Humanoid Locomotion on TOCABI Humanoid Robot Forward Walking (vx = 0.25, wyaw = 0.0) Real Robot Deployment
1.972Joint VelocityRegularization Reward
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Regularization RewardCommand Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 1.972 | 0.0271 | 13.74 | 75.11 | 1.81 | |
| GP-LCPCommand Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 1.7551 | 0.0222 | 16.3 | 55.12 | 1.55 | |
| SN$\lambda_{SN}$=0.2, Command Duration (s)=5, Command Steps=1250, Random Seeds=32025.04 | 1.3663 | 0.0206 | 7.43 | 47.96 | 3.15 |