Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle
cs.AI, cs.HC, cs.RO
Submitted: 2026-07-24
Updated: 2026-10-03
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
Abstract
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.
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
- RT-1: Robotics Transformer for Real-World Control at Scale
- Genie: Generative Interactive Environments
- Toward Trustworthy Evaluation of Sustainability Rating Methodologies: A Human-AI Collaborative Framework for Benchmark Dataset Construction
- Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions
- RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
- A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings
- LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
- Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
- PaLM-E: An Embodied Multimodal Language Model
- A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle
- Position: Embodied AI Requires a Privacy-Utility Trade-off
- DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
- Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
- World Model for Robot Learning: A Comprehensive Survey
- Impact of Static Friction on Sim2Real in Robotic Reinforcement Learning
- An Embodied Generalist Agent in 3D World
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection