Learning Place Cells from Sonar Data
Ollington, R and Vamplew, P (2004) Learning Place Cells from Sonar Data. In: AISAT2004: International Conference on Artificial Intelligence in Science and Technology, 21-25 November 2004, Hobart, Tasmania, Australia.
|PDF - Requires a PDF viewer|
A place cell system is developed that is able to provide
robust localisation using simple sonar information only.
The system uses egocentric view cells, based on the
Adaptive Response Function Neuron, as sensory input to
correct for path integration errors. The major
advantage of this system is that place field centres are
fixed prior to training, allowing downstream
navigational systems to make relevant predictions
immediately upon entering a new environment.
|Item Type:||Conference or Workshop Item (Paper)|
|Keywords:||robot localisation, robot navigation, sonars, place cells, view cells, dead reckoning, path integration|
|Deposited By:||utas eprints|
|Deposited On:||26 Nov 2004|
|Last Modified:||18 Jul 2008 19:37|
|ePrint Statistics:||View statistics for this ePrint|
Repository Staff Only: item control page