<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">TACS</journal-id><journal-title-group><journal-title>Technology and Application of Computer Science</journal-title></journal-title-group><issn>2998-8926</issn><eissn>2998-8934</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/tacs.2026</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>基于TD3算法的无人驾驶消防车匝道汇入模型</title><url>https://artdesignp.com/journal/TACS/3/10/10.61369/tacs.2026</url><author>陈泽宇</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>3</volume><issue>10</issue><history><date date-type="pub"><published-time>2026-05-28</published-time></date></history><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。</abstract><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</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[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.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
