A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy

TL;DR

This paper introduces a quality diversity approach using MAP-Elites to automatically generate diverse human-robot interaction scenarios in shared autonomy, enhancing evaluation and understanding of robotic algorithms.

Contribution

It applies the MAP-Elites algorithm to generate diverse failure scenarios in human-robot shared autonomy, revealing new insights and outperforming traditional search methods.

Findings

MAP-Elites effectively explores scenario space

Generated scenarios confirm and challenge existing theories

Outperforms Monte-Carlo and optimization methods

Abstract

The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applications. Exploring diverse scenarios of humans and robots interacting in simulation can improve understanding of the robotic system and avoid potentially costly failures in real-world settings. We formulate this problem as a quality diversity (QD) problem, where the goal is to discover diverse failure scenarios by simultaneously exploring both environments and human actions. We focus on the shared autonomy domain, where the robot attempts to infer the goal of a human operator, and adopt the QD algorithm MAP-Elites to generate scenarios for two published algorithms in this domain: shared autonomy via hindsight optimization and linear policy blending. Some of the generated scenarios confirm previous theoretical findings, while others are surprising and bring about a new understanding of state-of-the-art implementations. Our experiments show that MAP-Elites outperforms Monte-Carlo simulation and optimization based methods in effectively searching the scenario space, highlighting its promise for automatic evaluation of algorithms in human-robot interaction.