A Combination Model for Connected and Autonomous Vehicles Lane-changing Decision-making Under Multi Connectivity Range

被引：0
|
作者：
Zhao J.-D. [1 ,2 ]
He X.-Y. [1 ]
Yu Z.-X. [1 ]
Han M.-M. [3 ]
机构：
[1] School of Traffic and Transportation, Beijing Jiaotong University, Beijing
[2] Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Beijing Jiaotong University, Beijing
[3] Hebei Provincial Communications Planning, Design and Research Institute Co. Ltd., Shijiazhuang
来源：
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2023年 / 23卷 / 01期
基金：
中国国家自然科学基金;
关键词：
connectivity range; deep reinforcement learning; intelligent connected vehicles; intelligent transportation; lane change decision; molecular dynamics;
D O I：
10.16097/j.cnki.1009-6744.2023.01.009
中图分类号：
学科分类号：
摘要：
In order to improve the lane-changing efficiency of intelligent connected vehicles (ICV) under different network connection ranges, combined with deep reinforcement learning and molecular dynamics theory, a double deep Q network lane-changing decision model integrating the masking mechanism and attention mechanism (MAQ) is proposed. Firstly, in the Simulation of Urban Mobility (SUMO) simulation environment, the driving status information of connected vehicles and human drive vehicles (HDV) within the network range is collected. Secondly, the MAQ model is built, the mask mechanism and attention mechanism are adopted to achieve fixed model input size and displacement invariance. Thirdly, in order to quantify the degree of influence between vehicles, the relative speed and the relative position between vehicles are used as parameters, and the molecular dynamics theory is used to give weights to HDV information within the connectivity range. Finally, different lane-changing decision models and weighting methods are compared in different traffic density simulation environments. The effect of lane change decision is tested under different connectivity ranges (80~330 meters, with an interval of 50 meters). The simulation results show that, taking 40 HDVs and a 100-meter connectivity range as an example, the MAQ model has a 90.2% improvement in fitting accuracy compared with the DeepSet-Q model; compared with the linear weighting method, the molecular dynamics weighting method increases the total reward value by 5.5%, and the average speed of ICV by 4.4%; with the expansion of the connectivity range, the average speed of ICV shows a change rule of first increasing, then decreasing, and then tending to be stable. © 2023 Science Press. All rights reserved.
引用
收藏
页码：77 / 85
页数：8
相关论文
共 18 条
  • [11] WANG C, FU R, ZHANG Q, Et al., Research on parameter TTC characteristics of lane change warning system, China Journal of Highway and Transport, 28, 8, pp. 91-100, (2015)
  • [12] HASSELT H, GUEZ A, SILVER D., Deep reinforcement learning with double Q-learning, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, (2016)
  • [13] BAHDANAU D, CHO K, BENGIO Y., Neural machine translation by jointly learning to align and translate, (2014)
  • [14] SHI R., The construction of risk field and optimization of driving behaviors for signalized intersections, (2021)
  • [15] KRAJZEWICZ D, ERDMANN J, BEHRISCH M, Et al., Recent development and applications of SUMO-simulation of urban mobility, International Journal on Advances in Systems and Measurements, 5, 3, pp. 128-138, (2012)
  • [16] TREIBER M, KESTING A., Traffic flow dynamics, Traffic Flow Dynamics: Data, Models and Simulation, pp. 983-1000, (2013)
  • [17] ERDMANN J., SUMO's lane-changing model, Modeling Mobility with Open Data, pp. 105-123, (2015)
  • [18] MNIH V, KAVUKCUOGLU K, SILVER D, Et al., Human-level control through deep reinforcement learning, Nature, 518, 7540, pp. 529-533, (2015)
12