Vision-based Guidance and Navigation for Autonomous MAV in Indoor Environment

Mahammad Irfan, Sagar Dalai, Kaushal Kishore, Samarth Singh, S. A. Akbar

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

Abstract

The paper presents an autonomous vision-based guidance and mapping algorithm for navigation of drones in a GPS-denied environment. We propose a novel algorithm that accurately uses OpenCV ArUco markers as a reference for path detection and guidance using a stereo camera. It enables the drone to navigate and map an environment using vision-based path planning. Special attention has been given towards the robustness of guidance and controlling strategy, accuracy in the vehicle pose estimation and real-time operation. The proposed algorithm is evaluated in a 3D simulated environment using ROS and Gazebo. The results have been presented for drone navigation in a maze pattern indoor scenario. Evaluation of the given guidance system in the simulated environment suggests that the proposed system can be used for generating a 2D/3D occupancy grid map autonomously without the use of high-level algorithms and expensive sensors such as lidars.

Original languageEnglish
Title of host publication2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728168517
DOIs
Publication statusPublished - Jul 2020
Externally publishedYes
Event11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020 - Kharagpur, India
Duration: 1 Jul 20203 Jul 2020

Publication series

Name2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

Conference

Conference11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020
Country/TerritoryIndia
CityKharagpur
Period1/07/203/07/20

Keywords

  • Gazebo
  • Pose estimation
  • Quadcopter
  • ROS
  • SLAM
  • Vision Guidance

Fingerprint

Dive into the research topics of 'Vision-based Guidance and Navigation for Autonomous MAV in Indoor Environment'. Together they form a unique fingerprint.

Cite this