		rough_radar_adaptivity.jpg
setup.py		setup.py
transformer_modelling.py		transformer_modelling.py

Repository files navigation

Reinforcement Learning-based adaptive control for legged robots

Train dual_history policy

python legged_gym/scripts/train_dual.py --headless --task=a1 --sim_device=cuda:0 --rl_device=cuda:0

Evaluation

python legged_gym/scripts/eval.py --headless --task=a1 --sim_device=cuda:0 --rl_device=cuda:0

Radar Ploting

python adaptivity.py <a.pt> <b.pt>

It would be better add some args like --net_type=, --hist_design=,

Metrics Description

Command velocity test
- Fixed lin_vel_x
- Fixed lin_vel_y
Friction test
Add Mass test

About

Personal legged_gym Unitree A1 implementation for paper 'Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control'. Homework repo for SJTU ACM class RL courses

adaptive-control quadruped-robot reinforcement-learning robotics

19 stars

1 watching

Report repository

Releases

Packages

Contributors

Languages