Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2024, Vol. 58 Issue (8): 1659-1670    DOI: 10.3785/j.issn.1008-973X.2024.08.013
交通工程、土木工程     
基于多智体的自动驾驶汽车停车空载收费策略
黎文皓1,2(),季彦婕1,*(),吴浩3,贾叶雯1,张水潮4
1. 东南大学 交通学院，江苏 南京 211189
2. 名古屋大学 土木与环境工程系，爱知县 名古屋 464-8603
3. 安徽三联学院 交通信息与安全重点实验室，安徽 合肥 230601
4. 宁波工程学院 建筑与交通工程学院，浙江 宁波 315211
Empty-load charging strategy for autonomous vehicle parking based on multi-agent system
Wenhao LI1,2(),Yanjie JI1,*(),Hao WU3,Yewen JIA1,Shuichao ZHANG4
1. School of Transportation, Southeast University, Nanjing 211189, China
2. Department of Civil and Environmental Engineering, Nagoya University, Nagoya 464-8603, Japan
3. Key Laboratory of Traffic Information and Safety, Anhui Sanlian University, Hefei 230601, China
4. School of Civil and Transportation Engineering, Ningbo University of Technology, Ningbo 315211, China
 全文: PDF(2970 KB)   HTML
摘要：

为了制订自动驾驶车辆(AV)停车需求管理方案，搭建多智能体停车模拟框架，提出2种空载行驶收费策略：基于行驶距离的静态收费和基于道路拥堵水平的动态收费，研究费率计算方法. 建立空载行驶收费策略下停车场停车、居住地停车及持续空载巡航3种停车模式的成本函数，使用logit模型描述不同停车模式下的选择行为. 利用Simulation of urban mobility (SUMO)，以南宁市主城区为例开展大规模路网下的仿真实验，研究2种策略下的AV停车行为及路网运行状态变化. 仿真结果表明，静态收费策略和动态收费策略下的AV空载行驶里程分别减少了20.16%和10.85%，车辆总延误分别降低了39.80%和43.52%；动态收费策略能够灵活地根据路况变化进行实时调整，路网运行效率提升更显著.
关键词： 停车空载收费;  自动驾驶汽车;  多智能体模拟;  SUMO    
Abstract:

A multi-agent parking simulation framework was constructed in order to formulate autonomous vehicle (AV) parking demand management strategies. Two charging strategies for empty-load driving were proposed: a static charge based on driving distance and a dynamic charge based on road congestion levels. Rate calculation method was analyzed. Cost functions for parking lots, residential parking, and continuous empty cruising were established under these charging policies. A logit model was used to describe the choice behavior under different parking modes. The simulation of urban mobility (SUMO) was used to conduct a large-scale road network simulation experiment in Nanning’s main urban area. AV parking behavior and road network operation under both strategies were analyzed. The simulation results showed that the empty-load driving mileage of AVs decreased by 20.16% and 10.85% under the static and dynamic charging strategies, respectively. Total vehicle delay decreased by 39.80% and 43.52%, respectively. The dynamic charging strategy was adjustable in real-time based on road conditions, and operational efficiency of the road network was significantly enhanced.
Key words: empty-load parking charge    autonomous vehicle    multi-agent simulation    SUMO
收稿日期: 2023-09-21 出版日期: 2024-07-23
CLC:  U 491  
基金资助: 中央高校基本科研业务费专项资金资助项目（2242020K40063）；江苏省研究生科研与实践创新计划资助项目（KYCX20_0137）；浙江省自然科学基金资助项目（LTGG23E080005）.
通讯作者: 季彦婕     E-mail: liwenhao@seu.edu.cn;jiyanjie@seu.edu.cn
作者简介: 黎文皓（1993—），男，博士生，从事智能交通的研究. orcid.org/0000-0003-1420-8163. E-mail：liwenhao@seu.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
黎文皓
季彦婕
吴浩
贾叶雯
张水潮

引用本文:

黎文皓,季彦婕,吴浩,贾叶雯,张水潮. 基于多智体的自动驾驶汽车停车空载收费策略[J]. 浙江大学学报(工学版), 2024, 58(8): 1659-1670.

Wenhao LI,Yanjie JI,Hao WU,Yewen JIA,Shuichao ZHANG. Empty-load charging strategy for autonomous vehicle parking based on multi-agent system. Journal of ZheJiang University (Engineering Science), 2024, 58(8): 1659-1670.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.08.013    或    https://www.zjujournals.com/eng/CN/Y2024/V58/I8/1659

图 1  AV停车空载收费的仿真逻辑
智能体种类功能属性
AV-出行者实现车辆微观行驶、停车模式选择、路径选择速度、加速度、车辆类型、活动时间、路径选择规则、停车模式决策规则
停车系统动态更新停车资源，完成停车位预订和分配停车场容量、车位预定信息、停车位价格、空闲停车位数量、停车位位置
RSU实现道路状态识别，控制车辆巡航静态信息（限速、车道数、长度）、动态信息（车辆数、车速、行程时间）
TMC更新和整合道路资源、停车资源，完成空载收费发布，
实现停车诱导		车辆信息、道路状态信息、停车场信息、空载收费策略
表 1  AV停车仿真模型不同类型智能体的特性
图 2  动态空载收费策略的分段增长函数
图 3  南宁市主城区示意图
图 4  研究区域交通小区的需求生成分布（小汽车）
场景编号收费策略收费区域$ {\tau }_{G} $/（元·km?1）
1无收费（基础场景）——
2静态收费策略区域$ {G}_{1} $$ {\tau }_{{G}_{1}} $：1.98
区域$ {G}_{2} $$ {\tau }_{{G}_{2}} $：0.61
3动态收费策略区域$ {G}_{1} $最小值：0
最高值$ {3\tau }_{{G}_{1}} $：5.94
区域$ {G}_{2} $最小值：0
最高值$ {3\tau }_{{G}_{2}} $：1.83
表 2  AV停车行为仿真模型的仿真场景
参数数值
HVAV
加速度$ a $/（m·s?2）2.63.8
减速度$ {a}_{\mathrm{d}\mathrm{e}\mathrm{c}} $/（m·s?2）3.54.5
紧急情况下减速度$ {a}_{\mathrm{e}\mathrm{m}} $/（m·s?2）9.09
驾驶容差$ {T}_{\mathrm{t}\mathrm{o}\mathrm{l}} $0.50
最小跟车间隙$ {d}_{\mathrm{m}\mathrm{i}\mathrm{n}} $/m2.51.5
期望车头时距$ {t}_{\mathrm{h}\mathrm{e}\mathrm{a}\mathrm{d}} $/s1.00.6
表 3  跟驰和换道模型的参数
区域类别分段费率/（元·h?1）每日最高限价/元
一类区域前3小时：4
3小时后：6		50
二类区域330
三类区域215
表 4  停车场费率
活动目的ρres
$ {\lambda }_{\mathrm{s}\mathrm{u}\mathrm{b}\mathrm{s}}=0 $$ {\lambda }_{\mathrm{s}\mathrm{u}\mathrm{b}\mathrm{s}}=1 $
通勤30%70%
商务50%50%
生活50%50%
通学100%0
其他100%0
表 5  预约接载比例
场景停车模式$ {r_{{\text{choice}}}} $/%$ {\bar C_{{\text{total}}}} $/元$ {\bar T_{{\text{activity}}}} $/h$ {\bar C_{{\text{per hour}}}} $/（元·h?1）$ {\bar D_{{\text{travel}}}} $/km
场景1停车场停车45.6922.225.923.7515.99
住宅停车54.0117.039.191.858.62
巡航替代停车0.3010.910.4027.2810.20
均值—19.387.672.5311.99
场景2停车场停车62.0025.616.703.8214.69
住宅停车37.8019.729.302.127.54
巡航代替停车0.2010.600.3728.6517.32
均值—23.357.673.0411.99
场景3停车场停车59.2724.296.613.6815.01
住宅停车40.5518.979.262.057.55
巡航代替停车0.1810.630.3827.9717.43
均值—22.117.672.8811.99
表 6  不同场景下AV停车模式特征
图 5  不同场景下AV空载行驶里程的变化
图 6  不同场景下AV空载行程时间的变化
图 7  交通量变化vs.无收费场景（场景1）
图 8  不同场景早高峰相对速度的比较
道路类型场景2场景3
γmγvγdγmγvγd
高速公路?2.690.02?0.41?1.760.01?0.39
快速路?13.673.38?56.53?11.783.87?53.99
主干道?7.343.48?43.52?6.554.25?44.22
次干道?9.053.59?36.64?6.073.71?43.21
三级道路?5.132.41?27.62?4.393.06?32.81
居住区道路?6.462.44?31.44?6.271.45?43.15
表 7  不同道路类型的行驶里程、速度及延误变化vs.无收费场景（场景1）
图 9  停车场收费分布
图 10  AV停车空载收费的分布
1 何胜学 自动代客泊车背景下的共享停车供需匹配模型及对应禁忌搜索算法[J]. 计算机应用研究, 2021, 38 (9): 2721- 2725
HE Shengxue Shared parking supply-demand matching model and designed tabu search algorithm based on autonomous valet parking[J]. Application Research of Computers, 2021, 38 (9): 2721- 2725
2 SHIN H, KIM M J, BAEK S, et al Perpendicular parking path generation and optimal path tracking algorithm for auto-parking of trailers[J]. International Journal of Control, Automation and Systems, 2022, 20 (9): 3006- 3018
3 RADVAND T, BAHRAMI S, YIN Y, et al Curbing cruising-as-substitution-for-parking in automated mobility[J]. Transportation Research Part C: Emerging Technologies, 2022, 143: 103853
4 廉天翔. 面向自动驾驶汽车发展不同阶段的城市共享停车运营优化管理[D]. 北京: 北京交通大学, 2023.
LIAN Tianxiang. Optimized management of urban shared parking operations for different stages of self-driving vehicle development [D]. Beijing: Beijing Jiaotong University, 2023.
5 CHAI H, RODIER C J, SONG J W, et al The impacts of automated vehicles on center city parking[J]. Transportation Research Part A: Policy and Practice, 2023, 175: 103764
6 YAQOOB I, KHAN L U, KAZMI S M A, et al Autonomous driving cars in smart cities: recent advances, requirements, and challenges[J]. IEEE Network, 2019, 34 (1): 174- 181
7 KANG D, HU F, LEVIN M W Impact of automated vehicles on traffic assignment, mode split, and parking behavior[J]. Transportation Research Part D: Transport and Environment, 2022, 104: 103200
8 MILLARD-BALL A The autonomous vehicle parking problem[J]. Transport Policy, 2019, 75: 99- 108
9 CHILDRESS S, NICHOLS B, CHARLTON B, et al Using an activity-based model to explore the potential impacts of automated vehicles[J]. Transportation Research Record, 2015, 2493 (1): 99- 106
10 LEVIN M W, BOYLES S D Effects of autonomous vehicle ownership on trip, mode, and route choice[J]. Transportation Research Record, 2015, 2493 (1): 29- 38
11 HARPER C D, HENDRICKSON C T, SAMARAS C Exploring the economic, environmental, and travel implications of changes in parking choices due to driverless vehicles: an agent-based simulation approach[J]. Journal of Urban Planning and Development, 2018, 144 (4): 04018043
12 ZHANG X, LIU W, WALLER S T A network traffic assignment model for autonomous vehicles with parking choices[J]. Computer‐Aided Civil and Infrastructure Engineering, 2019, 34 (12): 1100- 1118
13 MONDAL A, JURI N R, BHAT C R, et al Accounting for ride-hailing and connected and autonomous vehicle empty trips in a four-step travel demand model[J]. Transportation research record, 2023, 2677 (3): 217- 228
14 WATANATADA T, DHARESHWAR A M, LIMA P R S R. Vehicle speeds and operating costs: models for road planning and management [R]. Washington, DC (USA): International Bank for Reconstruction and Development, 1987.
15 YAO E, WANG M, SONG Y, et al Estimating energy consumption on the basis of microscopic driving parameters for electric vehicles[J]. Transportation Research Record, 2014, 2454 (1): 84- 91
16 REZAEI M, NOORI H, RAZLIGHI M M, et al Refocus+: multi-layers real-time intelligent route guidance system with congestion detection and avoidance[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 22 (1): 50- 63
17 戴晶辰, 李瑞敏. 基于微观仿真的北京市拥堵收费研究[J]. 系统仿真学报, 2019, 31(11): 2458-2470.
DAI Jingchen, LI Ruimin. Microscopic simulation based evaluation of congestion pricing for Beijing urban area [J]. Journal of System Simulation , 2019, 31(11): 2458-2470.
[1] 张俊杰,马永锋,陈淑燕,邢冠仰,张子煜. 高速公路施工区车队被动换道行为建模与仿真[J]. 浙江大学学报(工学版), 2024, 58(2): 381-387.
[2] 曹宁博,赵利英. 路段环境自动驾驶汽车通行权决策方法[J]. 浙江大学学报(工学版), 2022, 56(1): 118-127.