Vehicle speed planning method with the vehicle-road-cloud integration system and incorporating human-vehicle game theory

doi:10.3969/j.issn.1674-8484.2026.02.012

Abstract

Abstract:

The vehicle-pedestrian interaction (VPI) for autonomous vehicles was investigated to resolve the conflicts between the driving continuity and the safety caused by sudden pedestrian crossing. A Social Force model was constructed for pedestrian crossing with roadside perception and cloud-side historical information to characterize the pedestrian behaviors and to deliver the corresponding data to on-board terminals. A two-layer collaborative decision-making and control strategy was proposed with its upper layer introduced the Stackelberg game model and with its lower layer adopted an improved model predictive control (MPC). The lower layer took upper-layer game results as the trajectory optimization objective. Simulation experiments were conducted on VPI scenarios in uncontrolled urban road segments. The results show that the proposed method reduces interaction time by 0.59 s and 0.27 s respectively, compared with the single obstacle avoidance control (OAC) method and the MPC method; improves traffic light passing rate by 6.2% and 2.9% respectively, compared with the above two control methods. Therefore, the proposed method improves the efficiency and the safety of vehicles within limited traffic time window, and can simulate the vehicle-pedestrian collaboration and conflict scenarios.

Key words: autonomous vehicles, vehicle-pedestrian interaction (VPI), game theory, social force model, speed planning

CLC Number:

U467.1

WEN Jiayan, ZOU Haifeng, ZHONG Wei, GAO Bolin, LU Yanbo. Vehicle speed planning method with the vehicle-road-cloud integration system and incorporating human-vehicle game theory[J]. Journal of Automotive Safety and Energy, 2026, 17(2): 261-269.

Figures/Tables 14

References 29

[1]	ZOU Fengjiao, Ogle J, JIN Weimin, et al. Pedestrian behavior interacting with autonomous vehicles: Role of AV operation and signal indication and roadway infrastructure[C]// IEEE Conf Virt Real 3D User Interf Abstr Workshops (VRW), 2023: 821-822.
[2]	LIANG Zijun, ZHAN Xuejuan, WANG Ruihan, et al. Identification of factors influencing the operational effect of the green wave on urban arterial roads based on association analysis[J]. *Appl Sci*, 2023, 13(14): 8372.
[3]	Rasouli A, Kotseruba I. Intend-wait-cross: Towards modeling realistic pedestrian crossing behavior[C]// 2022 IEEE Intell Vehi Symp (IV). IEEE, 2022: 83-90.
[4]	瞿广跃, 杨澜, 袁梦, 等. 面向自动驾驶汽车的信号交叉口行人多模态轨迹预测方法[J]. 汽车安全与节能学报, 2024, 15(5): 689-701.
	QU Guangyue, YANG Lan, YUAN Meng, et al. Pedestrian multi-modal trajectory prediction method for signalized intersections oriented to autonomous vehicles[J]. *J Autom Safe Energ*, 2024, 15(5): 689-701. (in Chinese)
[5]	Kapania N R, Govindarajan V, Borrelli F, et al. A hybrid control design for autonomous vehicles at uncontrolled crosswalks[C]// 2019 IEEE Intel Vehi Symp (IV). IEEE, 2019: 1604-1611.
[6]	Helbing D, Molnar P. Social force model for pedestrian dynamics[J]. *Phys Rev E*, 1995, 51(5): 4282-4286. pmid: 9963139
[7]	Shrivas A, Kumar A. Modified social force model for pedestrian-vehicle interactions at a signalized intersection[J]. *Transport Lett*, 2024, 16(4): 307-319.
[8]	LI Hanchu, LIAO Ziyi, RUI Yikang, et al. A physical law constrained deep learning model for vehicle trajectory prediction[J]. *IEEE Internet Things J*, 2023, 10(24): 22775-22790. doi: 10.1109/JIOT.2023.3305395 URL
[9]	Bjørnskau T. The zebra crossing game: Using game theory to explain a discrepancy between road user behaviour and traffic rules[J]. *Safe Sci*, 2017, 92: 298-301. doi: 10.1016/j.ssci.2015.10.007 URL
[10]	ZHU Dianchen, Sze N N. Propensities of red light running of pedestrians at the two-stage crossings with split pedestrian signal phases[J]. *Acci Anal Prev, 2021, 151*: 105958.
[11]	Amini R E, Dhamaniya A, Antoniou C. Towards a game theoretic approach to model pedestrian road crossings[J]. *Transport Res Procedia*, 2021, 52: 692-699. doi: 10.1016/j.trpro.2021.01.083 URL
[12]	周倩西, 巫诚诚, 胡政, 等. 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, et al. Decision-making of human-machine co-driving switching strategy in high-speed work zones based on combinatorial game theory[J]. *J Autom Safe Energ*, 2025, 16(3): 487-495. (in Chinese)
[13]	Holt C A, Roth A E. The Nash equilibrium: A perspective[J]. *Proc National Acad Sci, 2004, 101*(12): 3999-4002.
[14]	Başar T, Olsder G J. Dynamic Noncooperative Game Theory[M]. Philadelphia: Society for Industrial and Applied Mathematics, 1998: 70-155.
[15]	Nowak M A, May R M. Evolutionary games and spatial chaos[J]. *Nature, 1992, 359*(6398): 826-829.
[16]	李文礼, 张祎楠, 石晓辉, 等. 基于博弈论的右转无信号交叉口行人行为模拟[J]. 机械工程学报, 2024, 60(10): 86-101.
	LI Wenli, ZHANG Yinan, SHI Xiaohui, et al. Pedestrian behavior simulation at unsignalized right-turn intersections based on game theory[J]. *J Mech Engi*, 2024, 60(10): 86-101. (in Chinese)
[17]	李海洋, 曲大义, 杨子奕, 等. 无信号控制交通场景的人车博弈行为分析及决策建模[J]. 青岛理工大学学报, 2023, 44(5): 138-149.
	LI Haiyang, QU Dayi, YANG Ziyi, et al. Analysis and decision modeling of vehicle-pedestrian game behaviors in signal-free traffic scenarios[J]. *J Qingdao Univ Tech*, 2023, 44(5): 138-149. (in Chinese)
[18]	Parajuli S, Cherry C R, Zavisca E, et al. Are pedestrian crashes becoming more severe: A breakdown of pedestrian crashes in urban Tennessee[J]. *Transport Res Rec, 2023, 2678*(6): 523-541.
[19]	TANG Bin, YANG Zhengyi, JIANG Haobin. Development of pedestrian collision avoidance strategy based on the fusion of Markov and social force models[J]. *Mech Sci*, 2024, 15(1): 17-30.
[20]	CHEN Peng, WU Chaozhong, ZHU Shunying. Interaction between vehicles and pedestrians at uncontrolled mid-block crosswalks[J]. *Safe Sci*, 2016, 82: 68-76. doi: 10.1016/j.ssci.2015.09.016 URL
[21]	CHEN Yongli, LI Shen, TANG Xiaolin, et al. Interaction-aware decision-making for autonomous vehicles[J]. *IEEE Trans Transport Electrificat*, 2023, 9(3): 4704-4715.
[22]	DING Ning, ZHU Yu, LIU Xinyan, et al. A modified social force model for crowd evacuation considering collision predicting behaviors[J]. *Appl Math Comput, 2024, 466*: 128448. doi: 10.1016/j.amc.2023.128448 URL
[23]	PENG Jingxuan, WEI Zhonghua, CHEN Yanyan, et al. Heterogeneous pedestrian simulation in commercial complexes: When attractive potential meets social force[J]. *IEEE Trans Intel Transport Syst*, 2025, 26(4): 5102-5119.
[24]	WANG Xuwei, LIU Tingting, LIU Zhen. Study on collision avoidance behavior in the social force-based pedestrian-vehicle interaction simulation model at unsignalized intersections[J]. *Appl Sci*, 2025, 15(9): 4885.
[25]	Chandra S, Bharti A K. Speed distribution curves for pedestrians during walking and crossing[J]. *Procedia-Social Beha Sci, 2013, 104*: 660-667.
[26]	CHEN Hao, ZHANG Xi. Path planning for intelligent vehicle collision avoidance of dynamic pedestrian using Att-LSTM, MSFM, and MPC at unsignalized crosswalk[J]. IEEE Trans Indu Elect, 2021, 69( 4): 4285-4295.
[27]	Rasouli A, Tsotsos J K. Autonomous vehicles that interact with pedestrians: A survey of theory and practice[J]. *IEEE Trans Intel Transport Syst*, 2019, 21(3): 900-918.
[28]	Rasouli A, Kotseruba I, Tsotsos J K. Understanding pedestrian behavior in complex traffic scenes[J]. *IEEE Transport Intel Vehi*, 2017, 3(1): 61-70.
[29]	Amini R E, Abouelela M, Dhamaniya A, et al. A game-theoretic approach for modelling pedestrian-vehicle conflict resolutions in uncontrolled traffic environments[J]. *Acci Anal Prev, 2024, 203*: 107604.

交互情况	车辆成本		行人成本
交互情况	安全	效率	安全	效率
减速	+2	-1	+2	-1
保持	-6	-2	-5	-3
加速	-10	+4	-8	+3

交互情况	车辆成本		行人成本
交互情况	安全	效率	安全	效率
减速	+2	-1	+2	-1
保持	-6	-2	-5	-3
加速	-10	+4	-8	+3

车辆速度，	N(8, 0.8) m/s
期望间隙接受度，t_gap	N(4.25, 0.8) s
最大加速度，v_max	4 m/s²
最小减速度，v_min	-4 m/s²
最大观测距离，d_obs	30 m
行人距离，d_p	3.5 m
期望间歇均值，μ_gap	2.5 s
期望间隙标准差，σ_gap	0.4 s
仿真时间步长，?t	0.1 s
仿真总时长，T	10 s

车辆速度，	N(8, 0.8) m/s
期望间隙接受度，t_gap	N(4.25, 0.8) s
最大加速度，v_max	4 m/s²
最小减速度，v_min	-4 m/s²
最大观测距离，d_obs	30 m
行人距离，d_p	3.5 m
期望间歇均值，μ_gap	2.5 s
期望间隙标准差，σ_gap	0.4 s
仿真时间步长，?t	0.1 s
仿真总时长，T	10 s

行人	方法	TTC均值/ s	CR / %	YR / %
	OAC	5.22	0.14	71.2
年轻人	MPC	2.73	1.57	59.2
	本文	3.98	0.07	47.7
中年人	OAC	5.45	0.11	72.3
	MPC	2.66	2.2	57.7
	本文	4.07	0.05	50.2
老年人	OAC	5.53	0.09	74.9
	MPC	2.92	1.67	56.3
	本文	4.22	0.02	49.1