Accession Number : ADA294053

Title :   Using a Genetic Algorithm to Learn Strategies for Collision Avoidance and Local Navigation.

Corporate Author : NAVAL RESEARCH LAB WASHINGTON DC

Personal Author(s) : Schultz, Alan C.

PDF Url : ADA294053

Report Date : 1990

Pagination or Media Count : 13

Abstract : Navigation through obstacles such as mine fields is an important capability for autonomous underwater vehicles. One way to produce robust behavior is to perform projective planning. However, real-time performance is a critical requirement in navigation. What is needed for a truly autonomous vehicle are robust reactive rules that perform well in a wide variety of situations, and that also achieve real-time performance. In this work, SAMUEL, a learning system based on genetic algorithms, is used to learn high-performance reactive strategies for navigation and collision avoidance. (AN)

Descriptors :   *ALGORITHMS, *LEARNING MACHINES, *RULE BASED SYSTEMS, *UNDERWATER NAVIGATION, VELOCITY, REQUIREMENTS, OPTIMIZATION, ADAPTIVE CONTROL SYSTEMS, UNDERWATER VEHICLES, STRATEGIC ANALYSIS, REAL TIME, PERFORMANCE(ENGINEERING), MINEFIELDS, SELF OPERATION, HEURISTIC METHODS, KNOWLEDGE BASED SYSTEMS, SYSTEMS ANALYSIS, AUTOMATIC, COLLISION AVOIDANCE, SONAR, HIGH LEVEL LANGUAGES, RANDOM WALK.

Subject Categories : Cybernetics
      Underwater and Marine Navigation and Guidance

Distribution Statement : APPROVED FOR PUBLIC RELEASE