Article: Orientation and trajectory-specific movement assistance for quadcopter control using machine vision input Journal: International Journal of Sensor Networks (IJSNET) 2024 Vol.45 No.3 pp.177 - 190 Abstract: In recent years, quadcopter services have emerged under testing and trials for consumer and commercial applications. The trajectory and movement of the quadcopters will be aligned due to the external impact of building heights, winds, and other obstacles. Machine vision-based trajectory and movement alignment are pursued using orientation deflection detection. An orientation-specific trajectory assisted movement (OTAM) method is introduced in this article to address this issue. This method accounts for the obstacle's physical dimensions and the quadcopter trajectory for inducing the moving pathway. The pathway differences between the dimensions and trajectory are recurrently computed using neural learning. This computation calculates the trajectory and orientation using the quadcopter's vision (image) in its moving path. The recurrent learning process trains the process for safe movement without hitting/being obstructed by any obstacles. Based on the learning ability, the recommendations are provided for smooth movement and direction control of the quadcopter. The minor differences between the quadcopter's vision and the obstacle are classified for the next successful movement from the previous recurrences. Therefore, this proposed movement control method improves the accuracy under reduced error rates. Inderscience Publishers - linking academia, business and industry through research

Title: Orientation and trajectory-specific movement assistance for quadcopter control using machine vision input

Authors: Yan Ru; Xin Zhang

Addresses: School of Intelligent Manufacturing, Liuzhou Railway Vocational Technical College, Liuzhou Guangxi 545616, China ' School of Urban Rail Transit, Liuzhou Railway Vocational Technical College, Liuzhou Guangxi 545000, China

Abstract: In recent years, quadcopter services have emerged under testing and trials for consumer and commercial applications. The trajectory and movement of the quadcopters will be aligned due to the external impact of building heights, winds, and other obstacles. Machine vision-based trajectory and movement alignment are pursued using orientation deflection detection. An orientation-specific trajectory assisted movement (OTAM) method is introduced in this article to address this issue. This method accounts for the obstacle's physical dimensions and the quadcopter trajectory for inducing the moving pathway. The pathway differences between the dimensions and trajectory are recurrently computed using neural learning. This computation calculates the trajectory and orientation using the quadcopter's vision (image) in its moving path. The recurrent learning process trains the process for safe movement without hitting/being obstructed by any obstacles. Based on the learning ability, the recommendations are provided for smooth movement and direction control of the quadcopter. The minor differences between the quadcopter's vision and the obstacle are classified for the next successful movement from the previous recurrences. Therefore, this proposed movement control method improves the accuracy under reduced error rates.

Keywords: machine vision; neural network; pathway control; quadcopter orientation.

DOI: 10.1504/IJSNET.2024.139852

International Journal of Sensor Networks, 2024 Vol.45 No.3, pp.177 - 190

Received: 23 Jan 2024
Accepted: 29 Jan 2024
Published online: 08 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Orientation and trajectory-specific movement assistance for quadcopter control using machine vision input

Keep up-to-date