Book review

Citation

Butun, E. (2008), "Book review", Industrial Robot, Vol. 35 No. 3. https://doi.org/10.1108/ir.2008.04935cae.001

Book review

Article Type: Book review From: Industrial Robot: An International Journal, Volume 35, Issue 3.

Mobile robots: the evolutionary approach

Nadia Nedjah, Leandro Dos Santos Coelho and Luiza de Macedo Mourelle (Editors)SpringerPublication date: April 12, 2007£77.00223 pp.ISBN 978-3-540-49719-6, web site: www.springer.com/engineering/book/978-3- 540-49719-6

This book focuses mobile robots designed using evolutionary computation approaches and it is organized in two main parts: evolutionary mobile robots and learning mobile robots.

Part I. Evolutionary mobile robots

Authors introduce a new hybrid approach of differential evaluation combined with chaos to the optimization for path planning of mobile robots by new chaotic operators based on logistic map in Chapter 1, entitled “Differential evolution approach using chaotic sequences applied to planning of mobile robot in a static environment with obstacles.” An original method for the evolutionary design of robotic systems for locomotion on rough terrain with optimized control of system in a complex environment is proposed in Chapter 2 entitled “Evolving modular robots for rough terrain exploration.” In Chapter 3, entitled “Evolutionary navigation of autonomous robots under varying terrain conditions,” a fuzzy-genetic approach providing optimal path and trajectory planning by modeling terrain conditions using fuzzy-linguistic variables to allow for the imprecision and uncertainty of the terrain data. The authors investigate how aggregate fitness functions have been and continue to be used in evolutionary robotics in Chapter 4 entitled “Aggregate selection in evolutionary robotics.” In Chapter 5 entitled “Evolving fuzzy classifier for novelty detection and landmark recognition by mobile robots,” with a presentation an approach to real-time landmark recognition and simultaneous classifier design for mobile robotics.

Part II. Learning mobile robots

In Chapter 6 entitled “Reinforcement learning for autonomous robotic fish,” the authors discuss applications of reinforcement learning in an autonomous robotic fish by developing a three-layer control architecture. The author implement an solution including decomposition of the overall task into smaller groups by using qualitative and quantitative knowledge to make robot tasks able to be treated by reinforcement learning algorithms in Chapter 7 entitled “Module based autonomous learning for mobile robots.” In Chapter 8 entitled “A hybrid adaptive architecture for mobile robots based on reactive behaviors,” first high-level schemas commonly adopted for intelligent agent architectures is described and then main organization of the proposed architecture is presented. The scenario of a team of mobile robots working cooperatively is addressed by first presenting a distributed sensing algorithm and then a multi-robot motion planning algorithm using neural network-based methods in Chapter 9 entitled “Collaborative robots for infrastructure security operations.” In Chapter 10 entitled “Imitation learning: an application in a micro robot soccer game,” authors use both learning by imitation and learning by experience as an strategy to make robots grasp they should play soccer.

A wide range of subjects is presented such as the chaotic sequences and planning of mobile robot, navigation of autonomous robots, aggregate selection, fuzzy classifier and landmark recognition, reinforcement learning, module-based autonomous learning, hybrid adaptive architecture, collaborative robots and security applications and imitation learning. Interesting is it that a wide spectrum of sample works developed in robotic research throughout the world about evolutionary mobile robotics and success of the technique in related areas. The knowledge on this is presented on a high-scientific level as apply to the whole book.

To summarize, this book is a balanced, readable and accurate collection of reflections and solutions to the emerging problem of evolutionary mobile robotics. Even if algorithms are not detailed enough to be easily coded, this book is a good contribution of defining a lot of key points in this new field of research.

In summary, I recommend this book as a reference both for beginners, engineers and researchers in this exiting new sphere of mobile robotics.

Erhan ButunAssociate Professor, Civil Aviation College, Kocaeli University, Kocaeli, Turkey