Matching of Ground-Based LiDAR and Aerial Image Data For Mobile Robot Localization in Densely Forested Environments

Abstract

We present a vision-based method for the autonomous geolocation of ground vehicles or unmanned mobile robots in forested environments. The method provides an estimate of the global horizontal position of a vehicle strictly based on finding a geometric match between a map of observed tree stems, scanned in 3D by sensors onboard the vehicle, to another stem map estimated from the structure of tree crowns observed in overhead imagery of the forest canopy. This method can be used in real-time as a complement to the traditional Global Positioning System (GPS) in areas where signal coverage is inadequate due to attenuation by the forest canopy, or due to intentional denied access. The method presented in this paper has two key properties that are significant: 1) It does not require a priori knowledge of the area surrounding the robot. 2) It uses the geometry of detected tree stems as the only input to determine horizontal geoposition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2013
Accession Number
ADA599851

Entities

People

  • Karl Iagnemma
  • Marwan Hussein
  • Masaaki Watanabe
  • Matthew Renner

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Accuracy
  • Aerial Photography
  • Algorithms
  • Cells
  • Data Sets
  • Engineering
  • Environment
  • Forests
  • Geolocation
  • Geometry
  • Ground Based
  • High Resolution
  • Inertial Measurement Units
  • Lidar
  • Simultaneous Localization And Mapping
  • Supervised Machine Learning
  • Vehicles

Readers

  • Forest Ecology
  • Robotics and Automation.
  • Sensor Fusion and Tracking Systems.

Technology Areas

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