Learning to walk in confined spaces using 3D representation

Takahiro Miki, Joonho Lee, Lorenz Wellhausen and Marco Hutter This paper is accepted to ICRA2024. Arxiv: Project page: 0:00 Introduction 0:20 Method overview 0:27 Low-level policy training 0:40 Low-level policy testing 1:16 High-level policy training 1:57 High-level policy distillation 2:12 High-level policy testing Abstract: Legged robots have the potential to traverse complex terrain and access confined spaces beyond the reach of traditional platforms thanks to their ability to carefully select footholds and flexibly adapt their body posture while walking. However, robust deployment in real-world applications is still an open challenge. In this paper, we present a method for legged locomotion control using reinforcement learning and 3D volumetric representations to enable robust and versatile locomotion in confined and unstructur