Synopsis
This reference on multi-robot systems explains the essentials of multi-agent robotics theory and describes particular systems illustrating the major concepts of multi-robot research. Each chapter represents a key concept or design approach which has advanced the field of robotic research and development.

This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm - team-partitioned, opaque-transition reinforcement learning (TPOT-RL) -designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multi-agent system that incorporates learning in a real-time, noisy domain with teammates and adversaries - a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RocoCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0.

Synopsis
Presenting a formal approach to dealing with agents and agent systems, the Z specification language is used to establish an accessible and unified formal account of agent systems and inter-agent relationships. In particular, the framework provides precise and unambiguous meanings for common concepts and terms for agent systems, and allows for the description of alternative agent models and architectures, and serves as a foundation for subsequent development of increasingly refined agent concepts. The practicability of this approach is verified by applyingthe formal framework to three detailed case studies. The methodology presented takes a very significant step towards organizing and structuring the diverse and disparate landscape of agent-based systems by applying formal methods to develop a defining and encompassing agent framework. The book should appeal equally to researchers, students, and professionals in industry.
Useful framework for agents, with helpful case studies
There are several books on intelligent agents and multi-agents systems that I've come across, but most are either too broad-ranging and shallow so that they don't actually get to important core issues, or they're too narrow and mathematical for my liking (and for many others). This excellent book somehow manages to pull off the feat of providing a good introduction to agents, while also drilling down to some fascinating and deep issues in multi-agent systems. What's particularly good is that it does two things - it analyses and explains the issues with really clear textual description, and then provides a more formal description (using the Z specification language) that is surprisingly readable.
After providing an introductory chapter, the book presents a "framework" for understanding agent systems (hence the title) in which it brings together various different notions of agents. The chapters cover the framework itself, the different kinds of inter-agent
relationships that arise within it (to get to multi-agent systems), and more complex agents with greater sophistication. There are also a couple of case-study chapters that show how the model can be used to give descriptions of BDI systems and the contract net.
Throughout, the authors provide really good explanations, and then also formal descriptions using Z. Whether or not you buy the claim that Z is the most used industrial formal method, it turns out that despite the mathematical nature of the Z specification, the book as a whole is really very readable. It is worth noting that the level of mathematical description in the book for describing the framework and the systems is pretty close to abstract code descriptions (which is perhaps not surprising given that Z is intended for use for specifying software). With the appendix intro to Z, the book should also be a useful resource for developers wanting to understand exactly what would be involved in building systems.
One of the difficulties I've found when reading about agents is trying to make sense of some very different ideas and systems, and trying to understand how they fit together. This book provides some of the answers. In summary, the book covers some basic agent concepts, and builds them up to describe quite complex multi-agent systems, moving from abstract ideas to descriptions of specific implemented systems, and showing how they come together. It provides an excellent
introduction to agents, and keeps going to address some much deeper issues

Swarm Intelligence
Eric Bonabeau, Marco Dorigo, Guy Theraulaz

Synopsis
Social insects - bees, termites, and wasps - can be viewed as powerful problem-solving systems with sophisticated collective intelligence. Composed of simple interacting agents, this intelligence lies in the networks of interactions among individuals and between individuals and the environment. Social insects are also a metaphor for artificial intelligence, and the problems they solve - finding food, dividing labour among nestmates, building nests, responding to external challenges - have important counterparts in engineering and computer science. This text provides a detailed look at models of social insect behaviour and how to apply these models in the design of complex systems. It shows how these models replace an emphasis on control, preprogramming, and centralization with designs featuring autonomy, emergence, and distributed functioning. These designs are proving immensely flexible and robust, able to adapt quickly to changing environments and to continue functioning even when individual elements fail. In particular, these designs are an approach to the tremendous growth of complexity in software and information.

Multi-Agent Systems : An Introduction to Distributed Artificial Intelligence
Jacques Ferber

Mike Wooldridge, Queen Mary and Westfield College, UK
"Jacques Ferber can legitimately claim to be one of the founders of the discipline that is today known as multi-agent systems. In Multi-Agent Systems, he draws on over a decade of experience as a first-rate researcher and teacher in order to set out a coherent, unified view of the field. The end result is a readable and comprehensive book, that will be enthusiastically received by a growing and increasingly important discipline."
Dr H Van Dyke Parunak Centre for Electronic Commerce, Industrial Technology Institute, Michigan
"This author guides his readers responsibly and engagingly through the best of classical A1-based agent research while opening eyes to a powerful new version of swarm-based intelligence. I know of no other book on agents....that matches its comprehensive treatment and clear, enjoyable exposition."

This proceedings volume represents the contributions of the top researchers in this field and serves as a valuable tool for professionals in this interdisciplinary field.

Table of Contents
Part I localisation, Mapping and Navigation: On the Positional Uncertainty of Multi-Robot Cooperative Localization, I.M. Rekleitis, et al
A Multi-Agent System for Multi-Robot Mapping and Exploration, K. Konolige, et al
Distributed Heterogeneous Sensing for Outdoor Multi-Robot Localization, Mapping, and Path Planning, L.E. Parker
et al
Mission-Relevant Collaborative Observation and Localization, A.W. Stroupe, T. Balch
Deployment and Localization for Mobile Robot Teams, A. Howard, M.J. Mataric
Multiple Autonomous Robots for UXO Clearance, the Basic UXO Gathering System (BUGS) Project, T.N. Nguyen, et al.
Part II Distributed Survelliance: Programming and Controlling the Operations of a Team of Miniature Robots, P.E. Rybski, et al
Autonomous Flying Vehicle Research at the University of Southern California, S. Saripalli, et al.
Part III Manipulation: Distributed Manipulation of Multiple Objects Using Ropes, B. Donald, et al
A Distributed Multi-Robot System for Co-operative Manipulation, A. Das, et al.
Part IV Co-ordination and Formations: A Layered Architecture for Coordination of Mobile Robots, R. Simmons, et al
Stability Analysis of Decentralized Co-operative Controls, J.T. Feddema, D.A. Schoenwald. Snow White and the 700 Dwarves, B.H. Wilcox.
Part V Sensor and Hardware Issues: GOATS - Multi-platform Sonar Concept for Coastal Mine Countermeasures, H. Schmidt, J.R. Edwards
Design of the UMN Multi-Robot System, A. Drenner, et al.