Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-organizing Machines
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.
What people are saying - Write a review
Evolutionary and neural techniques
How to evolve robots
Evolution of simple navigation
Power and limits of reactive intelligence
Beyond reactive intelligence
Learning and evolution
Other editions - View all
ability activation adaptive agent approach arena artificial evolution back-propagation basic behaviors battery best individuals cells changes chapter chromosome co-evolution co-evolving complex computed connection weights constraints control system corresponding cycles cylinder cylindrical objects described in section discriminate dynamics effective encoding environment evolutionary algorithm evolutionary process evolutionary robotics evolvable hardware evolved controllers evolved individuals evolved robots example experiments described figure fitness function fitness landscape fitness values Floreano FPGA Francesco Mondada genetic algorithm genotype genotype-to-phenotype gripper hexapod robot hidden units incremental infrared sensors input units interaction Khepera robot lifetime mapping master tournament move mutation neural network neurons node Nolfi oscillators output units parameters performance phenotype physical robots population position predator and prey problem produce random randomly real robots replications represents rotation selected sensory patterns sensory-motor coordination simple simulated solutions solve space speed strategy synaptic synaptic weights target task tested trajectory visual walls wheel
Page 311 - In P. Husbands, & I. Harvey (eds.), Proceedings of the fourth European Conference on Artificial Life. Cambridge, MA: MIT Press.
Page 303 - AJ Ijspeert, J. Hallam, and D. Willshaw. From lampreys to salamanders: evolving neural controllers for swimming and walking. In R. Pfeifer, B. Blumberg, J.-A. Meyer, and SW Wilson, editors, From Animals to Animats, Proceedings of the Fifth International Conference of The Society for Adaptive Behavior (SAB98), pages 390-399.
Page 313 - Separability is a learner's best friend. In JA Bullinaria, DW Glasspool, and G. Houghton, editors, Proceedings of the Fourth Neural Computation and Psychology Workshop: Connectionist Representations, pages 40-47.