Household robots learn to plan safely around contamination risks
HygieneRoboBench: Benchmarking Hygiene-Aware Planning for Household Robots
RoboticsArtificial Intelligence
Summary
When household robots touch dirty things, they can spread germs or hazards through their tools and surfaces. The authors present a new test called HygieneRoboBench that checks how well robot planners can notice these hygiene risks and make safe plans to avoid spreading contamination. They also introduce a new method called Hygiene-NSP that plans robot actions while keeping things clean and prioritizing user needs. Their tests show this method works better than others to keep tasks safe and cost-effective.
What this means in practice
- •For household robot developers: Evaluate and improve robot task planners to safely handle contamination and user preferences during household chores.
- •For cleaning robot manufacturers: Design robots that dynamically adjust tasks to avoid spreading contamination based on contact history and event changes.$Commercial implications: Enables safer and user-prioritized cleaning robots, enhancing market appeal and compliance with hygiene standards.
Authors
Yurun Chen, Josh Qixuan Sun, Jason Qin, Chengtai Li, Tianyi Wang, Mark Crowley, Wentao Zhu
Abstract
Contact with contaminated objects can spread hazards through a household robot's grippers, tools, and shared surfaces, while new contacts can make an existing plan unsafe. Existing benchmarks do not jointly assess how planners identify hygiene risks from contact history and plan safe continuations after new contact events. Planners must do so within time and resource limits while respecting user priorities. We introduce HygieneRoboBench, with 624 instances across 134 task families, to evaluate safe resolution of household tasks from a given execution history. Tasks capture contamination through two grippers and shared objects, treatment costs, and user priorities. We combine controlled history, profile, and event comparisons with independent plan evaluation. These assess safe resolution, cost efficiency under user priorities, and responses to contact events. Evaluation of LLM-based and symbolic planners shows that safely completing a task does not guarantee the lowest execution costs under the user's priorities. To address this problem, we introduce Hygiene-NSP. It combines LLM-based grounding, contact-history reconstruction, and CP-SAT to jointly plan hygiene treatment and task execution under user priorities. Hygiene-NSP achieves safe resolution and optimal safe resolution rates of 94.4% and 90.4%, respectively. Both rates are higher than those of the evaluated baseline planners on the full dataset. Project page: https://euron-zc.github.io/HygieneRoboBench/.