ステレオビジョンを用いた安全臨界制御のための自己教師ありオンライン学習
Self-Supervised Online Learning for Safety-Critical Control using Stereo Vision
ステレオビジョンの不確かさを正解データなしで自己教師あり学習し、オンラインで新環境に適応させて制御バリア関数ベースの制御器を頑健化、四足ロボットで安全性と保守性低減を実証した論文。
著者: Ryan K. Cosner, Ivan D. Jimenez Rodriguez, Tamas G. Molnar, Wyatt Ubellacker, Yisong Yue, Aaron D. Ames, Katherine L. Bouman
分類: cs.RO
原文アブストラクト
With the increasing prevalence of complex vision-based sensing methods for use in obstacle identification and state estimation, characterizing environment-dependent measurement errors has become a difficult and essential part of modern robotics. This paper presents a self-supervised learning approach to safety-critical control. In particular, the uncertainty associated with stereo vision is estimated, and adapted online to new visual environments, wherein this estimate is leveraged in a safety-critical controller in a robust fashion. To this end, we propose an algorithm that exploits the structure of stereo-vision to learn an uncertainty estimate without the need for ground-truth data. We then robustify existing Control Barrier Function-based controllers to provide safety in the presence of this uncertainty estimate. We demonstrate the efficacy of our method on a quadrupedal robot in a variety of environments. When not using our method safety is violated. With offline training alone we observe the robot is safe, but overly-conservative. With our online method the quadruped remains safe and conservatism is reduced.
