Vision-based Guidance and Navigation for Autonomous MAV in Indoor Environment
IR@CEERI: CSIR-Central Electronics Engineering Research Institute, Pilani
View Archive InfoField | Value | |
Title |
Vision-based Guidance and Navigation for Autonomous MAV in Indoor Environment
|
|
Creator |
Irfan, M
Dalai, S Kishore, K Singh, S Akbar, SA |
|
Subject |
Digital Systems
|
|
Description |
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.
|
|
Date |
2020
|
|
Type |
Conference or Workshop Item
PeerReviewed |
|
Format |
application/pdf
|
|
Identifier |
http://ceeri.csircentral.net/554/1/032020.pdf
Irfan, M and Dalai, S and Kishore, K and Singh, S and Akbar, SA (2020) Vision-based Guidance and Navigation for Autonomous MAV in Indoor Environment. In: 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT-2020), July 1-3, 2020, IIT Kharagpur, India. |
|
Relation |
http://ceeri.csircentral.net/554/
|
|