AI RESEARCH
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
arXiv CS.AI
•
ArXi:2503.03480v4 Announce Type: replace-cross Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans. How can safety constraints be explicitly integrated into VLAs? We address this by exploring an integrated safety approach (ISA), systematically modeling safety requirements, then actively eliciting diverse unsafe behaviors, effectively cons