Towards provable probabilistic safety for scalable embodied AI systems

ArXi:2506.05171v3 Announce Type: replace-cross Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge, which severely hinders their large-scale deployment in safety-critical domains, such as autonomous vehicles, medical devices, and robotics.