整合物理规律与智能系统，推动AI从感知到理解的跃迁
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
- 构建物理规律与认知推理的统一框架
- 提升AI在真实世界中的理解与预测能力
- 适合关注具身智能与世界模型的研究者
具身智能与世界模型的快速发展推动了将物理规律融入AI系统的努力，但物理感知与符号化物理推理仍沿独立路径发展，缺乏统一的桥梁。本文全面综述物理AI，明确区分理论物理推理与应用物理理解，并系统分析基于物理的方法如何增强AI在结构化符号推理、具身系统和生成模型中的现实世界理解能力。通过严谨分析最新进展，我们倡导将学习建立在物理原理与具身推理双重基础上的智能系统，超越模式识别，实现对物理定律的真实理解。我们的综述展望下一代世界模型，具备解释物理现象与预测未来状态的能力，推动安全、可泛化且可解释的AI发展。相关资源持续更新，详见 https://github.com/AI4Phys/Awesome-AI-for-Physics。
原文摘要 · Abstract (English)
The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a unified bridging framework. This work provides a comprehensive overview of physical AI, establishing clear distinctions between theoretical physics reasoning and applied physical understanding while systematically examining how physics-grounded methods enhance AI's real-world comprehension across structured symbolic reasoning, embodied systems, and generative models. Through rigorous analysis of recent advances, we advocate for intelligent systems that ground learning in both physical principles and embodied reasoning processes, transcending pattern recognition toward genuine understanding of physical laws. Our synthesis envisions next-generation world models capable of explaining physical phenomena and predicting future states, advancing safe, generalizable, and interpretable AI systems. We maintain a continuously updated resource at https://github.com/AI4Phys/Awesome-AI-for-Physics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。