Cognitive navigation based on non-uniform Gabor space sampling, unsupervised growing networks, and reinforcement learning

We study spatial learning and navigation for autonomous agents. A state space representation is constructed by unsupervised Hebbian learning during exploration. As a result of learning, a representation of the continuous two-dimensional (2-D) manifold in the high-dimensional input space is found. The representation consists of a population of localized overlapping place fields covering the 2-D space densely and uniformly. This space coding is comparable to the representation provided by hippocampal place cells in rats. Place fields are learned by extracting spatio-temporal properties of the environment from sensory inputs. The visual scene is modeled using the responses of modified Gabor filters placed at the nodes of a sparse Log-polar graph. Visual sensory aliasing is eliminated by taking into account self-motion signals via path integration. This solves the hidden state problem and provides a suitable representation for applying reinforcement learning in continuous space for action selection. A temporal-difference prediction scheme is used to learn sensorimotor mappings to perform goal-oriented navigation. Population vector coding is employed to interpret ensemble neural activity. The model is validated on a mobile Khepera miniature robot.


Published in:
IEEE Transactions on Neural Networks, 15, 3, 639-652
Year:
2004
Publisher:
Institute of Electrical and Electronics Engineers
ISSN:
1045-9227
Note:
article
Other identifiers:
Laboratories:




 Record created 2006-12-12, last modified 2018-01-27

External link:
Download fulltext
n/a
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)