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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wilkinson, M., Fourney, E., Burdick, J. W., & Ames, A. D. (2026). VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies. https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies
MLA 9
Wilkinson, Meg, et al. "VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies." https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies.
Chicago (author–date)
Wilkinson, Meg, Emily Fourney, Joel W. Burdick, and Aaron D. Ames. 2026. "VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies." https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies.
Harvard
Wilkinson, M., Fourney, E., Burdick, J. W. and Ames, A. D. (2026) 'VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies', Available at: https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies.
Vancouver
Wilkinson M, Fourney E, Burdick JW, Ames AD. VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies. https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies
IEEE
M. Wilkinson, E. Fourney, J. W. Burdick, and A. D. Ames, "VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies," https://omanscience.com/en/articles/vlpsa-vision-language-poisson-safe-actions-for-full-body-safety-of-learned-policies.