Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control

University of Washington
*Equal advising
Overview of safe human-robot interaction using control barrier functions

Abstract

This paper presents a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control (CRC) to provide formal safety guarantees while considering complex human behavior. Safe deployment of autonomous robots in human environments remains challenging due to the inherent unpredictability in human actions, with traditional approaches either relying on restrictive distributional assumptions or defaulting to overly conservative worse-case bounds. Our approach uses CRC to quantify and control the prediction errors in CBF safety values and establishes formal guarantees on the probability of constraint satisfaction during interaction. We further introduce an online update scheme that dynamically adjusts the safety margins produced by CRC based on the current interaction context. Through experiments in challenging human-robot navigation scenarios, we demonstrate that our approach significantly reduces collision rates and safety violations compared to baseline methods while maintaining high success rates in goal-reaching tasks and efficient control.

Single-Agent Simulations

Generated trajectories from 100 trials
Trajectories generated from 100 single-agent head-on interactions with each method. Red trajectories indicate collisions.

Simulation Comparison

Simulation comparison

Multi-Agent Simulation

Multi-agent simulation comparison
Multi-agent simulation metrics

Appendix

It appears you don't have a PDF plugin for this browser. You can click here to download the PDF file.

BibTeX

@inproceedings{gonzales2025CRCCBF,
  author={Gonzales, Jake and Mizuta, Kazuki and Leung, Karen and Ratliff, Lillian},
  booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title={Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control},
  year={2025},
  note={Under Review}
}

Note: This paper is currently under review at IROS 2025.