Evolving Real-time Behavior Modules for a real Robot with GP

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@InProceedings{olmer:1996:ertbm,

• author = "Markus Olmer and Peter Nordin and Wolfgang Banzhaf",
• title = "Evolving Real-time Behavior Modules for a real Robot with {GP}",
• booktitle = "Proceedings of the 6th international symposium on robotics and manufacturing, ISRAM-96",
• year = "1996",
• editor = "M. Jamshidi and F. Pin and P. Dauchez",
• pages = "675--680",
• address = "Montpellier, France",
• publisher_address = "New York",
• month = may,
• publisher = "Asme Press",
• keywords = "genetic algorithms, genetic programming",
• URL = "http://www.cs.mun.ca/~banzhaf/papers/isram96.pdf",
• size = "6 pages",
• abstract = "In this paper we demonstrate an efficient method which divides a control task into smaller sub--tasks. We use a Genetic Programming system that first learns the sub-tasks and then evolves a higher--level action selection strategy for deciding which of the evolved lower--level algorithms should be in control. The Swiss miniature robot Khepera is employed as the experimental platform. Results are presented which show that the robot is indeed able to evolve both the control algorithms for the different lower--level tasks and the strategy for the selection of tasks. The evolved solutions also show robust performance even if the robot is lifted and placed in a completely different environment or if obstacles are moved around.",
• notes = "ISRAM 96, We have done some experiments combining GP and a subsumption architecture for robotic control. The system controlled a Khepera robot learning four different behaviours.",

}

Genetic Programming entries for Markus Olmer Peter Nordin Wolfgang Banzhaf

Citations