Recurrent neural robot controllers: feedback mechanisms for identifying environmental motion dynamics

Authors:
Stephen Paul Mckibbin;Bala Amavasai;Arul N. Selvan;Fabio Caparrelli;W. A. Othman
Affiliations:
Microsystems & Machine Vision Laboratory, Materials & Engineering Research Institute, Sheffield Hallam University, Sheffield, UK S1 1WB;Microsystems & Machine Vision Laboratory, Materials & Engineering Research Institute, Sheffield Hallam University, Sheffield, UK S1 1WB and Mechanistic Research, Procter & Gamble, Reading, UK RG2 ...;Microsystems & Machine Vision Laboratory, Materials & Engineering Research Institute, Sheffield Hallam University, Sheffield, UK S1 1WB;Microsystems & Machine Vision Laboratory, Materials & Engineering Research Institute, Sheffield Hallam University, Sheffield, UK S1 1WB;Microsystems & Machine Vision Laboratory, Materials & Engineering Research Institute, Sheffield Hallam University, Sheffield, UK S1 1WB
Venue:
Artificial Intelligence Review
Year:
2007

Citing 4
Cited 0

Active perception: a sensorimotor account of object categorization

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Evolving integrated controllers for autonomous learning robots using dynamic neural networks

ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
Evolution of Neural Architecture Fitting Environmental Dynamics

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
The particle swarm - explosion, stability, and convergence in amultidimensional complex space

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a series of recurrent controllers for mobile robots have been developed. The system combines the iterative learning capability of neural controllers and the optimisation ability of particle swarms. In particular, three controllers have been developed: an Exo-sensing, an Ego-sensing and a Composite controller which is the hybrid of the latter two. The task for each controller is to learn to follow a moving target and identify its trajectory using only local information. We show how the learned behaviours of each architecture rely on different sensory representations, although good results are obtained in all cases.