基于交通时空特征的车辆全局路径规划算法

doi:10.3969/j.issn.1674-8484.2021.01.005

摘要/Abstract

摘要：

为降低混合动力汽车（HEV）的出行时间和出行能耗,提出了一种基于时空动态交通信息的路径规划算法。分析了影响车辆通行时间和全程最低能耗的因素。一种基于广义回归网络（GRNN）模型,拟合计算了道路通行时间以及整体路径的全程能耗。构建了基于并行A*算法的车辆路径规划算法,为确定起终点位置后的车辆,规划了一条耗时更短、更加节能的路径。进行了仿真对比试验。结果表明：相比于依据平均车速与道路功率的计算方法,该算法能够获得更优的出行路径,可降低车辆能耗11%以上,缩短行车时间13%以上。因而,该算法可为车辆规划更优的路径。

关键词: 混合动力汽车(HEV), 城市交通, 路径规划, 时空搜索

Abstract:

A path planning algorithm based on spatiotemporal dynamic traffic information was proposed to reduce the travel time and energy consumption of hybrid electric vehicles (HEV). The factors that affect the vehicle travel time and the minimum energy consumption in the whole path were analyzed. The travel time and the path energy consumption are calculated based on the generalized regression network (GRNN) model. A vehicle path planning algorithm based on parallel A * algorithm was constructed to plan a shorter time-consuming or more energy-saving path for vehicles after determining the starting and ending positions. The virtual simulation test was implemented. The results show that the proposed algorithm can obtain a better travel path and reduce vehicle energy consumption by more than 11% or driving time by more than 13% compared with the calculation methods through average speed or power parameters. Therefore, the proposed algorithm can plan a better route for vehicles.

Key words: hybrid electric vehicle (HEV), urban traffic, path planning, space-time searching

中图分类号:

U469.7

杜茂, 杨林, 金悦, 涂家毓. 基于交通时空特征的车辆全局路径规划算法[J]. 汽车安全与节能学报, 2021, 12(1): 52-61.

DU Mao, YANG Lin, JIN Yue, TU Jiayu. Vehicle global path planning algorithm based on spatio-temporal characteristics of traffic[J]. Journal of Automotive Safety and Energy, 2021, 12(1): 52-61.

图/表 16

参考文献 21

[1]	李阳. 需求不确定的车辆路径问题模型与算法研究[D]. 大连:大连海事大学, 2018.
	LI Yang. Optimization models and algorithms of vehicle routing problem under uncertain demands[D]. Dalian: Dalian Maritime University, 2018. (in Chinese)
[2]	SONG Meixian, LI Junqing, HAN Yunqi, et al. Metaheuristics for solving the vehicle routing problem with the time windows and energy consumption in cold chain logistics[J]. Appl Soft Computing, 2020,95:178-190.
[3]	Karakatič S. Optimizing nonlinear charging times of electric vehicle routing with genetic algorithm[J]. Expert Sys Appl, 2021,164:356-371.
[4]	Losa J, Schulte F Spaan M T J, et al. The value of information sharing for platform-based collaborative vehicle routing[J]. Transp Res Part E: Logistics Transp Rev, 2020,141:145-160.
[5]	张照生. 交通约束下的行车最优路径规划[D]. 北京:清华大学, 2013.
	ZHANG Zhaosheng. Optimum vehicular path planning under traffic restriction[D]. Beijing: Tsinghua University, 2013. (in Chinese)
[6]	CHEN Dawei, PAN Shuangli, CHEN Qun, et al. Vehicle routing problem of contactless joint distribution service during COVID-19 pandemic[J]. Transp Res Interdisciplinary Perspectives, 2020,8:225-241.
[7]	Gmira M, Gendreau M, Lodi A, Potvin J Y. Tabu search for the time-dependent vehicle routing problem with time windows on a road network[J]. Euro J Operational Res, 2021,288:129-140.
[8]	Stellingwerf H, Groeneveld L, Laporte G, et al. The quality-driven vehicle routing problem: Model and application to a case of cooperative logistics[J]. Int’l J Production Economics, 2020,231:107-122.
[9]	LU Ji, CHEN Yuning, HAO Jinkao, HE Renjie. The time-dependent electric vehicle routing problem: Model and solution[J]. Expert Syst Appl, 2020,61:331-346.
[10]	张静. 面向路径规划的导航路网数据模型研究[D]. 北京:中国矿业大学, 2009.
	ZHANG Jing. Research on navigation network data model for route planning[D]. Beijing: China University of Mining and Technology, 2009. (in Chinese)
[11]	杨易. 智能车辆组合定位与路径导航技术研究[D]. 长沙:湖南大学, 2006.
	YANG Yi. Research on technologies of intelligent vehicle integrated location and route navigation[D]. Changsha: Hunan University, 2006. ( in Chinese)
[12]	CHEN Ning, ZHANG Yun. Energy consumption model of urban transportation based on road network capacity[C]// Asia-Pacific Power and Energy Eng Conf, Chengdu, China, 2010,1:1-4.
[13]	Ranacher P, Brunauer R, van der Spek S, et al. A model to estimate and interpret the energy-efficiency of movement patterns in urban road traffic[J]. Computers, Envi Urban Syst, 2016,59:152-163.
[14]	GUO Chenjuan, YANG Bin, Andersen O, et al. EcoMark 2.0: Empowering eco-routing with vehicular environmental models and actual vehicle fuel consumption data[J]. Geoinfo, 2015,19:567-599.
[15]	Kropiwnicki J. A unified approach to the analysis of electric energy and fuel consumption of cars in city traffic[J]. Energy, 2019,182:1045-1057.
[16]	LIU Chenglin, WANG Jianqiang, CAI Wenjuan, et al. An energy-efficient dynamic route optimization algorithm for connected and automated vehicles using velocity-space-time networks[J]. IEEE Access, 2019,7:108866-108877.
[17]	Krajzewicz D, Erdmann J, Behrisch M, et al. Recent development and applications of SUMO - simulation of urban mobility[J]. Int’l J Adv Syst Meas, 2012,5:128-138.
[18]	Celtek S A, Durdu A, Alı M E M. Real-time traffic signal control with swarm optimization methods[J] Measurement, 2020,166:108-122.
[19]	San José R, Pérez J L, Gonzalez-Barras R M. Assessment of mesoscale and microscale simulations of a NO₂ episode supported by traffic modelling at microscopic level[J]. Sci Total Envir, 2021,752:141-160.
[20]	ZHANG Zhengchao, LI Meng, LIN Xi, et al. Multistep speed prediction on traffic networks: A graph convolutional sequence-to-sequence learning approach with attention mechanism[J]. Transp Res Part C: Emerging Tech, 2019,105:297-322.
[21]	ZHOU Wei, YANG Lin, CAI Yishan, et al. Dynamic programming for new energy vehicles based on their work modes part I: Electric vehicles and hybrid electric vehicles[J]. J Power Sources, 2018,406:151-166.

平均车速		-0.42
车辆密度	ρ_i,t	0.64
道路长度	l_i	0.18
非绿灯的时长	r_i,t	0.08
路口长度	γ_i	0.11
通行功率	ē_i,t	-0.38
预估通行时长	τ_{i, t}	0.18
下一道路j的平均车速	v_j,t'	-0.29
下一道路j的车辆密度	ρ_j,t'	0.51
绿灯时长	j_i,t	-0.1

平均车速		-0.42
车辆密度	ρ_i,t	0.64
道路长度	l_i	0.18
非绿灯的时长	r_i,t	0.08
路口长度	γ_i	0.11
通行功率	ē_i,t	-0.38
预估通行时长	τ_{i, t}	0.18
下一道路j的平均车速	v_j,t'	-0.29
下一道路j的车辆密度	ρ_j,t'	0.51
绿灯时长	j_i,t	-0.1

ID		ρ_i,t	l_i	r_i,t	g_i,t	τ_{i, t}	ē_i,t		ρ_j,t'	γ_i	RE/%	MAE/s
1	√	√	√	√	√	√	√	√	√	√	10.39	2.95
2	√	√	√	√	√	√	√			√	8.66	2.59
3	√	√	√	√	√	√	√				8.60	2.51
4	√	√	√	√	√	√					8.97	2.65
5	√	√	√	√	√						8.97	2.66
6	√	√	√	√	√			√	√		9.68	2.78
7	√	√	√	√	√			√	√	√	10.01	2.87
8	√	√	√	√	√					√	8.71	2.64

ID		ρ_i,t	l_i	r_i,t	g_i,t	τ_{i, t}	ē_i,t		ρ_j,t'	γ_i	RE/%	MAE/s
1	√	√	√	√	√	√	√	√	√	√	10.39	2.95
2	√	√	√	√	√	√	√			√	8.66	2.59
3	√	√	√	√	√	√	√				8.60	2.51
4	√	√	√	√	√	√					8.97	2.65
5	√	√	√	√	√						8.97	2.66
6	√	√	√	√	√			√	√		9.68	2.78
7	√	√	√	√	√			√	√	√	10.01	2.87
8	√	√	√	√	√					√	8.71	2.64

	关联性
	DP油耗	参数1	参数2	参数3	参数4	参数5	参数6	参数7	参数8
DP油耗	1.00	0.90	0.63	0.44	0.66	-0.37	0.58	0.34	-0.46
参数1	0.90	1.00	0.92	0.30	0.83	-0.16	0.46	0.18	-0.25
参数2	0.63	0.92	1.00	0.61	0.62	-0.37	0.75	0.51	-0.49
参数3	0.44	0.30	0.61	1.00	-0.14	-0.57	0.80	0.86	-0.73
参数4	0.66	0.83	0.62	-0.14	1.00	0.35	0.06	-0.22	0.28
参数5	-0.37	-0.16	-0.37	-0.57	0.35	1.00	-0.64	-0.68	0.95
参数6	0.58	0.46	0.75	0.80	0.06	-0.64	1.00	0.92	-0.69
参数7	0.34	0.18	0.51	0.86	-0.22	-0.68	0.92	1.00	-0.73
参数8	-0.46	-0.25	-0.49	-0.73	0.28	0.95	-0.69	-0.73	1.00