Reinforcement learning recently shows great progress on legged robots, while bipedal robots in high dimensions but narrow solution space are still challenging to learn. The typical methods introduce the reference joints motion to guide the learning process; however, obtaining a high-quality reference trajectory is nontrivial, and imitation suffers from the local minimum. For general reference-free scenarios, the bipedal robot is discouraged by the early termination and biased sample collection. Inspired by the assistive learning commonly shown in biped animals, we introduce the assistive force to aid the learning process without the requirement of reference trajectories. The learned assistant could be a curricula to lead motor skills learning and is eliminated in the end to shape the learned motion to be plausible. We analyze the assistive system and verify its effectiveness in multiple challenging bipedal skills (Videos and supplementary materials: https://fanshi14.github.io/me/isrr22.).
Reference-Free Learning Bipedal Motor Skills via Assistive Force Curricula
Springer Proceedings in Advanced Robotics
The International Symposium of Robotics Research ; 2022 ; Geneva, Switzerland September 25, 2022 - September 30, 2022
2023-03-08
17 pages
Article/Chapter (Book)
Electronic Resource
English
NTIS | 2008
|BIPEDAL LOCOMOTION HAVING VARIABLE FOOTHOLD AND BIPEDAL LOCOMOTION ASSEMBLY
European Patent Office | 2017
BIPEDAL LOCOMOTION HAVING VARIABLE FOOTHOLD AND BIPEDAL LOCOMOTION ASSEMBLY
European Patent Office | 2016
|Springer Verlag | 2003
|