Models of visually guided routes in ants: embodiment simplifies route acquisition

Authors:
Bart Baddeley;Paul Graham;Andrew Philippides;Philip Husbands
Affiliations:
Centre for Computational Neuroscience and Robotics, University of Sussex, Brighton, UK;Centre for Computational Neuroscience and Robotics, University of Sussex, Brighton, UK;Centre for Computational Neuroscience and Robotics, University of Sussex, Brighton, UK;Centre for Computational Neuroscience and Robotics, University of Sussex, Brighton, UK
Venue:
ICIRA'11 Proceedings of the 4th international conference on Intelligent Robotics and Applications - Volume Part II
Year:
2011

Citing 6
Cited 0

Learning View Graphs for Robot Navigation

Autonomous Robots - Special issue on autonomous agents
Training products of experts by minimizing contrastive divergence

Neural Computation
Depth, contrast and view-based homing in outdoor scenes

Biological Cybernetics
Linked Local Navigation for Visual Route Guidance

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Linked Local Visual Navigation and Robustness to Motor Noise and Route Displacement

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Using fast weights to improve persistent contrastive divergence

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is known that ants learn long visually-guided routes through complex terrain. However, the mechanisms by which visual information is first learnt and then used to control a route direction are not well understood. In this paper we investigate whether a simple approach, involving scanning the environment and moving in the direction that appears most familiar, can provide a model of visually guided route learning in ants. The specific embodiment of an ant's visual system means that movement and viewing direction are tightly coupled, a familiar view specifies a familiar direction of viewing and thus a familiar movement to make. We show the feasibility of our approach as a model of ant-like route acquisition by learning non-trivial routes through a simulated environment firstly using the complete set of views experienced during learning and secondly using an approximation to the distribution of these views.