Title
A Self-Organized One-Neuron Controller for Artificial Life on Wheels
Authors
Claudius Gros, Laura Martin, Bulcsu Sandor
Schedule
Date: Wednesday 6 Sept
Talk Time: TBA
Session: Evolutionary robotics 1 10:30
Keywords
self-oranization, complaint actuators, emerging locomotion, sensorimotor loop, neural networks, dynamical systems
Abstract
We study simulated animats in terms of wheeled robots with the most simple neural controller possible – a single neuron per actuator. The system is fully self-organized in the sense that the controlling neuron receives uniquely the actual angle of the wheel as an input. Non-trivial locomotion results in structured environments, with the robot determining autonomously the direction of movement (time-reversal symmetry is spontaneously broken). Our controller, which mimics the mechanism used to transmit power in steam locomotives, abstracts from the body plan of the animat, working without problems also for chains of individual two-wheeled cars. Our controller is fully compliant and may be also used, in the spirit of morphological computation, as a basic unit for higher-level evolutionary algorithms.
