This introduction to the principles, design, and practice of intelligent behaviour-based autonomous robotic systems is a survey of the robotics field. The author presents the tools and techniques central to the development of this class of systems in a comprehensive manner. Following a discussion of the relevant biological and psychological models of behaviour, he covers the use of knowledge and learning in autonomous robots, behaviour-based and hybrid robot architectures, modular perception, robot colonies, and future trends in robot intelligence. The text throughout refers to actual implemented robots and includes many pictures and descriptions of hardware, making it clear that these are not abstract simulations, but real machines capable of perception, cognition and action.
The publisher, The MIT Press , 19 October, 1998
The definitive book on behavior-based robotics...
BEHAVIOR-BASED ROBOTICS is an introduction to the principles, design, and practice of intelligent behavior-based autonomous robotic systems. As the first true survey of the robotics field, it is appropriate for graduate students new to
AI / Robotics.
This is a definitive book on the theory and application of robots based on biological and psychological models of behavior, moving from models of behavior in animals and robots to the use of knowledge and learning in robots, onto colonies of robots and finally to speculation about future trends in robot intelligence.
Instead of abstract simulations the text refers back to real implemented robots with many pictures and hardware descriptions, making it clear that these are actual machines capable of perception, cognition and action in the world. BEHAVIOR-BASED ROBOTICS draws examples from engineering, computer science, cognitive science, biology and ethnology

As Steven Johnson explains with a rare lucidity in Emergence: The Connected Lives of Ants, Brains, Cities and Software, an individual ant, like an individual neuron, is just about as dumb as can be. Connect enough of them together properly, though, and you get spontaneous intelligence. Starting with the weird behaviour of the semi-colonial organisms we call slime molds, Johnson details the development of increasingly complex and familiar behaviour among simple components: cells, insects and software developers all find their place in greater schemes.
Most game players, alas, live on something close to day-trader time, at least when they're in the middle of a game--thinking more about their next move than their next meal, and usually blissfully oblivious to the 10-or-20-year trajectory of software development. No-one wants to play with a toy that's going to be fun after a few decades of tinkering--the toys have to be engaging now, or kids will find other toys.
Johnson has a knack for explaining complicated and counterintuitive ideas cleverly without stealing the scene. Though we're far from fully understanding how complex behaviour manifests from simple units and rules, our awareness that such emergence is possible is guiding research across disciplines. Readers unfamiliar with the sciences of complexity will find Emergence an excellent starting point, while those who were chaotic before it was cool will appreciate its updates and wider scope. --Rob Lightner
Synopsis
We have only recently begun to recognize it, yet it exists at every level of our lived experience. It is fast becoming clear that our lives revolve around the powers of emergence. An ant colony behaves with an intelligence no particular ant possesses; a brain is conscious although no particular brain cell is; a city develops districts and neighbourhoods no planner could impose. In each case, complex problems are solved by a profusion of relatively simple elements. Order arrives from the botto

Robot Shaping
Marco Dorigo, Marco Colombetti

To program an autonomous robot to act reliably in a dynamic environment is a complex task. The dynamics of the environment are unpredictable, and the robots' sensors provide noisy input. A learning autonomous robot, one that can acquire knowledge through interaction with its environment and then adapt its behaviour, greatly simplifies the designer's work. A learning robot need not be given all of the details of its environment, and its sensors and actuators need not be finely tuned. This book is about designing and building learning autonomous robots. The term "shaping" comes from experimental psychology, where it describes the incremental training of animals. The authors propose a new engineering discipline, "behaviour engineering," to provide the methodologies and tools for creating autonomous robots. Their techniques are based on classifier systems, a reinforcement learning architecture originated by John Holland, to which they have added several new ideas, such as "mutespec", classifier system "energy", and dynamic population size. In the book they present Behaviour Analysis and Training (BAT) as an example of a behaviour engineering methodology

Synopsis
This text provides information on learning robots. It treats this topic based on the idea that the integration of sensing and action is the central issue. In the first part of the book, aspects of learning in execution and control are discussed. Methods for the automatic synthesis of controllers, for active sensing, for learning to enhance assembly, and for learning sensor-based navigation are presented. Since robots are not isolated but should serve us, the second part of the book discusses learning for human-robot interaction. Methods of learning understandable concepts for assembly, monitoring, and navigation are described as well as optimizing the implementation of such understandable concepts for a robot's real-time performance. In terms of the study of embodied intelligence, the book asks how skills are acquired and where capabilities of execution and control come from. Can they be learned from examples or experience? What is the role of communication in the learning procedure? Whether we name it one way or the other, the methodological challenge is that of integrating learning capabilities into robots