Towards Trustworthy Physical AI: From Theory to Practice Across Life Cycle
Authors: Wang Yang, Hongxuan Liu, Xinghui Xu, Arjun Menon, Xiaoran Cai, Yunyu He, Jingzong Zhou, Mengzhong Ma, +24 more
Organizations: Case Western Reserve University · Massachusetts Institute of Technology · New York University · Princeton University · Columbia University · University of California, Riverside · Nanyang Technological University · Georgia Institute of Technology · Harvard University · University of Oxford · University of Toronto · University of Washington · University of Chicago · Carnegie Mellon University · Cornell University · NVIDIA · Salesforce · Imperial College London · Mila, Université de Montréal · Stanford University
Physical AI refers to AI systems that understand, reason about, and act in accordance with the physical world and its underlying laws, dynamics, and constraints. Unlike conventional AI systems, physical AI interacts continuously with uncertain physical environments, and its actions produce consequences that are physically irreversible. As existing trustworthy AI frameworks have been developed primarily for digital AI systems, they do not fully capture the distinctive challenges of physical AI, such as physical safety, cyber-physical security, and physical manufacturing process. To address this gap, we present a survey of trustworthy physical AI principles. First, we characterize the core capabilities and challenges of physical AI. Second, we examine the role of physics in AI. Third, we trace the end-to-end physical AI life cycle across five core stages and introduce Trustworthy Physical AI Operationalization (T-PAIO). Fourth, we develop the Trustworthy Physical AI (T-PAI) framework, a theoretical framework that organizes key trustworthiness principles and provides a foundation for governing trustworthy physical AI systems.