Effect of representation size and visual ambiguity on RatSLAM system performance
Milford, Michael, Prasser, David, & Wyeth, Gordon (2006) Effect of representation size and visual ambiguity on RatSLAM system performance. In MacDonald, Bruce (Ed.) Proceedings of the Australasian Conference on Robotics and Automation 2006, Australian Robotics and Automation Association Inc, Auckland.
RatSLAM is a vision-based SLAM system based on extended models of the rodent hippocampus. RatSLAM creates environment representations that can be processed by the experience mapping algorithm to produce maps suitable for goal recall. The experience mapping algorithm also allows RatSLAM to map environments many times larger than could be achieved with a one to one correspondence between the map and environment, by reusing the RatSLAM maps to represent multiple sections of the environment. This paper describes experiments investigating the effects of the environment-representation size ratio and visual ambiguity on mapping and goal navigation performance. The experiments demonstrate that system performance is weakly dependent on either parameter in isolation, but strongly dependent on their joint values.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Paper|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Adaptive Agents and Intelligent Robotics (080101)|
|Copyright Owner:||Copyright 2006 [please consult the authors]|
|Deposited On:||23 Jun 2010 04:30|
|Last Modified:||29 Feb 2012 14:14|
Repository Staff Only: item control page