Accession Number : ADA456805


Title :   Developing Autonomous Vehicles That Learn to Navigate by Mimicking Human Behavior


Descriptive Note : Final rept. 1 Mar 2005-30 Jun 2006


Corporate Author : IDAHO UNIV MOSCOW DEPT OF MECHANICAL ENGINEERING


Personal Author(s) : Edwards, Dean B ; Canning, John ; Alberts, Joel


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a456805.pdf


Report Date : 28 Sep 2006


Pagination or Media Count : 15


Abstract : A program initiated by the Defense Advanced Research Project Agency (DARPA) called Learning Applied to Ground Robots (LAGR) is developing control algorithms that would allow a vehicle to safely travel cross-country. The University of Idaho with funding from the Office of Naval Research is participating in this program in which DARPA provided a vehicle having both sensors and supporting software for the sensors. We used the LAGR vehicle to help solve navigation problems that afflicts both underwater crawlers and ground vehicles. With the application of fuzzy logic and specialized software, we were able to successfully autonomously navigate in an unstructured environment to a specific target or location.


Descriptors :   *ADAPTIVE CONTROL SYSTEMS , *AUTONOMOUS NAVIGATION , *FUZZY LOGIC , *LAND NAVIGATION , OPTIMIZATION , UNDERWATER VEHICLES , ROBOTS , LEARNING MACHINES , GROUND VEHICLES


Subject Categories : Cybernetics
      Land and Riverine Navigation and Guidance
      Bionics


Distribution Statement : APPROVED FOR PUBLIC RELEASE