Using a Cognitive Architecture to Solve Simultaneous Localization and Mapping (SLAM) Problems
Technical Report,01 May 2005,01 May 2006
Human Research and Engineering Directorate, Army Research Laboratory Aberdeen Proving Ground United States
Pagination or Media Count:
The cognitive production system architecture, the Atomic Components of Thought-Rational ACT-R, was applied to the problem of simultaneous localization and mapping SLAM. The map space was represented as a pseudo-topological map of salient features, which was then evaluated with a production system architecture ACT-R. Results showed that after therobot was placed in five unique locations, it was able to recognize them as spaces that it had previously visited. Results also showed that intrinsic error associated with robotic sensor readings was overcome with the use of the simulated human memory activation equations of ACT-R.