VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies

2026-09-18

AI Summary

本文提出VLPSA框架，通过在线合成Poisson Safety Functions并结合双分辨率PSF，为VLA模型提供全身体碰撞避免安全保障，无需重新训练。

Abstract

Vision-language-action (VLA) models enable increasingly general-purpose robotic manipulation, but such learned policies do not provide safety guarantees for collision avoidance---especially in environments outside of training distributions. This work presents Vision-Language-Poisson-Safe Actions (VLPSA), a safety filtering framework that provides full-body safety for VLA policies in cluttered and dynamic environments without retraining. VLPSA synthesizes Poisson Safety Functions (PSF) online from perception data, yielding a Control Barrier Function (CBF) that is enforced through a CBF-QP safety filter over the full body and any grasped object, treated as an extension of the final robot link. To enable real-time deployment while maintaining fine spatial resolution in critical task regions, VLPSA combines dual resolutions of this PSF using Boolean CBF compositions. We evaluate VLPSA on SafeLIBERO against safety-filtering baselines, where it achieves the highest collision avoidance rate among the evaluated methods, increasing collision avoidance from 23.1% for the base $π_{0.5}$ policy to 91.2% while surpassing its task success rate. We further deploy VLPSA on a Franka FR3 in cluttered scenes with dynamic obstacles and human interference, demonstrating real-time full-body safety during manipulation tasks.

Problem

• Vision-Language-Action
• Safety Guarantees
• Collision Avoidance
• Dynamic Environments
• Full-Body Safety

Innovation

• Vision-Language-Poisson-Safe Actions
• Poisson Safety Functions
• Control Barrier Function
• collision avoidance