Evolutionary robot behavior via natural selection based on neural networks

Wang Hongyan1, Yang Jingan2
1Artificial Intelligence Institute, Hefei University of Technology, Hefei, Anhui, China
2Artificial Intelligence Institute, Hefei University of Technology, Hefei, Anhui, P. R. China

Tóm tắt

The traditional fitness function based methodology of artificial evolution is argued to be inadequate for the construction of entities with behaviors novel to their designers. Evolutionary emergence via natural selection (without an explicit fitness function) is the way forward. This paper primarily considers the question of what to evolve, and focuses on principles of developmental modularity in neural networks. To develop and test the ideas, an artificial world containing autonomous organisms has been created and is described. Experimental results show that the developmental system is well suited to long-term incremental evolution. Novel emergent strategies are identified both from an observer's perspective and in terms of their neural mechanisms.

Từ khóa

#Robots #Neural networks #Artificial neural networks #Artificial intelligence #Organisms #Genetic mutations #Large Hadron Collider #Evolutionary computation #Buildings #Life testing

Tài liệu tham khảo

channon, 1998, Perpetuating evolutionary emergence, Proc SAB yaeger, 1993, Computational genetics, physiology, metabolism, neural systems, learning, vision, and behavior or polyworld: Life in a new context, 263 boers, 1992, Biological metaphors and the design of modular artificial neural networks koza, 1992, Genetic Programming wang, 2000, Research on combined behavior method for evolutionary robot based on neural network, Journal of Computer research and development, 37, 1457 harvey, 1993, Evolutionary robotics and SAGA: the case for hill crawling and tournament selection wang, 2000, Research on evolutionary robot behavior using developmental network, Acta Enectronica Sinica, 28, 41 10.1016/0022-5193(68)90079-9 10.1007/3-540-61093-6_3 ray, 1991, An approach to the synthesis of life, Artificial Life II, 371 kitano, 1990, Designing neural networks using genetic algorithms with graph generation system, Complex Systems, 4, 461 zaera, 0, Evolving collective behaviours in synthetic fish, Proc SAB, 635