Speaker
Description
Line Follower Algorithm for a Flying Quadcopter
Mikołaj Stasiak, Wiktor Ważny, Grzegorz Zając
Institute for Automation and Robotics, Faculty of Mechatronics, Warsaw University of Technology.
As interest in aerial drones and autonomous systems grows, so does the need for optimal solutions that can be run on minimalistic hardware. This paper describes an autonomous, vision-based algorithm designed for participation in the MathWorks Minidrone Competition. The algorithm was developed within competition’s specification [1] and the authors won the 3rd place in the nationwide MathWorks Minidrone Competition Poland 2025 [2]. The work done included research on publicly available, already existing solutions [3] as well as on tools that could be applied to the task at hand [4], [5]. As a result a custom vision algorithm was developed to balance fidelity and speed and to minimise the computing power required. The drone software, written entirely in Matlab is capable of controlling a Parrot Mambo mini drone tasked with traversing a course made of red straight lines joined at different angles. The programme is designed around a built-in low-resolution camera pointing downwards. The work focuses on the design and development of an image processing algorithm as well as path planner and flight control programs that transform a low resolution image into a list of instructions for the drone.
Full version with pictures can be found attached below.
References
[1] Contest rules: https://www.mathworks.com/content/dam/mathworks/mathworks-
dot-com/academia/student-competitions/minidrone-
competition/mathworks-minidrone-competition-guidelines.pdf
[2] Contest results: https://ont.com.pl/wydarzenia/minidrone-poland-25
[3] Projects reviewed: https://github.com/Rutwik1000/Parrot-Minidrone-
Compettion/tree/f176186176548ac9ab66335d6225048e436e043c; https://github.com/mar4945/Vision-Based-Pure-Pursuing-
Algorithm
[4] Min-max algorithm: https://arxiv.org/abs/2011.14035
[5] Imfindcircles function: https://www.mathworks.com/help/images/ref/imfindcircles.html
