Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees

TL;DR

This paper introduces a vision-based human pose estimation and motion prediction framework that provides probabilistic safety guarantees for human-robot collaboration using conformal prediction and uncertainty estimation.

Contribution

It combines aleatoric uncertainty estimation with out-of-distribution detection and introduces conformal prediction sets for certifiable safe human motion prediction.

Findings

Framework achieves high probabilistic confidence in predictions.

Evaluated successfully on real-world human-robot interaction data.

Provides safety guarantees in collaborative settings.

Abstract

We propose a framework for vision-based human pose estimation and motion prediction that gives conformal prediction guarantees for certifiably safe human-robot collaboration. Our framework combines aleatoric uncertainty estimation with OOD detection for high probabilistic confidence. To integrate our pipeline in certifiable safety frameworks, we propose conformal prediction sets for human motion predictions with high, valid confidence. We evaluate our pipeline on recorded human motion data and a real-world human-robot collaboration setting.