SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Understand

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 constraining VLA policies via safe reinforcement learning, and rigorously assuring their safety through targeted evaluations.
• Leveraging the constrained Markov decision process (CMDP) paradigm, ISA optimizes VLAs from a min-max perspective against elicited safety risks.