Building Trustworthy Household Robots through Open-World Safety

Summary

This position paper argues for open-world safety in household robots, meaning safety requirements should hold in unseen situations, including when a robot cannot complete its task. The authors examine why existing safety methods fail, citing misinterpreted context, overlooked past interactions, and unsafe stopping or recovery strategies under unfamiliar conditions. They propose a research agenda to specify, learn, and ground safety requirements, enforce them with reliable recovery, and evaluate how well those protections generalize.

Topics

• Robotics and embodied AI