Robust Recovery Motion Control for Quadrupedal Robots via Learned Terrain Imagination

I Made Aswin Nahendra, Minho Oh, Byeongho Yu, Hyungtae Lim, Hyun Myung

Experiment-oriented Locomotion and Manipulation Research Workshop @ Robotics: Science and Systems (RSS)

상세내용

BibTeX

저자 : I Made Aswin Nahendra, Minho Oh, Byeongho Yu, Hyungtae Lim, Hyun Myung
논문명 : Robust Recovery Motion Control for Quadrupedal Robots via Learned Terrain Imagination
학회명 : Experiment-oriented Locomotion and Manipulation Research Workshop @ Robotics: Science and Systems (RSS)
발간년도 : 2023
발간년도 : 2023
발간월 : July
초록 : Quadrupedal robots have emerged as a cutting-edge platform for assisting humans, finding applications in tasks related to inspection and exploration in remote areas. Nevertheless, their floating base structure renders them susceptible to fall in cluttered environments, where manual recovery by a human operator may not always be feasible. Several recent studies have presented recovery controllers employing deep reinforcement learning algorithms. However, these controllers are not specifically designed to operate effectively in cluttered environments, such as stairs and slopes, which restricts their applicability. In this study, we propose a robust all-terrain recovery policy to facilitate rapid and secure recovery in cluttered environments. We substantiate the superiority of our proposed approach through simulations and real-world tests encompassing various terrain types.

첨부파일

목록