基于深度强化学习的路径规划研究
Research on Path Planning Based on Deep Reinforcement Learning
DOI: 10.12677/aam.2025.144187, PDF,   
作者: 周泰霖：浙江师范大学数学科学学院，浙江 金华
关键词: 路径规划；深度强化学习；奖励函数；Path Planning； Deep Reinforcement Learning； Reward Function
摘要: 随着自动化和智能系统的发展，高效的路径规划已成为机器人、自动驾驶汽车、无人机导航等领域的关键技术之一。本文主要研究基于深度强化学习的路径规划算法，我们设计了一系列奖励函数提高智能体路径规划能力，最后通过仿真实验验证算法有效性。
Abstract: With the development of automation and intelligent systems, efficient path planning has become one of the key technologies in the fields of robotics, autonomous vehicles, and drone navigation. In this paper, we study the path planning problem based on deep reinforcement learning. We design a series of reward functions to improve the agent’s path planning ability, and verify the effectiveness of the algorithm through simulation experiments.
文章引用：周泰霖. 基于深度强化学习的路径规划研究[J]. 应用数学进展, 2025, 14(4): 572-578. https://doi.org/10.12677/aam.2025.144187

参考文献

[1] Bai, X., Jiang, H., Cui, J., Lu, K., Chen, P. and Zhang, M. (2021) UAV Path Planning Based on Improved A∗ and DWA Algorithms. International Journal of Aerospace Engineering, 2021, Article 4511252. [Google Scholar] [CrossRef] 
[2] 宋佳. 基于Dijkstra算法的AGV绿色节能路径规划研究[D]: [硕士学位论文]. 南昌: 南昌大学, 2022.
[3] 向金林, 王鸿东, 欧阳子路, 等. 基于改进双向RRT的无人艇局部路径规划算法研究[J]. 中国造船, 2020, 61(1): 157-166.
[4] Ballesteros, J., Urdiales, C., Velasco, A.B.M. and Ramos-Jimenez, G. (2017) A Biomimetical Dynamic Window Approach to Navigation for Collaborative Control. IEEE Transactions on Human-Machine Systems, 47, 1123-1133. [Google Scholar] [CrossRef] 
[5] 黄岩松, 姚锡凡, 景轩, 等. 基于深度Q网络的多起点多终点AGV路径规划[J]. 计算机集成制造系统, 2023, 29(8): 2550-2562.
[6] Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., et al. (2015) Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529-533. [Google Scholar] [CrossRef] [PubMed]
[7] Van Hasselt, H., Guez, A. and Silver, D. (2016) Deep Reinforcement Learning with Double Q-Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 30, 2094-2100. [Google Scholar] [CrossRef] 
[8] Kato, Y. and Morioka, K. (2019) Autonomous Robot Navigation System without Grid Maps Based on Double Deep Q-Network and RTK-GNSS Localization in Outdoor Environments. 2019 IEEE/SICE International Symposium on System Integration (SII), Paris, 14-16 January 2019, 346-351. [Google Scholar] [CrossRef] 
[9] Han, S., Choi, H., Benz, P. and Loaiciga, J. (2018) Sensor-Based Mobile Robot Navigation via Deep Reinforcement Learning. 2018 IEEE International Conference on Big Data and Smart Computing (BigComp), Shanghai, 15-17 January 2018, 147-154. [Google Scholar] [CrossRef] 
[10] Li, J., Ran, M., Wang, H. and Xie, L. (2021) A Behavior-Based Mobile Robot Navigation Method with Deep Reinforcement Learning. Unmanned Systems, 9, 201-209. [Google Scholar] [CrossRef] 
[11] Sampedro, C., Bavle, H., Rodriguez-Ramos, A., de la Puente, P. and Campoy, P. (2018) Laser-Based Reactive Navigation for Multirotor Aerial Robots Using Deep Reinforcement Learning. 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, 1-5 October 2018, 1024-1031. [Google Scholar] [CrossRef] 
[12] Leiva, F. and Ruiz-del-Solar, J. (2020) Robust RL-Based Map-Less Local Planning: Using 2D Point Clouds as Observations. IEEE Robotics and Automation Letters, 5, 5787-5794. [Google Scholar] [CrossRef] 

为你推荐