A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy
This work provides a method for automatically generating diverse and challenging human-robot interaction scenarios, which is crucial for evaluating and improving shared autonomy algorithms for researchers and developers in robotics.
This paper addresses the challenge of automatically generating diverse human-robot interaction scenarios, particularly focusing on failure cases in shared autonomy. By formulating this as a quality diversity problem and using the MAP-Elites algorithm, the authors successfully generated scenarios that confirmed theoretical findings and revealed new insights into state-of-the-art shared autonomy algorithms, outperforming Monte-Carlo and optimization-based methods in scenario space exploration.
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.