Utilizing Human Feedback for Primitive Optimization in Wheelchair Tennis

Anonymous

Keywords: Learning from demonstrations and feedback, Movement primitives, Agile Mobile manipulator

TL;DR: We present an evaluation of a learned primitive ground-stroke on a wheelchair tennis robot and propose a method to refine the primitives online through evaluative human feedback.

Abstract: Agile robotics presents a difficult challenge with robots moving at high speeds requiring precise and low-latency sensing and control. Creating agile motion that accomplishes the task at hand while being safe to execute is a key requirement for agile robots to gain human trust. This requires designing new approaches that are flexible and maintain knowledge over world constraints. In this paper, we consider the problem of building a flexible and adaptive controller for a challenging agile mobile manipulation task of hitting ground strokes on a wheelchair tennis robot. We propose and evaluate an extension to the work done on learning striking behaviors using a probabilistic movement primitive (ProMP) framework by (1) demonstrating the safe execution of learned primitives on an agile mobile manipulator setup, and (2) proposing an online primitive refinement procedure that utilizes evaluative feedback from humans on the executed trajectories.