Variable guidance lanes are designed to alleviate traffic congestion by adjusting the functional configurations of intersection entrance lanes. Existing variable guidance lanes predominantly operate on fixed-time schedules,which fail to fully utilize their adaptive potential. An intelligent control method integrating Kolmogorov-Arnold networks(KAN),convolutional neural networks(CNN),and long short-term memory(LSTM) networks was proposed to predict short-term traffic flow and temporal occupancy rates for straight-through and left-turn movements. Traffic data predictions were processed using a firefly algorithm-optimized fuzzy C-means(FCM) clustering algorithm,categorizing traffic states into three modes: “straight-through”“combined straight-left” and “left-turn”. A constrained switching framework was developed to dynamically adjust lane functions based on real-time traffic conditions. A microscopic traffic simulation was implemented in VISSIM to evaluate operational performance under different lane configurations. Results demonstrate that the proposed system reduces average travel time by 5.33%,queue length by 3.52%,and traffic delay by 11.79% in variable guidance lane approaches. The intelligent control method effectively enhances intersection operational efficiency while maintaining compliance with traffic regulations. This approach provides a data-driven solution for adaptive traffic management in urban road networks.
YANG Yan, TANG Qiu-sheng.
Intelligent Control Method of Variable Direction Lane Based on Traffic State Prediction[J].
Science Technology and Engineering, 2026, 26(4): 1710-1719 DOI:10.12404/j.issn.1671-1815.2501668
式中:φx为外层非线性函数中的第x个函数;ωb、ωs为系数,用于控制激活函数(即基函数与样条函数之和)的整体大小,对函数的缩放起到调节作用;b(x)为基函数,在式(2)中具体采用的是SiLU(Sigmoid linear unit)函数,用于提供基本的非线性变换;SiLU(x)是一种特殊的激活函数,是Sigmoid函数的一种变体,具有平滑的非线性特性;ci为样条函数的可训练系数,这些系数是可训练的参数,在网络训练过程中通过学习进行调整,以优化样条函数的拟合效果;Bi(x)为第i个基函数,是样条函数的基本组成部分,通过不同基函数的线性组合构成样条函数。
SunXu, LaiYuhao, QieKun. Research on adaptive variable guidance lane capacity enhancement based on explainable machine learning[J]. Traffic Engineering, 2025, 25(2): 16-22, 33.
WangJiawen, FengYang, ZhaoJing, et al. Collaborative optimization method and empi-rical research on lane function and signal control[J]. Highway Traffic Science andTe-chnology, 2023, 40(3): 219-227.
ZhuCongkun, ZhangLefeng. Credit control variable lane to adapt to the traffic intersection reverse left study[J]. Journal of Transportation Engineering, 2021, 21(2): 79-84.
ZhangWenqi, XuFagang, ZhaoBinxu. Applied to adaptive mobile fence tidal lane control system design[J]. Journal of Electronic Design Engineering, 2023, 31(16): 96-101.
BaiJia’an, ZhangCunbao, CaoYu. Research on dynamic position adjustment and signal timing optimization of reverse variable lane openings[J]. Journal of Wuhan University of Technology(Traffic Science and Engineering), 2023, 47(5): 781-787.
LiXuemei, ZhangCunbao, CaoYu, et al. A collaborative optimization method of lane function and signal control at intersections with variable guidance lanes[J]. Traffic Information and Safety, 2023, 41(5): 54-63.
KongXiangfen, LiuJingyun, WangJie, et al. Research on variable guidance lane setting strategy based on evolutionary game Theory[J]. Industrial Engineering, 2023, 26(1): 115-122.
ZhaoChen, FangTian. Variable lane intersection synthetic dynamic control and signal timing optimization study[J]. Transportation and ports, 2024, 11(4): 76-81, 91.
ShiJiying, WangJiawen, ZhengXin, et al. Optimization method of time division scheme for variable entrance lanes at signal controlled intersections of urban roads[J] Water Transport in China, 2023(7): 148-150.
WangLianzhen, WangYuping, YaoLi. A collaborative optimization method of spatial-temporal resources at intersections based on variable guidance lane[J]. Journal of Wuhan University of Technology(Traffic Science and Engineering), 2021, 45(6): 1005-1009.
XuXiaogao, XiaYingjie, ZhuSiyu, et al. Multi-intersection variable lane cooperative control method based on reinforcement learning[J]. Journal of Zhejiang University(Engineering and Technology), 2022, 56(5): 987-994, 1005.
[25]
AlagbéJ A, WangR, XuC, et al. Empirical analysis of traffic flow characteristics at variable approach lanes[J]. International Journal of Transportation Science and Technology, 2024, 14: 87-98
[26]
ZhouG, MaoL, BaoT, et al. Construction of real-time dynamic reversible lane safety control model in intelligent vehicle infrastructure cooperative system[J] Applied Artificial Intelligence, 2023, 37(1): 2177009.
[27]
SunZ, WangZ, QiX, et al. A two-stage robust optimal traffic signal control with reversible lane for isolated intersections[J]. IET Intelligent Transport Systems, 2023, 18(4): 723-742.
[28]
DanteP, CarlosG, ElenaM L, et al. Modeling adaptive reversible lanes: a cellular automata approach[J]. PLoS One, 2021, 16(1): 0244326.
[29]
NingB, LiangS, ZuoS, et al. Dynamic straight-right lane design and signal control at urban intersections[J]. Journal of Transportation Engineering, Part A: Systems, 2023, 149(10): 7581.
[30]
HongW Q, YangZ S, SunX, et al. Temporary reversible lane design based on bi-level programming model during the Winter Olympic Games[J]. Sustainability, 2022, 14(8): 4780-4780.
ZhangShengrui, LianJiangnan, JiaoShuaiyang, et al. Short-time traffic congestion state prediction model with FCM-RBF[J]. Journal of Chongqing University of Technology(Natural Science), 2023, 37(3): 12-21.