Acquisition of 3-D Map Structures for Mobile Robots

Abstract

For an autonomous mobile robot to move around intelligently in its surroundings, it must possess a map of the environment which it can use to determine where it is, where it wants to go, and the best way to get there. The ability to successfully navigate in its surroundings allows the robot to perform more complicated tasks with greater autonomy. When a mobile robot is introduced into an unfamiliar environment, it does not have that map available and therefore must generate one itself. Methods currently exist to perform such a task in an environment where the robot moves about a single plane. However, this limitation restricts the robot's movement to a at and smooth surface (typically an indoor setting). This project builds upon current map building techniques to enable a ground-based mobile robot to navigate robustly in an unfamiliar, more three-dimensional (outdoor) environment. A new map structure has been developed to store three-dimensional information in a compressed form. It represents the robot's environment as a two-dimensional surface existing in three-dimensional space. This map structure was implemented on an all-terrain outdoor robot for use in urban environments. The map structure was tested both by comparing generated maps to the environment on which they were based, and by testing the robots ability to navigate with them. The map structure has been shown to accurately model the robot's environment and enable the robot to navigate in it while requiring few computational resources.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 07, 2002
Accession Number
ADA403360

Entities

People

  • Edward H. Fong

Organizations

  • United States Naval Academy

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Acquisition
  • Artificial Intelligence
  • Autonomous Navigation
  • Collision Avoidance
  • Coordinate Systems
  • Dead Reckoning
  • Detectors
  • Inertial Navigation
  • Inertial Navigation Systems
  • Measurement
  • Motion Planning
  • Navigation
  • Robot Navigation
  • Robots
  • Three Dimensional
  • Two Dimensional
  • United States Naval Academy

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Space
  • Space - Spacecraft Maneuvers