<![CDATA[Transportation plays a critical role in modern society, with air travel being a key component of long-distance mobility. Despite strict regulations by the Federal Aviation Administration (FAA) and mandatory periodic inspections, aircraft maintenance issues often arise due to human error. Factors such as fatigue and the challenges of working in hard-to-reach areas contribute to these errors. Automated Ground Vehicles (AGVs) equipped with automated inspection systems offer a promising solution by reducing reliance on human performance, enabling inspections that are more accurate, efficient, and automated. However, optimizing inspection routes to minimize travel distance remains a challenging issue. This study aims to optimize the inspection distance for AGVs inspecting the underside of a Boeing 757-200 aircraft using MATLAB R2023a simulation tools. The input data for the simulation consists of the x, y, and z coordinates of various inspection points on the aircraft, and the output is the total distance travelled by the AGV during inspection. The objective is to minimize the travel distance, calculated as a vector from one point to the next. Two optimization methods to be compared include Simulated Annealing (SA) and Genetic Algorithm (GA). The SA method involves varying parameters such as the number of iterations, initial temperature, and cooling rate. Meanwhile, the GA method varies the number of iterations, population size, and crossover and mutation percentages. The study evaluates the performance of both methods using a dataset of 34 inspection points. The results show that Simulated Annealing produces the most optimal path-planning distance, achieving a minimum of 85.099 meters across all parameter variations. This optimized solution contributes to more efficient and reliable aircraft maintenance processes, reducing human error and enhancing air travel safety and reliability.]]>
