Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
🤖 AI Summary
Embodied AI faces critical challenges in bridging the gap between cyberspace and the physical world to enable AGI and applications such as intelligent mechatronic systems and smart manufacturing.
Method: We conduct a systematic survey of over 150 state-of-the-art works, proposing the first comprehensive taxonomy for embodied intelligence tailored to the multimodal large model (MLM) era. Our framework rigorously characterizes adaptation mechanisms, bottlenecks, and cross-modal alignment pathways between MLMs and world models (WMs) in both virtual and real-world environments. We analyze four core directions—embodied perception, interaction, agent construction, and sim-to-real transfer—integrating simulation platforms (e.g., AI2-THOR, Habitat), robotic hardware, and transfer techniques.
Contribution/Results: We establish a structured, open-access survey framework and release an open-source paper platform, delivering foundational theoretical insights and a concrete technical roadmap for AGI deployment.
Application Category
📝 Abstract
Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications that bridge cyberspace and the physical world. Recently, the emergence of Multi-modal Large Models (MLMs) and World Models (WMs) have attracted significant attention due to their remarkable perception, interaction, and reasoning capabilities, making them a promising architecture for the brain of embodied agents. However, there is no comprehensive survey for Embodied AI in the era of MLMs. In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI. Our analysis firstly navigates through the forefront of representative works of embodied robots and simulators, to fully understand the research focuses and their limitations. Then, we analyze four main research targets: 1) embodied perception, 2) embodied interaction, 3) embodied agent, and 4) sim-to-real adaptation, covering the state-of-the-art methods, essential paradigms, and comprehensive datasets. Additionally, we explore the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in dynamic digital and physical environments. Finally, we summarize the challenges and limitations of embodied AI and discuss their potential future directions. We hope this survey will serve as a foundational reference for the research community and inspire continued innovation. The associated project can be found at https://github.com/HCPLab-SYSU/Embodied_AI_Paper_List.
Problem
Research questions and friction points this paper is trying to address.
Surveying Embodied AI advancements for AGI and applications.
Analyzing embodied perception, interaction, agents, and sim-to-real adaptation.
Exploring MLMs and World Models in virtual and real agents.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-modal Large Models for embodied agents
World Models enhancing perception and reasoning
Sim-to-real adaptation for physical deployment
🔎 Similar Papers
No similar papers found.
