论文信息 - Behavioral Interactions of Two Individual Arm Robots Using Independent Chaos in Recurrent Neural Networks

Behavioral Interactions of Two Individual Arm Robots Using Independent Chaos in Recurrent Neural Networks

Based on a heuristic idea and by computer experiment, we show that chaos introduced into a recurrent neural network model can enable “complex control with simple rule(s)” under ill-posed situations. Furthermore, we show behavioral interactions of two individual arm robots driven by independent chaos implemented into each arm control system using recurrent neural networks.

[1] I. Tsuda. Toward an interpretation of dynamic neural activity in terms of chaotic dynamical systems. , 2001, The Behavioral and brain sciences.

[2] Shigetoshi Nara,et al. CHAOTIC MEMORY DYNAMICS IN A RECURRENT NEURAL NETWORK WITH CYCLE MEMORIES EMBEDDED BY PSEUDO-INVERSE METHOD , 1995 .

[3] S. Nara. Can potentially useful dynamics to solve complex problems emerge from constrained chaos and/or chaotic itinerancy? , 2003, Chaos.

[4] Shigetoshi Nara,et al. Application of chaotic dynamics in a recurrent neural network to control: hardware implementation into a novel autonomous roving robot , 2008, Biological Cybernetics.

[5] P. Davis,et al. Chaotic wandering and search in a cycle-memory neural network , 1992 .

[6] Shigetoshi Nara,et al. Adaptive Control of Robot Systems with Simple Rules Using Chaotic Dynamics in Quasi-layered Recurrent Neural Networks , 2010, IJCCI.

[7] Shigetoshi Nara,et al. A Solution for Two-Dimensional Mazes with Use of Chaotic Dynamics in a Recurrent Neural Network Model , 2004, Neural Computation.

[8] W. Freeman,et al. How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.