Saved in:
Bibliographic Details
Main Authors: Sheetz, Emily, Zemler, Emma, Savchenko, Misha, Rainen, Connor, Holum, Erik, Graf, Jodi, Albright, Andrew, Azimi, Shaun, Kuipers, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01129
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913971658817536
author Sheetz, Emily
Zemler, Emma
Savchenko, Misha
Rainen, Connor
Holum, Erik
Graf, Jodi
Albright, Andrew
Azimi, Shaun
Kuipers, Benjamin
author_facet Sheetz, Emily
Zemler, Emma
Savchenko, Misha
Rainen, Connor
Holum, Erik
Graf, Jodi
Albright, Andrew
Azimi, Shaun
Kuipers, Benjamin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01129
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-Robot Red Teaming for Safety-Aware Reasoning
Sheetz, Emily
Zemler, Emma
Savchenko, Misha
Rainen, Connor
Holum, Erik
Graf, Jodi
Albright, Andrew
Azimi, Shaun
Kuipers, Benjamin
Robotics
Artificial Intelligence
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.
title Human-Robot Red Teaming for Safety-Aware Reasoning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2508.01129