Affiliation:
1. Department of Communications, Navigation and Control Engineering, National Taiwan Ocean University, Keelung 20224, Taiwan
Abstract
This study proposes using unmanned aerial vehicles (UAVs) to carry out tasks involving path planning and obstacle avoidance, and to explore how to improve work efficiency and ensure the flight safety of drones. One of the applications under consideration is aquaculture cage detection; the net-cages used in sea-farming are usually numerous and are scattered widely over the sea. It is necessary to save energy consumption so that the drones can complete all cage detections and return to their base on land. In recent years, the application of reinforcement learning has become more and more extensive. In this study, the proposed method is mainly based on the Q-learning algorithm to enable improvements to path planning, and we compare it with a well-known reinforcement learning state–action–reward–state–action (SARSA) algorithm. For the obstacle avoidance control procedure, the same reinforcement learning method is used for training in the AirSim virtual environment; the parameters are changed, and the training results are compared.
Funder
Ministry of Science and Technology
Subject
Control and Optimization,Control and Systems Engineering
Reference37 articles.
1. A formal basis for the heuristic determination of minimum cost paths;Hart;IEEE Trans. Syst. Sci. Cybern.,1968
2. Optimal and efficient path planning for unknown and dynamic environments;Stentz;Int. J. Robot. Autom. Syst.,1995
3. Randomized kinodynamic planning;LaValle;Int. J. Robot. Res.,2001
4. Sen, Y., and Zhongsheng, W. (2017, January 23–26). Quad-Rotor UAV Control Method Based on PID Control Law. Proceedings of the 2017 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xi’an, China.
5. Kamel, B., Yasmina, B., Laredj, B., Benaoumeur, I., and Zoubir, A. (2017, January 12–13). Dynamic Modeling, Simulation and PID Controller of Unmanned Aerial Vehicle UAV. Proceedings of the 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Porto, Portugal.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献