Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching

2026-07-01

AI Summary

Existing vision-language-action models lack effective safeguards against cumulative risks in long-horizon tasks, typically mitigating only immediate collisions. This work proposes a neuro-symbolic safety guidance mechanism that, for the first time, dynamically integrates symbolic safety constraints with neural trajectory generation during flow-matching-based trajectory denoising. By employing real-time minimum-norm projection to correct unsafe trajectories, the method enables proactive collision avoidance. Evaluated on the SafeLIBERO benchmark, it achieves an 82.8% obstacle avoidance rate and 81.6% task success rate—improvements of 6.3% and 19.8%, respectively, over single-step baselines—with particularly pronounced gains in long-horizon tasks.

Abstract

Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities across robotic manipulation tasks, yet their real-world deployment remains limited by the lack of effective safety measures. Specifically, existing safety measures only prevent collisions caused by the robot's next action. In this paper, we propose a neuro-symbolic safety guidance mechanism for flow matching based VLAs that enables predictive collision avoidance. Flow matching based VLAs determine the next actions by predicting a trajectory (a sequence of actions) through an iterative neural flow matching process. Our method formulates safety enforcement as a minimum-norm constrained optimization problem that corrects safety violations during the denoising process of noisy intermediate trajectory predictions. By analyzing predicted trajectories and applying corrections during iterative denoising, our approach anticipates collisions before they become unavoidable. This interleaving of symbolic constraint satisfaction with neural trajectory generation enables predictive collision avoidance rather than reactive intervention. On the SafeLIBERO benchmark, our method achieves 82.8% collision avoidance and 81.6% task success, a 6.3% and 19.8% improvement respectively over single-step methods, with the largest gains on long-horizon tasks where compounding distribution shift is most pronounced. Video demonstrations of our approach are included on our project page at https://willenglish.tech/SafetyGuidedFlowMatching/.

Problem

• Vision-Language-Action models
• safety
• collision avoidance
• predictive safety
• robotic manipulation

Innovation

• Neuro-Symbolic
• Flow Matching
• Predictive Collision Avoidance
• Constrained Optimization
• Vision-Language-Action Models