Learning to Nudge: A Scalable Barrier Function Framework for Safe Robot Interaction in Dense Clutter

2026-01-06

arXiv.org

AI Summary

This work addresses the challenge of enabling robots to safely perform contact-rich interactions in dense, cluttered environments, where conventional approaches avoid contact and existing learning-based methods suffer from limited generalization. The authors propose Dense Contact Barrier Functions (DCBF), an object-centric, composable, and linearly scalable safety framework. By offline learning object-level safety barrier functions and dynamically composing them at runtime to construct a global safety filter, DCBF enables safe policy execution across diverse tasks without retraining. Experimental results demonstrate that DCBF effectively supports both collision-free navigation and safe physical interaction in complex simulated environments, significantly alleviating the computational burden associated with modeling multi-object dynamics while maintaining strong scalability and task generalization capabilities.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Learning & Optimization for ROB
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Robots operating in everyday environments must navigate and manipulate within densely cluttered spaces, where physical contact with surrounding objects is unavoidable. Traditional safety frameworks treat contact as unsafe, restricting robots to collision avoidance and limiting their ability to function in dense, everyday settings. As the number of objects grows, model-based approaches for safe manipulation become computationally intractable; meanwhile, learned methods typically tie safety to the task at hand, making them hard to transfer to new tasks without retraining. In this work we introduce Dense Contact Barrier Functions(DCBF). Our approach bypasses the computational complexity of explicitly modeling multi-object dynamics by instead learning a composable, object-centric function that implicitly captures the safety constraints arising from physical interactions. Trained offline on interactions with a few objects, the learned DCBFcomposes across arbitrary object sets at runtime, producing a single global safety filter that scales linearly and transfers across tasks without retraining. We validate our approach through simulated experiments in dense clutter, demonstrating its ability to enable collision-free navigation and safe, contact-rich interaction in suitable settings.

Problem

• safe robot interaction
• dense clutter
• physical contact
• safety constraints
• scalability

Innovation

• Barrier Functions
• Safe Robot Interaction
• Dense Clutter
• Composable Safety
• Contact-Rich Manipulation