Guardians as You Fall: Active Mode Transition for Safe Falling

Yikai Wang, Mengdi Xu, Guanya Shi, Ding Zhao

Carnegie Mellon University

[arXiv] [GitHub]

Video

Abstract

Supplement Videos

Reward Terms

Observation Noise & Domain Randomization

Video

Abstract

Recent advancements in optimal control and reinforcement learning have enabled quadrupedal robots to perform a variety of agile locomotion tasks over diverse terrains. During these agile motions, ensuring the stability and resiliency of the robot is a primary concern to prevent catastrophic falls and mitigate potential damages. Previous methods primarily focus on recovery policies after the robot falls. There is no active safe falling solution to the best of our knowledge. In this paper, we proposed Guardians as You Fall (GYF), a safe falling/tumbling and recovery framework that can actively tumble and recover to stable modes to reduce damage in highly dynamic scenarios. The key idea of GYF is to adaptively traverse across different stable modes via active tumbling, before the robot shifts to irrecoverable poses. Via comprehensive simulation and real-world experiments, we show that GYF significantly reduces the maximum acceleration and jerk of the robot base compared to the baselines. In particular, GYF reduces the maximum acceleration and jerk by 20% ∼ 73% in different scenarios in simulation and real-world experiments. GYF offers a new perspective on safe falling and recovery in locomotion tasks, which potentially enables much more aggressive explorations of existing agile locomotion skills.