Inproceedings3006: Unterschied zwischen den Versionen
Lko (Diskussion | Beiträge) K |
Lko (Diskussion | Beiträge) |
||
Zeile 9: | Zeile 9: | ||
{{Inproceedings | {{Inproceedings | ||
|Referiert=True | |Referiert=True | ||
+ | |BibTex-ID=koenig:2009b | ||
|Title=A Completely Evolvable Genotype-Phenotype Mapping for Evolutionary Robotics | |Title=A Completely Evolvable Genotype-Phenotype Mapping for Evolutionary Robotics | ||
|Year=2009 | |Year=2009 | ||
Zeile 15: | Zeile 16: | ||
|Pages=175-185 | |Pages=175-185 | ||
|Publisher=IEEE Computer Society | |Publisher=IEEE Computer Society | ||
+ | |Address=Washington DC | ||
}} | }} | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=To achieve a desired global behavior for a swarm of robots where each robot has a local view and operating range in the environment is a well-known and challenging problem. Evolutionary Robotics is a self-adaptation approach which has been shown to effectively find robot controllers for behaviors which are hard to implement by hand. There, evolvability is highly dependent on controller representation during evolution. It is known that using a genotypic controller representation which also encodes parts of the genotype-phenotype mapping (GPM) can lead to a | |Abstract=To achieve a desired global behavior for a swarm of robots where each robot has a local view and operating range in the environment is a well-known and challenging problem. Evolutionary Robotics is a self-adaptation approach which has been shown to effectively find robot controllers for behaviors which are hard to implement by hand. There, evolvability is highly dependent on controller representation during evolution. It is known that using a genotypic controller representation which also encodes parts of the genotype-phenotype mapping (GPM) can lead to a | ||
meta-adaptation of the evolutionary operators to the search space structure, thus improving evolvability. We enhance this idea using a fully flexible GPM which is represented in the same way as the behavioral controllers are, and, therefore, can be completely evolved along with the behavior. The approach is based on finite state machines and extends an existing framework for decentralized evolution of robot behavior in swarms of mobile robots. Experiments indicate that the evolvable GPM outperforms both the extensively improved operators of the existing framework and a standard operator for the new real-valued genotypes with fixed GPM. | meta-adaptation of the evolutionary operators to the search space structure, thus improving evolvability. We enhance this idea using a fully flexible GPM which is represented in the same way as the behavioral controllers are, and, therefore, can be completely evolved along with the behavior. The approach is based on finite state machines and extends an existing framework for decentralized evolution of robot behavior in swarms of mobile robots. Experiments indicate that the evolvable GPM outperforms both the extensively improved operators of the existing framework and a standard operator for the new real-valued genotypes with fixed GPM. | ||
+ | |ISBN=978-0-7695-3794-8 | ||
|Forschungsgruppe=Effiziente Algorithmen | |Forschungsgruppe=Effiziente Algorithmen | ||
}} | }} |
Version vom 16. Februar 2010, 15:24 Uhr
A Completely Evolvable Genotype-Phenotype Mapping for Evolutionary Robotics
A Completely Evolvable Genotype-Phenotype Mapping for Evolutionary Robotics
Published: 2009
September
Buchtitel: Proceedings of the Third IEEE International Conference on Self-Adaptive and Self-Organizing Systems
Seiten: 175-185
Verlag: IEEE Computer Society
Erscheinungsort: Washington DC
Referierte Veröffentlichung
BibTeX
Kurzfassung
To achieve a desired global behavior for a swarm of robots where each robot has a local view and operating range in the environment is a well-known and challenging problem. Evolutionary Robotics is a self-adaptation approach which has been shown to effectively find robot controllers for behaviors which are hard to implement by hand. There, evolvability is highly dependent on controller representation during evolution. It is known that using a genotypic controller representation which also encodes parts of the genotype-phenotype mapping (GPM) can lead to a
meta-adaptation of the evolutionary operators to the search space structure, thus improving evolvability. We enhance this idea using a fully flexible GPM which is represented in the same way as the behavioral controllers are, and, therefore, can be completely evolved along with the behavior. The approach is based on finite state machines and extends an existing framework for decentralized evolution of robot behavior in swarms of mobile robots. Experiments indicate that the evolvable GPM outperforms both the extensively improved operators of the existing framework and a standard operator for the new real-valued genotypes with fixed GPM.
ISBN: 978-0-7695-3794-8
Organic Computing Learning Robots Arena
Organic Computing, Agentensysteme, Evolutionäre Robotik