Surrogate Assisted Generation of Human-Robot Interaction Scenarios

TL;DR

This paper introduces surrogate models to efficiently generate diverse and challenging human-robot interaction scenarios, reducing computational costs and enabling better evaluation of complex systems.

Contribution

It proposes a surrogate-assisted approach for scenario generation in human-robot interaction, improving efficiency and applicability in complex domains.

Findings

Surrogate models accurately predict human and robot behaviors.

Generated scenarios include challenging cases that are reproducible in real-world settings.

Method reduces computational costs compared to traditional simulation-based approaches.

Abstract

As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments and with different users. To this end, previous methods have algorithmically generated diverse scenarios that reveal system failures in a shared control teleoperation task. However, these methods require directly evaluating generated scenarios by simulating robot policies and human actions. The computational cost of these evaluations limits their applicability in more complex domains. Thus, we propose augmenting scenario generation systems with surrogate models that predict both human and robot behaviors. In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios. We demonstrate that these failures are reproducible in real-world interactions.