ユーザ選好による二足歩行ロボットの制御ゲイン学習
Learning Controller Gains on Bipedal Walking Robots via User Preferences
ユーザの選好を繰り返し問い合わせる選好ベース学習で、CLFベース非線形制御器のゲインをオンライン最適化し、AMBERとCassieで安定な歩行を実現した。
著者: Noel Csomay-Shanklin, Maegan Tucker, Min Dai, Jenna Reher, Aaron D. Ames
分類: cs.RO
原文アブストラクト
Experimental demonstration of complex robotic behaviors relies heavily on finding the correct controller gains. This painstaking process is often completed by a domain expert, requiring deep knowledge of the relationship between parameter values and the resulting behavior of the system. Even when such knowledge is possessed, it can take significant effort to navigate the nonintuitive landscape of possible parameter combinations. In this work, we explore the extent to which preference-based learning can be used to optimize controller gains online by repeatedly querying the user for their preferences. This general methodology is applied to two variants of control Lyapunov function based nonlinear controllers framed as quadratic programs, which provide theoretical guarantees but are challenging to realize in practice. These controllers are successfully demonstrated both on the planar underactuated biped, AMBER, and on the 3D underactuated biped, Cassie. We experimentally evaluate the performance of the learned controllers and show that the proposed method is repeatably able to learn gains that yield stable and robust locomotion.
