ARTICLE

Volume 3,Issue 9

Cite this article
1
Download
15
Citations
111
Views
28 May 2026

基于TD3算法的无人驾驶消防车匝道汇入模型

泽宇 陈1
Show Less
1 中国消防救援学院, 中国
TACS 2026 , 3(10), 1–5; https://doi.org/10.61369/tacs.2026
© 2026 by the authors. Licensee Art and Technology, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

在匝道汇入时,无人驾驶消防车应能清晰感知周围交通状况,以确保车辆适应不同交通场景,并做出相应决策,避免碰撞、优化路径。为解决现有基础无人驾驶消防车匝道汇入模型(以下简称基础模型)中深度强化学习算法存在的收敛速度慢,汇入成功率较低等问题,提出建立将TD3(Twin Delayed Deep Deterministic Policy Gradient) 算法与长短期记忆网络相结合的新型智能车匝道汇入(LSTM-TD3)模型,用长短期记忆网络分别替换Actor 网络的输入层和Critic 网络的输入层,以有效预测输出结果。试验结果表明,LSTM-TD3模型比基础模型收敛速度和汇入成功率更高,同时能够帮助无人驾驶消防车做出最佳汇入决策。

Keywords
无人驾驶;消防车;匝道汇入;深度强化学习;长短期记忆网络
References

[1] 刘传贺. 关于增强汽车驾驶员安全驾驶意识的探讨[J]. 时代汽车,2021(12):197-198.
[2] 乔良, 鲍泓, 玄祖兴, 等. 基于强化学习的无人驾驶匝道汇入模型[J]. 计算机工程,2018,44(07):20-24+31.
[3] 鲍实, 方勇. 基于深度增强学习的无人车汇流决策方法[J]. 电子测量技术,2018,41(19):44-49.
[4]Wang H , Yuan S , Guo M , et al. A deep reinforcement learning-based approach for autonomous driving in highway on-ramp merge[J]. Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering, 2021,235(6):095440702199948.
[5]Mnih V, Kavukcuoglu K, Silver D, et al. Playing atari with deep reinforcement learning[J]. arXiv preprint arXiv:1312.5602, 2013.
[6]Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning[J]. arXiv preprint arXiv:1509.02971, 2015.
[7] 吴思凡,杜煜,徐世杰,等. 基于深度确定性策略梯度的智能车汇流模型[J]. 计算机工程,2020,46(01):87-92.
[8]Lin Y, McPhee J, Azad N L. Anti-jerk on-ramp merging using deep reinforcement learning[C]//2020 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2020: 7-14.
[9]Chen Y, Dong C, Palanisamy P, et al. Attention-based hierarchical deep reinforcement learning for lane change behaviors in autonomous driving[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019: 0-0.
[10]Zhang M, Zhang Y, Gao Z, et al. An improved DDPG and its application based onthe double-layer BP neural network[J]. IEEE Access, 2020, 8: 177734-177744.
[11]Alighanbari S, Azad N L. Deep Reinforcement Learning with NMPC Assistance Nash Switching for Urban Autonomous Driving[J]. IEEE Transactions on Intelligent Vehicles, doi: 10.1109/TIV.2022.3167616.
[12]Fujimoto S, Hoof H, Meger D. Addressing function approximation error in actorcritic methods[C]//International conference on machine learning. PMLR, 2018:1587-1596.
[13]Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation,1997, 9(8): 1735-1780.

Share
Back to top