| dc.description.abstract | The application of Genetic Algorithm (GA) in addressing the challenges of last-mile
delivery scenarios in drone logistics is gaining attention due to its potential for optimizing
route planning and resource allocation. This thesis explores the use of GA for solving drone
delivery problems in last-mile scenarios, focusing on enhancing the algorithm to improve
delivery efficiency and cost-effectiveness. By incorporating specialized genetic operators
tailored for drone routing and scheduling, this study aims to develop a novel approach to
address the complexities of last-mile logistics using GA. The algorithm begins by
initializing a population of potential drone delivery routes, with each route represented as
a chromosome encoding the sequence of delivery locations. Through selection based on
factors such as distance, delivery time, promising routes are chosen for crossover, where
genetic information is exchanged to generate offspring routes. Mutation introduces random
variations to explore new solutions and maintain genetic diversity within the population.
Fitness evaluation assesses the performance of each route based on criteria such as delivery
time, cost, and energy consumption. The least fit routes are replaced by superior solutions,
driving the population towards optimal drone delivery routes. By iteratively evolving and
improving route plans over successive generations, GA offers a systematic approach to
addressing the complexities of last-mile drone logistics and enhancing delivery efficiency
in real-world scenarios. | en_US |
