連続時間安全性を保証する遠隔操作模倣学習
Teleoperator Imitation with Continuous-time Safety
縮約理論と二乗和計画法に基づき、実演から多項式ベクトル場として制御則を学習する手法を提案。模倣損失を最小化しつつ連続時間の安全性を保証し、動的障害物への適応と新しい初期・目標姿勢への汎化を実現した。
著者: Bachir El Khadir, Jake Varley, Vikas Sindhwani
分類: cs.RO, math.OC
原文アブストラクト
Learning to effectively imitate human teleoperators, with generalization to unseen and dynamic environments, is a promising path to greater autonomy enabling robots to steadily acquire complex skills from supervision. We propose a new motion learning technique rooted in contraction theory and sum-of-squares programming for estimating a control law in the form of a polynomial vector field from a given set of demonstrations. Notably, this vector field is provably optimal for the problem of minimizing imitation loss while providing continuous-time guarantees on the induced imitation behavior. Our method generalizes to new initial and goal poses of the robot and can adapt in real-time to dynamic obstacles during execution, with convergence to teleoperator behavior within a well-defined safety tube. We present an application of our framework for pick-and-place tasks in the presence of moving obstacles on a 7-DOF KUKA IIWA arm. The method compares favorably to other learning-from-demonstration approaches on benchmark handwriting imitation tasks.
