Embedded visual SLAM for navigation of an autonomous vehicle

Marco A. Moreno-Armend́ariz, Carlos A. Duchanoy, ́Angel A.G. Zanatta-Júarez, Carlos A. Cruz-Villar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

An important objective of an autonomous vehicle is to navigate through an unknown environment. A method used to achieve this objective is to generate a map. A map provides the means to the vehicle to create paths between the visited places autonomously in order to perform a task. A particular problem is to obtain such a map when there is no initial knowledge of the surroundings or not even the initial position of the robot in the environment. The present paper shows a new design of a Visual SLAM processor that solves this problem and it is implemented on an FPGA. The processor is then tested on a differential traction mobile robot with a computer vision system that travels on a controlled unknown environment. The experimental results obtained show a good performance in real time.

Original languageEnglish
Title of host publicationProceedings of the 2nd IASTED International Conference on Robotics, Robo 2011
Pages211-218
Number of pages8
DOIs
StatePublished - 2011
Event2nd IASTED International Conference on Robotics, Robo 2011 - Pittsburgh, PA, United States
Duration: 7 Nov 20119 Nov 2011

Publication series

NameProceedings of the 2nd IASTED International Conference on Robotics, Robo 2011

Conference

Conference2nd IASTED International Conference on Robotics, Robo 2011
Country/TerritoryUnited States
CityPittsburgh, PA
Period7/11/119/11/11

Keywords

  • Autonomous vehicle
  • Embedded system
  • Visual slam

Fingerprint

Dive into the research topics of 'Embedded visual SLAM for navigation of an autonomous vehicle'. Together they form a unique fingerprint.

Cite this