Optical flow based obstacle avoidance for multi-rotor aerial vehicles

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

Abstract

The miniaturization of multi-rotor aerial vehicles (MAVs) poses challenges to autonomous navigation. Cameras are preferred due to the limited payload of MAVs. In this paper, we present an optical flow (OF)-based approach for obstacle avoidance in indoor environments with a payload constrained MAV. Our approach mainly utilizes Time-To-Contact (TTC) and balance strategy (BS), two basic principles demonstrated effectively in many different obstacle avoidance systems. Free spaces through which a MAV can fly are estimated by TTC. BS is used to guide a MAV flying in a collision free path. Our approach is implemented in the framework of Robot Operating System (ROS). The simulation demonstrates the effectiveness of the approach.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Tools with Artificial Intelligence, ICTAI 2017
PublisherIEEE Computer Society
Pages574-578
Number of pages5
ISBN (Electronic)9781538638767
DOIs
StatePublished - 2 Jul 2017
Event29th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2017 - Boston, United States
Duration: 6 Nov 20178 Nov 2017

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2017-November
ISSN (Print)1082-3409

Conference

Conference29th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2017
Country/TerritoryUnited States
CityBoston
Period6/11/178/11/17

Keywords

  • Balance strategy
  • MAVs
  • Obstacle avoidance
  • Optical flow
  • Time to Contact

Fingerprint

Dive into the research topics of 'Optical flow based obstacle avoidance for multi-rotor aerial vehicles'. Together they form a unique fingerprint.

Cite this