Visual Navigation Constructing and Utilizing Simple Maps of an Indoor Environment

Abstract

Much work with mobile robots has been done in the past using both vision and sonar to build maps, or, given a map, to successfully plan and execute trajectories to a goal. The most successful examples of robot navigation occurred in carefully engineered environments where the robot was able to accurately predict what its sensory input should be at any point, and correct for drift by comparing actual input to the projected input. In unstructured environments however, the problem became much harder, and the obvious approaches failed to produce good results. The problem is further complicated by the fact that most interesting environments are not static, but rather are changing continually. In this thesis I have attempted to attack the problem from a different angle altogether, using the way people navigate through buildings as insight and inspiration. The goal is to navigate through an office environment using only visual information gathered from four cameras, whose initial detailed configuration is not known, placed onboard a mobile robot. The method is insensitive to physical changes within the room it is inspecting, such as moving objects.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1989
Accession Number
ADA216761

Entities

People

  • Karen B. Sarachik

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Autonomous Navigation
  • Collision Avoidance
  • Composite Images
  • Computational Complexity
  • Computer Science
  • Computer Stereo Vision
  • Information Processing
  • Motion Planning
  • Navigation
  • Office Buildings
  • Recognition
  • Robot Navigation
  • Robots
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computational Modeling and Simulation
  • Naval Architecture and Marine Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Autonomy