SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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 Hami

Read original source ↗ Open in workspace

recordType

paper

region

Global