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

arXiv: https://arxiv.org/abs/2609.22462 · HTML: https://mlsanity.com/paper/2609.22462/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety and adversarial attacks, one of 13 directions in Vision-language-action models.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- Vision-language-action models / [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/)

## Builds on (most cited first, 24 of 24)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis](https://mlsanity.com/paper/2502.00935/) (2025)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures](https://mlsanity.com/paper/2505.00779/) (2025)
- [Safe, Task-Consistent Manipulation with Operational Space Control Barrier Functions](https://mlsanity.com/paper/2503.06736/) (2025)
- [LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models](https://mlsanity.com/paper/2606.23686/) (2026)
- [Safety-Critical Manipulation for Collision-Free Food Preparation](https://mlsanity.com/paper/2205.01026/) (2022)
- [Composing Control Barrier Functions for Complex Safety Specifications](https://mlsanity.com/paper/2309.06647/) (2023)
- [From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies](https://mlsanity.com/paper/2511.06385/) (2025)
- [Planning and Control for Deformable Linear Object Manipulation](https://mlsanity.com/paper/2503.04007/) (2025)
- [Geometry-Aware Predictive Safety Filters on Humanoids: From Poisson Safety Functions to CBF Constrained MPC](https://mlsanity.com/paper/2508.11129/) (2025)
- [Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models](https://mlsanity.com/paper/2606.09749/) (2026)
- [Neural Configuration-Space Barriers for Manipulation Planning and Control](https://mlsanity.com/paper/2503.04929/) (2025)
- [Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An Option](https://mlsanity.com/paper/2506.17601/) (2025)
- [CSSDF-Net: Safe Motion Planning Based on Neural Implicit Representations of Configuration Space Distance Field](https://mlsanity.com/paper/2603.18669/) (2026)
- [Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters](https://mlsanity.com/paper/2604.21189/) (2026)
- [Dynamic Safety in Complex Environments: Synthesizing Safety Filters with Poisson's Equation](https://mlsanity.com/paper/2505.06794/) (2025)
- [Combinatorial Control Barrier Functions: Nested Boolean and p-choose-r Compositions of Safety Constraints](https://mlsanity.com/paper/2509.10716/) (2025)

## Abstract (arXiv)

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 π0.5 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.