Optimizing UAV Routes: An Implementation and Evaluation of Ant-Colony Optimization Algorithm on Crazyflie Quadcopter for Solving the Traveling Salesman Problem

This title has been presented on Thursday, December 14, 2023 at 13.20-13.30 GMT+7.

Abstract

This title will be presented on Thursday, December 14, 2023 at 13.10 - 13.20 GMT+7.

The Traveling Salesman Problem (TSP) is an optimization problem aimed at finding the best possible route. An illustrative instance of TSP in agricultural problem arises when a UAV needs to visit several locations (nodes) to perform specific tasks, such as surveillance or fertilization. One of the algorithms employed for solving TSP is Ant-Colony Optimization (ACO). The ACO algorithm operates by utilizing the “ants” as the virtual agents exploring the potential routes and storing the information in memory to determine the optimal route. This research aims to address the TSP problem using the ACO algorithm and subsequently apply it to the Crazyflie quadcopter. The developed ACO algorithm is designed to identify the most efficient route, guiding the UAV along the obtained path. Test results demonstrate the successful navigation of the Crazyflie quadcopter to the specified coordinates, with an average position error of 0.02 meters on the x-axis, 0.02 meters on the y-axis, and 0.01 meters on the z-axis.