基于组合博弈的高速作业区人机共驾切换策略决策

doi:10.3969/j.issn.1674-8484.2025.03.015

摘要/Abstract

摘要：

为有效缓解高速公路作业区路段混合交通流所导致的瓶颈效应，提升路段行车安全性，针对高速公路作业区行驶路段的人机共驾车辆控制权分配决策，提出了基于Stackelberg博弈和非合作Nash博弈组成的动态组合博弈模型。利用VISSIM软件构建作业区路段微观混合交通流仿真场景，验证决策模型有效性并分析模型对交通流安全性和通行效率的影响。结果表明：作业区路段仿真试验中所提出的决策模型有效性超过66%，平均降低冲突发生率34.15%，低流量下冲突发生率最高降低70.77%，该模型显著提升了作业区路段的安全性，并在91.67%的行车场景中有效提高了通行效率。未来在作业区路段的交通管制中，考虑进一步应用和优化该模型，以实现更高效的交通安全保障。

关键词: 交通安全, 人机共驾, 驾驶策略, 高速公路, 作业区

Abstract:

To effectively mitigate the bottleneck effect induced by mixed traffic flow and enhance road safety, a dynamic combination game model based on Stackelberg game and non-cooperative Nash game was presented for the allocation decision of control rights of man-machine vehicles in the road section of the highway operation area. VISSIM software was employed to establish a micro-hybrid traffic flow simulation scenario for the sections in the operation area, validate the effectiveness of the decision model, and analyze the influence of the model on traffic flow safety and traffic efficiency. The results show that the effectiveness of the proposed decision model exceeds 66%, the average conflict incidence is decreased by 34.15%, and the highest conflict incidence is reduced by 70.77% under low traffic flow. The model significantly enhances the safety of the road section in the operation area and effectively improves the traffic efficiency in 91.67% of driving scenarios. In the future, the model should be further applied and optimized to achieve more efficient traffic safety.

Key words: traffic safety, man-machine co-driving, driving strategy, highway, working area

中图分类号:

U492.8

周倩西, 巫诚诚, 胡政, 石亮亮. 基于组合博弈的高速作业区人机共驾切换策略决策[J]. 汽车安全与节能学报, 2025, 16(3): 487-495.

ZHOU Qianxi, WU Chengcheng, HU Zheng, SHI Liangliang. Strategy decision of man-machine co-driving switching in high-speed operation area based on combination game[J]. Journal of Automotive Safety and Energy, 2025, 16(3): 487-495.

图/表 9

参考文献 21

[1]	WANG Junhua, SONG Hao, FU Ting, et al. Crash prediction for freeway work zones in real time: A comparison between convolutional neural network and binary logistic regression model[J]. Int’l J Transport Sci Tech, 2022, 11(3): 484-495.
[2]	林庆峰, 王兆杰, 鲁光泉. L3级自动驾驶汽车的接管安全性评价模型[J]. 汽车工程, 2019, 41(11): 1258-1264. doi: 10.19562/j.chinasae.qcgc.2019.011.005
	LIM Qingfeng, WANG Zhaojie, LU Guangquan. Takeover safety evaluation model of level 3 autonomous vehicle[J]. Autom Engineering, 2019, 41(11): 1258-1264. (in Chinese)
[3]	郑元. 智能网联环境下高速公路自动驾驶车辆决策控制研究[D]. 南京: 东南大学, 2020.
	ZHENG Yuan. Research on decision control of autonomous driving vehicles on expressway under intelligent network environment[D]. Nanjing: Southeast university, 2020. (in Chinese)
[4]	梁国华, 石权, 李瑞, 等. 高速公路合流区主要参数对自动驾驶车辆的影响[J]. 哈尔滨工业大学学报, 2021, 53(9): 62-68.
	LIANG Guohua, SHI Quan, LI Rui, et al. Influence of main parameters in expressway confluence area on autonomous vehicles[J]. J Harbin Instit Tech, 2021, 53(9): 62-68. (in Chinese)
[5]	樊永恒, 李美玲, 冉晋, 等. 自动驾驶车辆对高速公路混合交通流影响研究[J]. 武汉理工大学学报(交通科学与工程版), 2022, 46(1): 28-32.
	FAN Yongheng, LI Meiling, RAN Jin, et al. Study on the impact of autonomous vehicles on mixed traffic flow on expressway[J]. J Wuhan Univ Tech (Traf Sci Engi), 2022, 46(1): 28-32. (in Chinese)
[6]	LI Mingjun, SONG Xiaolin, CAO Haotian, et al. Shared control with a novel dynamic authority allocation strategy based on game theory and driving safety field[J]. Mech Syst Sign Proc, 2019, 124: 199-216.
[7]	刘瑞, 朱西产, 刘霖, 等. 基于非合作模型预测控制的人机共驾策略[J]. 同济大学学报(自然科学版), 2019, 47(7): 1037-1045.
	LIU Rui, ZHU Xichang, LIU Lin, et al. Co-driving strategy based on non-cooperative model predictive control[J]. J Tongji Univ (Nat Sci), 2019, 47(7): 1037-1045. (in Chinese)
[8]	何任, 赵小聪, 杨毅斌, 等. 基于人类驾驶员风险反应机制的人机共享驾驶模型[J]. 吉林大学学报(工学版), 2021, 51(3): 799-809.
	HE Ren, ZHAO Xiaocong, YANG Yibin, et al. Human-machine shared driving model based on human driver's risk response mechanism[J]. J Jilin Uni (Engi Tech Edit), 2021, 51(3): 799-809. (in Chinese)
[9]	孙博华. 考虑驾驶能力及驾驶习性的个性化人机共驾策略研究[D]. 长春: 吉林大学, 2020.
	SUN Bohua. Research on personalized man-machine co-driving strategy considering driving ability and driving habit[D]. Changchun: Jilin University, 2020. (in Chinese)
[10]	郭柏苍, 王胤霖, 谢宪毅, 等. 基于人-车风险状态的人机共驾控制权决策方法[J]. 中国公路学报, 2022, 35(3): 153-165. doi: 10.19721/j.cnki.1001-7372.2022.03.013
	GUO Baicang, WANG Yinlin, XIE Xianyi, et al. Control decision method of human-machine co-driving based on human-vehicle risk state[J]. China J Highw Transport, 2022, 35(3): 153-165. (in Chinese)
[11]	武珂缦, 赵娜乐, 矫成武, 等. 高速公路施工路段合流区车辆智能汇合控制策略研究[J]. 交通技术, 2022, 11(4): 355-366.
	WU Keman, ZHAO Nale, JIAO Chengwu, et al. Research on vehicle intelligent confluence control strategy in confluence area of expressway construction section[J]. Transport Tech, 2022, 11(4): 355-366. (in Chinese)
[12]	过秀成, 肖哲, 张一鸣, 等. 考虑智能网联车辆影响的八车道高速公路施工区可变限速控制方法[J]. 东南大学学报(自然科学版), 2024, 54(2): 353-359.
	GUO Xiucheng, XIAO Zhe, ZHANG Yiming, et al. Variable speed limit control method in construction area of eight-lane expressway considering the influence of intelligent networked vehicles[J]. J Southeast Univ (Nat Sci Edit), 2019, 54(2): 353-359. (in Chinese)
[13]	陈玲娟, 张思琦, 马东方. 施工区混行车流跟驰及换道模型研究[J]. 交通运输系统工程与信息, 2021, 21(2): 58-64.
	CHEN Lingjuan, ZHANG Siqi, MA Dongfang. Research on mixed traffic flow following and lane change model in construction area[J]. Transport Syst Engi Info, 2021, 21(2): 58-64. (in Chinese)
[14]	李晓虎, 麦乐, 任杰, 等. 高速公路施工区自动车辆行驶轨迹优化方法[J]. 交通信息与安全, 2020, 38(3): 40-47.
	LI Xiaohu, MAI Le, REN Jie, et al. Optimization method of automatic vehicle trajectory in expressway Construction area[J]. Traf Info Safe, 2020, 38(03): 40-47. (in Chinese)
[15]	朱顺应, 邹禾, 蒋若曦, 等. 高速公路施工区合流路段交通冲突模型[J]. 哈尔滨工业大学学报, 2020, 52(9): 70-76.
	ZHU Hui, ZOU He, JIANG Ruoxi, et al. Traffic conflict model of confluence section of expressway construction area[J]. J Harbin Instit Tech, 2020, 52(9): 70-76. (in Chinese)
[16]	严利鑫, 吴超仲, 贺宜, 等. 人机共驾智能车驾驶模式决策属性析取研究[J]. 中国公路学报, 2018, 31(1): 120-127.
	YAN Lixin, WU Chaozhong, HE Yi, et al. Computer has a smart car driving mode decision attribute extraction research[J]. China J Highw Transport, 2018, 31(1): 120-127. (in Chinese)
[17]	李胜琴, 杜鹏. 考虑驾驶员差异性的安全距离模型优化[J]. 江苏大学学报(自然科学版), 2023, 44(3): 249-253, 261.
	LI Shengqin, DU Peng. Safety distance model optimization considering driver difference[J]. J Jiangsu Univ (Nat Sci Edit), 2023, 44(3): 249-253, 261. (in Chinese)
[18]	GUO Mengzhu, LI Shiwu, WANG Linhong, et al. Research on the relationship between reaction ability and mental state for online assessment of driving fatigue[J]. Int’l J Environ Res Publ Heal, 2016, 13(12): No 1174.
[19]	李浩, 康柳江, 罗斯达, 等. 人工和自动混合驾驶环境下的最优道路拥堵收费模型[J]. 北京大学学报(自然科学版), 2023, 59(5): 747-756.
	LI Hao, KANG Liujiang, Rosda, et al. An optimal road congestion charging model in hybrid driving environment[J]. J Peking Uni (Nat Sci), 2023, 59(5): 747-756. (in Chinese)
[20]	LIU Zhaocai, SONG Ziqi. Strategic planning of dedicated autonomous vehicle lanes and autonomous vehicle/toll lanes in transportation networks[J]. Transport Res Part C, 2019, 106: 381-403.
[21]	姚志洪, 金玉婷, 王思琛, 等. 混入智能网联汽车的交通流稳定性与安全性分析[J]. 中国安全科学学报, 2021, 31(10): 136-143. doi: 10.16265/j.cnki.issn1003-3033.2021.10.019
	YAO Zhihong, JIN Yuting, WANG Sichen et al. Stability and safety analysis of traffic flow with intelligent networked vehicles[J]. China Safe Sci J, 2021, 31(10): 136-143. (in Chinese)

驾驶模式	α_i (i为A或M)		ε
驾驶模式	参数值	P值	参数值	P值
人工驾驶	1.635	0.021	0.572	0.492
自动驾驶	2.474	0.001	-0.389	0.642

驾驶模式	α_i (i为A或M)		ε
驾驶模式	参数值	P值	参数值	P值
人工驾驶	1.635	0.021	0.572	0.492
自动驾驶	2.474	0.001	-0.389	0.642

驾驶人疲劳状态	Nash均衡解存/否	收益函数均衡值	结果
不疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} \bar{h}_{\mathrm{tm}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sm}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{1 \mathrm{n}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\mathrm{max}} t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
不疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式
轻微疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} \overline{h_{\mathrm{tn}}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sn}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{\mathrm{ln}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\max } t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
轻微疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式
严重疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} h_{\mathrm{tn}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sn}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{1 \mathrm{n}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\mathrm{max}} t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
严重疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式

驾驶人疲劳状态	Nash均衡解存/否	收益函数均衡值	结果
不疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} \bar{h}_{\mathrm{tm}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sm}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{1 \mathrm{n}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\mathrm{max}} t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
不疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式
轻微疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} \overline{h_{\mathrm{tn}}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sn}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{\mathrm{ln}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\max } t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
轻微疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式
严重疲劳	存在	$\pi_{i}^{*}=\frac{2.474 \beta_{\mathrm{A}} h_{\mathrm{tn}} f_{1 \mathrm{w}} f_{2 \mathrm{w}} f_{3 \mathrm{w}} N_{\mathrm{sn}} d_{\mathrm{n}}}{n \overline{h_{\mathrm{tw}}} f_{1 \mathrm{n}} f_{2 \mathrm{n}} f_{3 \mathrm{n}} N_{\mathrm{sw}} v_{\mathrm{max}} t} \forall i \in\{\mathrm{~A}, \mathrm{M}\}$	人机共驾车辆保持自动驾驶模式通过高速公路作业区路段
严重疲劳	不存在	式(16)不成立	根据式(16)中数值更大一方决策出驾驶人未处于疲劳状态时，车辆的驾驶模式

疲劳状态等级	间隙时间 / s	P_w / %
1级	0.9	0
2级	0.8	8.16
3级	0.7	16.72