04488nam 22006255 450 991100746240332120250521124741.0981-9658-71-310.1007/978-981-96-5871-8(CKB)38891412900041(DE-He213)978-981-96-5871-8(MiAaPQ)EBC32127059(Au-PeEL)EBL32127059(EXLCZ)993889141290004120250521d2025 u| 0engur|||||||||||txtrdacontentcrdamediacrrdacarrierEmbodied Multi-Agent Systems Perception, Action, and Learning /by Huaping Liu, Xinzhu Liu, Kangyao Huang, Di Guo1st ed. 2025.Singapore :Springer Nature Singapore :Imprint: Springer,2025.1 online resource (XXVIII, 229 p. 108 illus., 107 illus. in color.) Machine Learning: Foundations, Methodologies, and Applications,2730-9916981-9658-70-5 Part I. Background -- Chapter 1. Embodied Intelligence -- Chapter 2. Embodied Multi-agent System -- Part II. Theory and Methods -- Chapter 3. Perception-Action Loop in Embodied Multi-agent System -- Chapter 4. Embodied Cooperation in Multi-agent System -- Chapter 5. Competitive Learning in Embodied Multi-agent System -- Chapter 6. Large Language Model for Embodied Multi-agent System -- Part III. Applications -- Chapter 7. Simulation Platform for Embodied Collaboration between Human and Robots -- Chapter 8. Application of Embodied Multi-agent System -- Part IV. Conlusions -- Chapter 9. Conclusions and Future Directions.In recent years, embodied multi-agent systems, including multi-robots, have emerged as essential solution for demanding tasks such as search and rescue, environmental monitoring, and space exploration. Effective collaboration among these agents is crucial but presents significant challenges due to differences in morphology and capabilities, especially in heterogenous systems. While existing books address collaboration control, perception, and learning, there is a gap in focusing on active perception and interactive learning for embodied multi-agent systems. This book aims to bridge this gap by establishing a unified framework for perception and learning in embodied multi-agent systems. It presents and discusses the perception-action-learning loop, offering systematic solutions for various types of agents—homogeneous, heterogeneous, and ad hoc. Beyond the popular reinforcement learning techniques, the book provides insights into using fundamental models to tackle complex collaboration problems. By interchangeably utilizing constrained optimization, reinforcement learning, and fundamental models, this book offers a comprehensive toolkit for solving different types of embodied multi-agent problems. Readers will gain an understanding of the advantages and disadvantages of each method for various tasks. This book will be particularly valuable to graduate students and professional researchers in robotics and machine learning. It provides a robust learning framework for addressing practical challenges in embodied multi-agent systems and demonstrates the promising potential of fundamental models for scenario generation, policy learning, and planning in complex collaboration problems.Machine Learning: Foundations, Methodologies, and Applications,2730-9916Multiagent systemsRoboticsArtificial intelligenceMultiagent SystemsRoboticsIntelligence InfrastructureArtificial IntelligenceMultiagent systems.Robotics.Artificial intelligence.Multiagent Systems.Robotics.Intelligence Infrastructure.Artificial Intelligence.006.30285436Liu Huapingauthttp://id.loc.gov/vocabulary/relators/aut954499Liu Xinzhuauthttp://id.loc.gov/vocabulary/relators/autHuang Kangyaoauthttp://id.loc.gov/vocabulary/relators/autGuo Diauthttp://id.loc.gov/vocabulary/relators/autMiAaPQMiAaPQMiAaPQBOOK9911007462403321Embodied Multi-Agent Systems4393316UNINA