Evolutionary Robotics

The Biology, Intelligence, and Technology of Self-Organizing Machines

Stefano Nolfi and Dario Floreano

MIT Press/Bradford Books

Evolutionary Robotics is a new technique for the automatic creation of autonomous robots. Inspired by the Darwinian principle of selective reproduction of the fittest, it views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention.Drawing heavily on biology and ethology, it uses the tools of neural networks, genetic algorithms, dynamic systems, and biomorphic engineering. The resulting robots share with simple biological systems the characteristics of robustness, simplicity, small size, flexibility, and modularity.

In evolutionary robotics, an initial population of artificial chromosomes, each encoding the control system of a robot, is randomly created and put into the environment. Each robot is then free to act (move, look around, manipulate) according to its genetically specified controller while its performance on various tasks is automatically evaluated. The fittest robots then "reproduce" by swapping parts of their genetic material with small random mutations. The process is repeated until the "birth" of a robot that satisfies the performance criteria.

This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far. An important feature is the clear presentation of a set of empirical experiments of increasing complexity. Software with a graphic interface, freely available on a Web Page, will allow the reader to replicate and vary (in simulation and on real robots) most of the experiments. 		Evolutionary Robotics Book

Available from: Mit Press, Amazon

Contents

1. The Role of Self-organization for the Synthesis and the Understanding of Behavioral Systems
2. Evolutionary and Neural Techniques
3. How to Evolve Robots
4. Evolution of Simple Navigation
5. Power and Limits of Reactive Intelligence
6. Beyond Reactive Intelligence
7. Learning and Evolution
8. Competitive Co-Evolution
9. Encoding, Mapping, and Development
10. Complex Hardware Morphologies: Walking Machines
11. Evolvable Hardware

Intelligent Robots and Autonomous Agents series edited by Ronald C. Arkin, MIT Press., November 2000, ISBN 0-262-14070-5, 384 pp., 157 illus.


Book Reviews

"This is an exciting new area that has implications and ramifications ranging from psychology to artificial life; can we create robots with intelligent or adaptive behavior using techniques comparable to the Darwinian evolution that created the animals and ourselves? Here is an authoritative, clearly written survey written by two of the researchers who helped to pioneer the field"
Inman Harvey (2001) book cover.

"An excellent book providing a thorough coverage of the subject. Clearly and insightfully written, this is a must for researchers and postgraduate students interested in new approaches to intelligent robotics "
Phil Husband (2001) book cover.

"This book will be welcomed by those interested in building complex robots or simple robots that do complex things"
David B. Fogel (2001) American Scientist, pp.371.

"You can tell a field is reaching maturity when its first textbook is written....Stefano Nolfi and Dario Floreano make a good job of this task... This is one of those books from which you learn more that you initially set out to...Nolfi and Floreano make a superb job of presenting the state of the art of evolutionary robotics, weaving their own experimental results with current theoretical ideas. It is indeed a notable achievement and will certainly be considered a hallmark in this leading-edge field."
Hod Lipson (2001) Artificial Life, 7:419-424.

"Overall, Evolutionary Robotics is an informative and inspiring book that provides a through examination of the subject. It is suitable for researchers and postgraduate students who are interested in this subject"
(2001) Industrial Robot: An International Journal, 4:350-351.

"In summary, the book is highly reccommended for all involved in the field of evolutionary robotics. It will be an important reference for experimental and theoretical studies in evolutionary robotics for quite some time."
Horatiu Voicu (2002) AI Magazine, pp.106-107.

Last Update: August 2002

Back to Nolfi homepage 

Stefano Nolfi
Institute of Cognitive Science and Technology
National Research Council (CNR), Rome
Viale Marx, 15 / 00137 / Rome / Italy
Tel.: ++39-06-86090231
Fax : ++39-06-824737
Email: nolfi@ip.rm.cnr.it