Human-Robot Red Teaming for Safety-Aware Reasoning

TL;DR

This paper introduces a human-robot red teaming approach that enables robots to perform safety-aware reasoning through collaborative hazard exploration, improving safety and trust in high-risk environments.

Contribution

It presents a novel red teaming paradigm for safety-aware reasoning, allowing robots and humans to collaboratively identify hazards and enhance safety in diverse environments.

Findings

Human-robot red teaming enables safe task planning.

Robots learn to operate safely in lunar and household environments.

The approach promotes trust in safety-critical domains.

Abstract

While much research explores improving robot capabilities, there is a deficit in researching how robots are expected to perform tasks safely, especially in high-risk problem domains. Robots must earn the trust of human operators in order to be effective collaborators in safety-critical tasks, specifically those where robots operate in human environments. We propose the human-robot red teaming paradigm for safety-aware reasoning. We expect humans and robots to work together to challenge assumptions about an environment and explore the space of hazards that may arise. This exploration will enable robots to perform safety-aware reasoning, specifically hazard identification, risk assessment, risk mitigation, and safety reporting. We demonstrate that: (a) human-robot red teaming allows human-robot teams to plan to perform tasks safely in a variety of domains, and (b) robots with different embodiments can learn to operate safely in two different environments -- a lunar habitat and a household -- with varying definitions of safety. Taken together, our work on human-robot red teaming for safety-aware reasoning demonstrates the feasibility of this approach for safely operating and promoting trust on human-robot teams in safety-critical problem domains.