Biologically inspired approaches to robotics: what can we learn from insects?
Communications of the ACM
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neural Network Perception for Mobile Robot Guidance
Neural Network Perception for Mobile Robot Guidance
Evolutionary Robotics: The Biology,Intelligence,and Technology
Evolutionary Robotics: The Biology,Intelligence,and Technology
Introduction to Autonomous Mobile Robots
Introduction to Autonomous Mobile Robots
Multi-robot learning with particle swarm optimization
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Memory-enhanced evolutionary robotics: the echo state network approach
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
The particle swarm - explosion, stability, and convergence in amultidimensional complex space
IEEE Transactions on Evolutionary Computation
Survey: Reservoir computing approaches to recurrent neural network training
Computer Science Review
Hi-index | 0.00 |
Recurrent neural networks (RNNs) have good modeling capability for nonlinear dynamic systems, but due to the difficulties for training this superiority is discounted. Echo state network (ESN) is a new paradigm for using RNNs with a simpler training method, where an RNN is generated randomly and only a readout is trained. ESN method has quickly become popular in robotics, such as for motor control, for navigation. However, the classical training method for ESNs can not ensure the dynamics asymptotic stability if the trained ESNs run in a closed-loop self-generative mode. The reason is analyzed at first. We then consider the ESN training problem as an optimization problem with a nonlinear constraint, and take a particle swarm optimization (PSO) algorithm solve it. In our simulation experiments, the ESNs are trained as "figure-eight" trajectory generators. The results show that the proposed PSO-based training method can effectively ensure the dynamics asymptotic stability as well as the precision of generating trajectories of the trained ESNs.