AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。
[Submitted on 2 Sep 2026] Title:ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models View a PDF of the paper titled ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models, by Manan Tayal and 1 other authors View PDF HTML (experimental) 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. Comments: 24 pages, 3 figures, 14 tables Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.13231 [cs.RO] (or arXiv:2609.13231v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2609.13231 arXiv-issued DOI via DataCite Submission history From: Manan Tayal [view email] [v1] Wed, 2 Sep 2026 10:10:32 UTC (1,441 KB) Full-text links: Access Paper: View a PDF of the paper titled ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models, by Manan Tayal and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO new | recent | 2026-09 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)