发表机构
Qualcomm Research; University of the Cumberlands; BITS-Pilani; National University of Singapore; Nanyang Technological University（高通研究院; 坎伯兰大学; 皮拉尼比尔拉理工学院; 新加坡国立大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述系统分类并分析了生成式物理人工智能的五种方法，探讨其互补关系，并总结了在自动驾驶、工业自动化等领域的性能提升与未来研究方向。
AI 中文摘要
大规模基础模型与物理实体的集成，推动了机器人领域的重大进展，这一领域被称为生成式物理人工智能（GPAI）。这些智能体系统能够在复杂的现实情境中自主感知、推理和行动。本综述全面分析了GPAI系统，重点关注其架构基础、当前应用和关键局限性。我们提出了一种包含五种不同方法的分类法：用于跨平台技能迁移的机器人基础模型（RFMs）；用于端到端多模态感知与控制的视觉-语言-动作（VLA）模型；用于类人动作生成的大型行为模型（LBMs）；基于扩散模型、生成时间上连贯动作的扩散策略模型（DPMs）；以及用于符合物理规律的仿真与数据生成的世界基础模型（WFMs）。我们考察了这些方法之间的互补关系：WFMs为VLAs和DPMs生成训练数据，RFMs实现所学策略的跨平台部署，而LBMs为自然行为提供运动先验。通过自动驾驶汽车、工业自动化、医疗机器人和人形系统等实例，我们识别了显著的性能提升，并总结了数据高效学习、仿真到现实迁移、边缘兼容架构和安全框架等有前景的研究方向。这些见解推进了面向物联网连接环境的具身人工智能，在该环境中，智能体与网络化传感器、执行器和边缘设备进行交互。
英文摘要
The integration of large-scale foundation models with physical embodiments has led to significant advancements in robotics known as Generative Physical Artificial Intelligence (GPAI). These agentic AI systems autonomously perceive, reason, and act in complex real-world situations. This survey comprehensively analyzes GPAI systems, focusing on their architectural foundations, current applications, and key limitations. We introduce a taxonomy of five distinct approaches: Robot Foundation Models (RFMs) for cross-platform skill transfer; Vision-Language Action (VLA) models for end-to-end multi-modal perception and control; Large Behavior Models (LBMs) for human-like movement generation; Diffusion Policy Models (DPMs) for diffusion model-based temporally coherent action generation; and World Foundation Models (WFMs) for physics-compliant simulation and data generation. We examine how these approaches complement each other: WFMs generate training data for VLAs and DPMs, RFMs enable cross-platform deployment of learned policies, while LBMs provide motion priors for natural behavior. Through examples across autonomous vehicles, industrial automation, healthcare robotics, and humanoid systems, we identify significant performance improvements and summarize promising research directions in data-efficient learning, sim-to-real transfer, edge-compatible architectures, and safety frameworks. These insights advance embodied AI for IoT-connected environments where intelligent agents interact with networked sensors, actuators, and edge devices.
Comments25 pages, 8 figures
Journal refIEEE Internet of Things Journal, vol. 13, no. 10, pp. 20452-20476, 15 May 2026
