Bot, Martijn, Urquhart, Neil B and Chisholm, Ken (2001) Agent motion planning with GAs enhanced by memory models. Genetic and Evolutionary Computation Conference - GECCO 2001. pp. 227-234.
Available under License Creative Commons Attribution Non-commercial.
Download (136kB) | Preview
The Tartarus problem may be considered a benchmark problem in the field of robotics. A robotic agent is required to move a number of blocks to the edge of an environment. The location of the blocks and position of the robot is unknown initially. The authors present a framework that allows the agent to learn about its environment and plan ahead using a GA to solve the problem. The authors prove that the GA based method provides the best published result on the Tartarus problem. An exhaustive search is used within the framework as a comparison, this provides a higher score still. This paper presents the two best Tartarus results yet published
|Uncontrolled Keywords:||Tartarus; robotic agent; GA; memory models;|
|University Divisions/Research Centres:||Faculty of Engineering, Computing and Creative Industries > School of Computing|
|Dewey Decimal Subjects:||600 Technology > 620 Engineering > 629 Vehicle engineering|
|Library of Congress Subjects:||T Technology > TK Electrical engineering. Electronics Nuclear engineering|
|Depositing User:||Computing Research|
|Date Deposited:||30 Jun 2010 13:17|
|Last Modified:||12 Sep 2013 11:40|
Actions (login required)