To enhance the operational efficiency of urban expressway diversion areas,a decision-making method for connected and automated vehicles (CAVs) was proposed for expressway diversion areas with dedicated CAV lanes. The Deep Q-Network (DQN) algorithm was improved by focusing on the spatial states of multiple future moments and taking the operation speed and stability of CAVs into consideration. A multi-objective reward function applicable to expressway diversion areas equipped with dedicated CAV lanes was designed, and a CAV car-following and lane-changing decision-making method was established for such expressway diversion areas with dedicated connected and automated driving lanes. A simulation platform for heterogeneous traffic flow in expressway diversion areas was developed based on Python for the simulation and comparative verification of the CAV decision-making method. Simulation results show that the proposed decision-making method can effectively reduce the lane-changing times of CAVs in urban expressway diversion areas, increase the operation speed of CAVs, and improve the operation efficiency of heterogeneous traffic flow in expressway diversion areas. Theoretical references can be provided for the research and development of intelligent driving software, and a decision-making basis can be offered for the layout of dedicated CAV lanes on urban expressways.
MohajerpoorR, RamezaniM. Mixed flow of autonomous and human-driven vehicles: analytical headway modeling and optimal lane management[J]. Transportation Research Part C: Emerging Technologies, 2020, 109: 194-210.
[2]
YaoZ H, WuY X, WangY, et al. Analysis of the impact of maximum platoon size of CAVs on mixed traffic flow: an analytical and simulation method[J]. Transportation Research Part C: Emerging Technologies, 2023,147: No.103989.
[3]
SunZ B, HuangT Y, ZhangP T. Cooperative decision-making for mixed traffic: A ramp merging example[J]. Transportation Research Part C: Emerging Technologies, 2020,120: No.102764.
[4]
CuiS H, CaoF, YuB, et al. Modeling heterogeneous traffic mixing regular, connected, and connected-autonomous vehicles under connected environment[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 8579-8594.
[5]
ZhengF F, LiuC, LiuX B, et al. Analyzing the impact of automated vehicles on uncertainty and stability of the mixed traffic flow[J]. Transportation Research Part C: Emerging Technologies, 2020,112: 203-219.
[6]
YangH, WeiZ Q, FengZ Y, et al. Intelligent computation offloading for MEC-based cooperative vehicle[J]. IEEE Transactions on Intelligent Transportation Systems, 2022,71(7): 7665-7679.
[7]
LiG F, QiuY F, YangY F . et al. Lane change strategies for autonomous vehicles: a deep reinforcement learning approach based on transformer[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(3): 2197-2211.
[8]
GaoZ B, WuZ Z, HaoW, et al. Optimal trajectory planning of connected and automated vehicles at on-ramp merging area[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(8):12675- 12687.
[9]
PengJ L, WeiS G, ChaiL G.Strategy of lane-changing coupling process for connected and automated vehicles in mixed traffic environment[J].Transportmetrica B: Transport Dynamics, 2023, 11(1): 979-995.
[10]
WangB W, GongX L, LyuP Y, et al. Iterative learning-based cooperative motion planning and decision-making for connected and autonomous vehicles coordination at on-ramps[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(7):8105-8120.
JiXiao-feng, XuYing-hao, HaoJing-jing, et al. Time covariate modeling of overtaking behavior risk evolution on two-lane highway[J].Journal of Southwest Jiaotong University, 2025, 60(5): 1240-1249.
[13]
FanJ Y, LiangJ, TulaA K. A lane changing time point and path tracking framework for autonomous ground vehicle[J]. IET Intelligent Transport Systems, 2022, 16(7): 860-874.
[14]
AraghiS, KhosraviA, Abbas, et al. A review on computational intelligence methods for controlling traffic signal timing[J]. Expert Systems with Applications, 2015, 42(3): 1538-1550.
[15]
HidasP. Modelling lane changing and merging in microscopic traffic simulation[J]. Transportation Research Part C: Emerging Technologies, 2002,10(5):351-371.
LiRui, RanBin, QuXu. Traffic capacity enhancement strategy for urban expressway diversion area under vehicle-infrastructure cooperative environment[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 126-138.
[18]
CuiS H, CaoF, YuB, et al. Modeling heterogeneous traffic mixing regular, connected, and connected-autonomous vehicles under connected environment[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(7): 8579-8594.
[19]
ZhengF F, LiuC, LiuX B, et al. Analyzing the impact of automated vehicles on uncertainty and stability of the mixed traffic flow[J]. Transportation Research Part C: Emerging Technologies, 2020, 112: 203-219.
HaoWei, ZhangZhao-lei, Neng-chaoLyu, et al. Mixed traffic assignment model based on autonomous driving lanes[J]. China Journal of Highway and Transport, 2023, 36(10): 317-327.
[22]
LinX, WangM, AremB V. Traffic flow impacts of converting an HOV lane into a dedicated CACC lane on a freeway corridor[J]. IEEE Intelligent Transportation Systems Magazine, 2020, 12(1): 60-73.
[23]
VicenteM, ShladoverS E. Modeling cooperative and autonomous adaptive cruise control dynamic responses using experimental data[J]. Transportation Research Part C: Emerging Technologies, 2014,48:285-300.
[24]
ShladoverS, SuD, LuX Y. Impacts of cooperative adaptive cruise control on freeway traffic flow[J]. Transportation Research Record, 2012, 2324: 63-70.