Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thumm, Jakob, Frei, Marian, Ni, Tianle, Althoff, Matthias, Pavone, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909045377466368
author Thumm, Jakob
Frei, Marian
Ni, Tianle
Althoff, Matthias
Pavone, Marco
author_facet Thumm, Jakob
Frei, Marian
Ni, Tianle
Althoff, Matthias
Pavone, Marco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15221
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees
Thumm, Jakob
Frei, Marian
Ni, Tianle
Althoff, Matthias
Pavone, Marco
Robotics
Computer Vision and Pattern Recognition
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.
title Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.15221