Using an evolutionary algorithm to determine the parameters of a biologically inspired model of head direction cells

Authors:
Theocharis Kyriacou
Affiliations:
Research Institute for the Environment, Physical Sciences and Applied Mathematics (EPSAM), Keele University, Staffordshire, UK
Venue:
Journal of Computational Neuroscience
Year:
2012

Citing 10
Cited 0

Qualitative navigation for mobile robots

Artificial Intelligence
Sigma-Pi learning: on radial basis functions and cortical associative learning

Advances in neural information processing systems 2
Evolution strategies –A comprehensive introduction

Natural Computing: an international journal
A Distributed Model for Mobile Robot Environment-Learning and Navigation

A Distributed Model for Mobile Robot Environment-Learning and Navigation
Head Direction Cells and the Neural Mechanisms of Spatial Orientation (Bradford Books)

Head Direction Cells and the Neural Mechanisms of Spatial Orientation (Bradford Books)
Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)

Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)
“dead reckoning,” landmark learning, and the sense of direction: A neurophysiological and computational hypothesis

Journal of Cognitive Neuroscience
An implementation of a biologically inspired model of head direction cells on a robot

TAROS'11 Proceedings of the 12th Annual conference on Towards autonomous robotic systems
Ant colony optimization

IEEE Computational Intelligence Magazine
Map-based navigation in mobile robots

Cognitive Systems Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

A biologically inspired model of head direction cells is presented and tested on a small mobile robot. Head direction cells (discovered in the brain of rats in 1984) encode the head orientation of their host irrespective of the host's location in the environment. The head direction system thus acts as a biological compass (though not a magnetic one) for its host. Head direction cells are influenced in different ways by idiothetic (host-centred) and allothetic (not host-centred) cues. The model presented here uses the visual, vestibular and kinesthetic inputs that are simulated by robot sensors. Real robot-sensor data has been used in order to train the model's artificial neural network connections. The main contribution of this paper lies in the use of an evolutionary algorithm in order to determine the values of parameters that determine the behaviour of the model. More importantly, the objective function of the evolutionary strategy used takes into consideration quantitative biological observations reported in the literature.