Human-in-the-Loop Robot Planning with Non-Contextual Bandit Feedback

摘要

In this paper, we consider robot navigation problems in environments populated by humans. The goal is to determine safe trajectories that also maximize human satisfaction. In practice, human satisfaction is subjective and hard to describe mathematically. As a result, the planning problem we consider in this paper may lack important contextual information. To address this challenge, we propose a semi-supervised Bayesian Optimization (BO) method to design globally optimal robot trajectories using bandit human feedback, in the form of complaints or satisfaction ratings, that expresses how desirable a trajectory is. We demonstrate the efficiency of our proposed trajectory planning method in a simulated scenario where humans have diversified and unknown demands.