Today, autonomous robots are used in a rather limited range of applications such as exploration of inaccessible locations, cleaning floors, mowing lawns etc. However, ongoing hardware improvements (and human fantasy) steadily reveal new robotic applications of significantly higher sophistication. For such applications, the crucial bottleneck in the engineering process tends to shift from physical boundaries to controller generation. As an attempt to automatize this process, Evolutionary Robotics has successfully been used to generate robotic controllers of various types. However, a major challenge of the field remains the evolution of truly complex behavior. Furthermore, automatically created controllers often lack analyzability which makes them useless for safety-critical applications. In this book, a simple controller model based on Finite State Machines is proposed which allows a straightforward analysis of evolved behaviors. To increase the model's evolvability, a procedure is introduced which, by adapting the genotype-phenotype mapping at runtime, efficiently traverses both the behavioral search space as well as (recursively) the search space of genotype-phenotype mappings. Furthermore, a data-driven mathematical framework is proposed which can be used to calculate the expected success of evolution in complex environments.

An overview of the basic concepts and methodologies of evolutionary robotics, which views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention.

In this book the use of ER techniques for the design of self-organising group behaviours, for both simulated and real robots is introduced. The book tries to mediate between two apparently opposed perspectives: engineering and cognitive science. The experiments presented in the book and the results obtained contribute to the assessment of ER not only as a design tool, but also as a methodology for modelling and understanding intelligent adaptive behaviours.

This exciting study explores the novel insight, based on well-established ethological principles, that animals, humans, and autonomous robots can all be analyzed as multi-task autonomous control systems.

Abstract: "This paper sets out a conceptual framework for the open-ended artificial evolution of complex behaviour in autonomous agents. If recurrent dynamical neural networks (or similar) are used as phenotypes, then a Genetic Alogorithm that employs variable length genotypes, such as Inman Harvey's SAGA, is capable of evolving arbitrary levels of behavioural complexity. Furthermore, with simple restrictions on the encoding scheme that governs how genotypes develop into phenotypes, it may be guaranteed that if an increase in fitness requires an increase in behavioural complexity, then it will evolve. In order for this process to be practicable as a design alternative, however, the time periods involved must be acceptable. The final part of this paper looks at general ways in which the encoding scheme may be modified to speed up the process. Experiments are reported in which different categories of scheme were tested against each other, and conclusions are offered as to the most promising type of encoding scheme for a viable open-ended Evolutionary Robotics."

Embodied and evolving systems — biological or robotic — are interacting networks of structure, function, information, and behavior. Understanding these complex systems is the goal of the research presented in this book. We address different questions and hypotheses about four essential topics in complex systems: evolvability, environments, embodiment, and emergence. Using a variety of approaches, we provide different perspectives on an overarching, unifying question: How can embodied and evolutionary robotics illuminate (1) principles underlying biological evolving systems and (2) general analytical frameworks for studying embodied evolving systems? The answer — model biological processes to operate, develop, and evolve situated, embodied robots.

The book presents an overview of current research on biologically inspired autonomous robotics from the perspective of some of the most relevant researchers in this area. The book crosses several boundaries in the field of robotics and the closely related field of artificial life. The key aim throughout the book is to obtain autonomy at different levels. From the basic motor behavior in some exotic robot architectures right through to the planning of complex behaviors or the evolution of robot control structures, the book explores different degrees and definitions of autonomous behavior. These behaviors are supported by a wide variety of modeling techniques: structural grammars, neural networks, and fuzzy logic and evolution underlies many of the development processes. Thus this text can be used by scientists and students interested in these areas and provides a general view of the field for a more general audience.