Composite Artificial Neural Network for Controlling Artificial Flying Creature
This paper proposes a composite artificial neural network (CANN). The CANN is a method that contains concepts of an evolutionary artificial neural network, a neural network ensemble and subsumption architecture, and designed for efficient robot control. In the CANN, while low-level ANNs work as actual controllers for calculating outputs, a high-level work as a selector. The high-level ANN works up some optimized ANNs, which output real values, into a controller. In order to verify performance of the CANN, numerical experiments are carried out. An artificial flying creature (AFC) is controlled by the CANN for flying to a target point. Motions of the AFC is calculated by a virtual physics environment, which consists of functions of a physical engine PhysX and a simple drag force calculation. Experimental results show that performance of the CANN is higher than that of a simple ANN.
Keywordsartificial life evolutionary artificial neural network particle swarm optimization neural network ensemble
Unable to display preview. Download preview PDF.
- 1.Sims, K.: Evolving virtual creatures. In: Proc. 21st Annual Conference on Computer Graphics and Interactive Techniques, pp. 15–22 (1994)Google Scholar
- 3.Allen, B., Faloutsos, P.: Complex networks of simple neurons for bipedal locomotion. In: IROS 2009, Proc. of 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4457–4462 (2009)Google Scholar
- 4.Sareni, B., Krahenbuhl, L.: Fitness sharing and niching methods revisited. IEEE Transactions on Evolutionary Computation (1998)Google Scholar
- 5.Gomez, F.: Sustaining diversity using behavioral information distance. In: GECCO 2009, Proc. of the 11th Annual Conference on Genetic and Evolutionary Computation (2009)Google Scholar
- 8.Kennedy, J., Eberhart, R.: Particle swarm optimization. IEEE International Conference on Neural Networks 4, 1942–1948 (1995)Google Scholar