Date of Award

9-20-2024

Publication Type

Thesis

Degree Name

M.A.Sc.

Department

Electrical and Computer Engineering

Supervisor

Ning Zhang

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Unmanned Aerial Vehicles (UAVs) have emerged as a pivotal technology within Internet of Things (IoT) networks, addressing the limitations of traditional IoT devices, such as delayed information updates and high labor costs. The flexibility of UAVs makes them particularly well-suited for data collection tasks. However, the energy constraints of both UAVs and sensors within IoT networks necessitate the discovery of energy-efficient routes to ensure the operational longevity of the UAVs and the entire network. In this thesis, we propose an advanced UAV path planning framework that leverages the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize UAV flight paths in complex environments, thereby minimizing energy consumption. Our final simulations reveal that the UAV demonstrates exceptional performance in consistently identifying the optimal path after training. In the end, by comparing our trained model with both random, greedy baseline and APF methods, our approach achieved outstanding and near-optimal results within the constructed simulation scenarios.

Share

COinS