Developing Autonomous Vehicles That Learn to Navigate by Mimicking Human Behavior

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 28, 2006
Accession Number
ADA456805

Entities

People

  • Dean B. Edwards
  • Joel Alberts
  • John Canning

Organizations

  • University of Idaho

Tags

Communities of Interest

  • Autonomy
  • Ground and Sea Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Autonomous Navigation
  • Autonomous Vehicles
  • Collision Avoidance
  • Control Systems
  • Environment
  • Fuzzy Logic
  • Fuzzy Sets
  • Ground Vehicles
  • Image Processing
  • Learning
  • Logic
  • Motion Planning
  • Navigation
  • Robots
  • Two Dimensional
  • Vehicles

Fields of Study

  • Computer science

Readers

  • Robotics and Automation.
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy