NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Real-time Accurate Surface Reconstruction Pipeline for Vision Guided Planetary Exploration Using Unmanned Ground and Aerial VehiclesThis report discusses work completed over the summer at the Jet Propulsion Laboratory (JPL), California Institute of Technology. A system is presented to guide ground or aerial unmanned robots using computer vision. The system performs accurate camera calibration, camera pose refinement and surface extraction from images collected by a camera mounted on the vehicle. The application motivating the research is planetary exploration and the vehicles are typically rovers or unmanned aerial vehicles. The information extracted from imagery is used primarily for navigation, as robot location is the same as the camera location and the surfaces represent the terrain that rovers traverse. The processed information must be very accurate and acquired very fast in order to be useful in practice. The main challenge being addressed by this project is to achieve high estimation accuracy and high computation speed simultaneously, a difficult task due to many technical reasons.
Document ID
20150005526
Acquisition Source
Jet Propulsion Laboratory
Document Type
Other
External Source(s)
Authors
Almeida, Eduardo DeBrito
(Brown Univ. Providence, RI, United States)
Date Acquired
April 10, 2015
Publication Date
August 1, 2012
Subject Category
Instrumentation And Photography
Lunar And Planetary Science And Exploration
Cybernetics, Artificial Intelligence And Robotics
Distribution Limits
Public
Copyright
Other
Keywords
computer vision
autonomous navigation systems
aerial unmanned robots

Available Downloads

There are no available downloads for this record.
No Preview Available