Skip to content

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Sep 2026 · 0 citations · 37 references
Computer Science

TL;DR

ShieldVLA is proposed, a safety-aligned fine-tuning framework for VLA models based on Hamilton-Jacobi (HJ) reachability that reduces cumulative safety cost by 57% on average and improves task success rate by +0.13 over SafeVLA.

Abstract

Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provide limited safety guarantees. Current approaches primarily rely on Lagrangian optimization that enforces safety through soft penalties on expected cumulative cost, often resulting in residual constraint violations or overly conservative behavior. Moreover, learning safety in visual domains is challenging due to the absence of dense per-step safety annotations. We propose ShieldVLA, a safety-aligned fine-tuning framework for VLA models based on Hamilton-Jacobi (HJ) reachability. ShieldVLA learns a model-free approximation of the HJ reachability value function directly from visual observations to estimate the safe operating region. The learned safety critic gates policy optimization by separating reward maximization within feasible regions from recovery near unsafe states, avoiding persistent reward-cost trade-offs. To enable scalable supervision in visual environments, we introduce rubric-based VLM safety scores that convert semantic safety feedback into structured critic targets without requiring manual cost labels. Across five navigation and manipulation benchmarks spanning multiple VLA backbones, ShieldVLA reduces cumulative safety cost by 57% on average and improves task success rate by +0.13 over SafeVLA.

View source

Similar papers

Preprint Sep 2026

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

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, and deploys VLPSA on a Franka FR3 in cluttered scenes with dynamic obstacles and human interference.

Meg Wilkinson, E. Fourney, Joel W. Burdick et al. · 0 citations
Preprint Sep 2026

RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving

Vision-Language-Action (VLA) models for autonomous driving rely heavily on successful expert demonstrations, leaving model-specific failures underexploited. Learning from these failures is hindered by unreliable diagnoses, poorly matched correction targets, and coarse rewards. We propose RefineDrive, a failure-guided p...

Zhe Sun, Zi-Yin Luo, Ye-Hao Lu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies

ActSafeGuard is introduced, a differentiable and training-aligned safeguard layer for flow-matching based policies that integrates hard action feasibility into policy learning, not merely treating safety as an inference-time external component.

Jian-Ming Ma, Rong-Jun Jin, Xia-Xi Si et al. · 0 citations

Vision-Language Signals in Constrained RL: Safety Gains Without Anticipation

VLM-Safe-RL is proposed, a framework that integrates frozen CLIP signals into PPO-Lagrangian through reward shaping and an augmented multiplier update, and shows a conditional reduction in observed catastrophe rate without evidence of collision anticipation.

Samuel T. K. Tetteh, Cody H. Fleming · 1 citation
#computer vision Preprint Aug 2026

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

SafeBranch is proposed, a framework that aligns an embodied actor on safety through branch pairs constructed from the actor's own unsafe rollouts via environment rollback, achieving roughly ten times more safe successes than the untrained baseline on the unseen-object variant.

Hyunse Lee, Jiwoo Jeong, Haneul Lee et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.