This survey provides a comprehensive overview of Embodied AI, focusing on its role in bridging the cyber space and the physical world. Embodied AI is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications that bridge the digital and physical environments. Recent advancements in Multi-modal Large Models (MLMs) and World Models (WMs) have significantly enhanced the perception, interaction, and reasoning capabilities of embodied agents, making them a promising architecture for the brain of embodied agents. However, there is a lack of a comprehensive survey on Embodied AI in the era of MLMs. This survey explores the latest advancements in Embodied AI, analyzing four main research targets: embodied perception, embodied interaction, embodied agent, and sim-to-real adaptation. It also explores the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in dynamic digital and physical environments. The survey also summarizes the challenges and limitations of Embodied AI and discusses their potential future directions. The survey covers various aspects of Embodied AI, including embodied robots, simulators, and four main research tasks: embodied perception, embodied interaction, embodied agents, and sim-to-real robotic control. It provides a comprehensive analysis of the latest advancements in Embodied AI, offering a broad overview with a thorough summary and categorization of existing studies. The survey also examines the latest progress in Embodied AI, providing comprehensive benchmarking and discussion of current work across multiple simulators and datasets. It identifies several research challenges and potential directions for future research in AGI for Embodied AI. The survey is organized into sections covering various aspects of Embodied AI, including embodied robots, simulators, embodied perception, embodied interaction, embodied agents, and sim-to-real adaptation. The survey highlights the importance of Embodied AI in achieving AGI and provides insights into the current state of research and future directions. The survey also discusses the differences between previous works and the contributions of this survey, emphasizing its comprehensive coverage of Embodied AI. The survey provides a detailed analysis of the latest advancements in Embodied AI, covering various aspects such as embodied robots, simulators, and research tasks. The survey aims to fill the gap in comprehensive surveys on Embodied AI and provide a clear picture of the current state of research and future directions. The survey is structured to provide a comprehensive overview of Embodied AI, covering various aspects such as embodied robots, simulators, and research tasks. The survey highlights the importance of Embodied AI in achieving AGI and provides insights into the current state of research and future directions. The survey also discusses the challenges and limitations of Embodied AI and their potential future directions. The survey is organized into sections covering various aspects of Embodied AI, including embodied robots, simulators, embodied perception, embodied interaction, embodied agents, and sim-to-real adaptation. The survey provides a detailed analysis of the latest advancements in Embodied AI, covering various aspects such as embodied robots, simulatorsThis survey provides a comprehensive overview of Embodied AI, focusing on its role in bridging the cyber space and the physical world. Embodied AI is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications that bridge the digital and physical environments. Recent advancements in Multi-modal Large Models (MLMs) and World Models (WMs) have significantly enhanced the perception, interaction, and reasoning capabilities of embodied agents, making them a promising architecture for the brain of embodied agents. However, there is a lack of a comprehensive survey on Embodied AI in the era of MLMs. This survey explores the latest advancements in Embodied AI, analyzing four main research targets: embodied perception, embodied interaction, embodied agent, and sim-to-real adaptation. It also explores the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in dynamic digital and physical environments. The survey also summarizes the challenges and limitations of Embodied AI and discusses their potential future directions. The survey covers various aspects of Embodied AI, including embodied robots, simulators, and four main research tasks: embodied perception, embodied interaction, embodied agents, and sim-to-real robotic control. It provides a comprehensive analysis of the latest advancements in Embodied AI, offering a broad overview with a thorough summary and categorization of existing studies. The survey also examines the latest progress in Embodied AI, providing comprehensive benchmarking and discussion of current work across multiple simulators and datasets. It identifies several research challenges and potential directions for future research in AGI for Embodied AI. The survey is organized into sections covering various aspects of Embodied AI, including embodied robots, simulators, embodied perception, embodied interaction, embodied agents, and sim-to-real adaptation. The survey highlights the importance of Embodied AI in achieving AGI and provides insights into the current state of research and future directions. The survey also discusses the differences between previous works and the contributions of this survey, emphasizing its comprehensive coverage of Embodied AI. The survey provides a detailed analysis of the latest advancements in Embodied AI, covering various aspects such as embodied robots, simulators, and research tasks. The survey aims to fill the gap in comprehensive surveys on Embodied AI and provide a clear picture of the current state of research and future directions. The survey is structured to provide a comprehensive overview of Embodied AI, covering various aspects such as embodied robots, simulators, and research tasks. The survey highlights the importance of Embodied AI in achieving AGI and provides insights into the current state of research and future directions. The survey also discusses the challenges and limitations of Embodied AI and their potential future directions. The survey is organized into sections covering various aspects of Embodied AI, including embodied robots, simulators, embodied perception, embodied interaction, embodied agents, and sim-to-real adaptation. The survey provides a detailed analysis of the latest advancements in Embodied AI, covering various aspects such as embodied robots, simulators