Learning to Move in Modular Robots using Central Pattern Generators and Online Optimization
International Journal of Robotics Research
An adaptive, self-organizing dynamical system for hierarchical control of bio-inspired locomotion
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
This paper investigates the ability of STRAGEN to construct state trajectories so as to control the locomotion of legged robots. STRAGEN is a model of a self-organized artificial neural network which has a variable topology. Two scenarios are developed: one for checking the behavior of STRAGEN vis-à-vis noisy data and other to test the ability of STRAGEN to construct states belonging to different trajectories.