ArXiv TLDR

Vision-Based Safe Human-Robot Collaboration with Uncertainty Guarantees

🐦 Tweet
2604.15221

Jakob Thumm, Marian Frei, Tianle Ni, Matthias Althoff, Marco Pavone

cs.ROcs.CV

TLDR

A vision-based framework uses conformal prediction and uncertainty estimation to ensure certifiably safe human-robot collaboration.

Key contributions

  • Proposes a vision-based framework for human pose and motion prediction with safety guarantees.
  • Integrates aleatoric uncertainty estimation and Out-of-Distribution (OOD) detection for high confidence.
  • Uses conformal prediction sets to provide valid, high-confidence human motion predictions for safety.
  • Validated on recorded human motion data and a real-world human-robot collaboration setup.

Why it matters

This paper enhances human-robot collaboration safety by providing robust uncertainty guarantees. Its novel approach allows for certifiable safety, crucial for deploying robots in shared human workspaces. This is vital for industrial and service applications.

Original 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.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.