Multilayer feedforward networks are universal approximators
Neural Networks
Characterization of periodic attractors in neural ring networks
Neural Networks
A modular network for legged locomotion
Physica D
Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments
Evolutionary Computation
SO(2)-networks as neural oscillators
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
A digital hardware pulse-mode neuron with piecewise linear activation function
IEEE Transactions on Neural Networks
Neural control of a modular multi-legged walking machine: Simulation and hardware
Robotics and Autonomous Systems
Hi-index | 0.00 |
Using the principle of homeostasis, we derive a learning rule for a specific recurrent neural network structure, the so-called Self-Adjusting Ring Module (SARM). Several of these Ring Modules can be plugged together to drive segmented artificial organisms, for example centipede-like robots. Controlling robots of variable morphologies by SARMs has major advantages over using Central Pattern Generators (CPGs). SARMs are able to immediately reconfigure themselves after reassembly of the robot's morphology. In addition, there is no need to decide on a singular place for the robot's control processor, since SARMs represent inherently distributed control structures.