智能汽车显式沟通下的交互式行人穿行行为预测

doi:10.3901/JME.2023.08.151

机械工程学报 ›› 2023, Vol. 59 ›› Issue (8): 151-162.doi: 10.3901/JME.2023.08.151

扫码分享

智能汽车显式沟通下的交互式行人穿行行为预测

王永胜¹, 刘金鑫¹, 卜德旭¹, 江发潮², 罗禹贡¹

1. 清华大学车辆与运载学院北京 100084;
2. 中国农业大学工学院北京 100083

收稿日期:2022-03-10 修回日期:2022-12-15 出版日期:2023-04-20 发布日期:2023-06-16
通讯作者: 罗禹贡,男,1974年出生,博士,研究员,博士研究生导师。主要研究方向为智能网联电动车辆动力学及控制。E-mail:lyg@tsinghua.edu.cn
作者简介:王永胜，男， 1991 年出生，博士，博士后。主要研究方向为智能网联电动车辆定位系统的预期功能安全、动力学及控制。E-mail： wang_ysh@tsinghua.cn
基金资助:
国家重点研发计划(2022YFE0101000); 北京市科技计划(Z21100004221005)资助项目

Interactive Pedestrian Crossing Behavior Prediction under the Explicit Communication of Intelligent Vehicles

WANG Yong-sheng¹, LIU Jin-xin¹, BU De-xu¹, JIANG Fa-chao², LUO Yu-gong¹

1. School of Vehicle and Mobility, Tsinghua University, Beijing 100084;
2. College of Engineering, China Agricultural University, Beijing 100083

Received:2022-03-10 Revised:2022-12-15 Online:2023-04-20 Published:2023-06-16

摘要/Abstract

摘要： 室内停车场是“行人-智能汽车”（Pedestrian-intelligent vehicle,P-IV）产生交互的典型场景，针对P-IV交互过程中缺乏交互阶段的定量划分，提出行人穿行风险状态评估（Pedestrian crossingriskassessment,PCRA）模型，该模型依据行人与车辆运动之间的时空关联，将P-IV交互过程定量划分为四个阶段，并明确各阶段边界。针对缺乏探讨显式沟通信息对P-IV交互策略及行人预测的影响，首先基于PCRA模型预测行人的纵向可穿行范围，将其作为智能汽车向行人传递的动态显式沟通信息；然后分析显式沟通下的P-IV交互决策顺序，结合交互过程中行人穿行行为的关键特征量，依据模糊理论建立融合预测层与识别层的行人穿行行为预测模型。试验结果表明，PCRA模型能够准确评估行人穿行风险，定量预测行人的纵向可穿行范围；行人穿行行为预测的平均提前时间为0.46 s，达到有效预测效果。

关键词: 智能汽车, 行人穿行预测, 人车交互, 显式沟通, 风险评估

Abstract: Indoor parking lots are the typical scenario of pedestrian-intelligent vehicle（P-IV） interaction. Aiming at the lack of quantitative division of interaction stages in the P-IV interaction process, a pedestrian crossing risk assessment（PCRA） model is proposed. The model quantitatively divides the P-IV interaction process into four basic stages according to the spatiotemporal relationship between pedestrian motion and vehicle motion, and clarifies the boundaries of each stage. In view of the lack of exploring the influence of explicit communication information on P-IV interaction strategy and pedestrian prediction, the longitudinal available crossing range of pedestrians is firstly predicted based on the PCRA model, which is used as the dynamic and explicit communication information transmitted by intelligent vehicles to pedestrians. Then, the P-IV interactive decision-making sequence is analyzed under explicit communication. And combined with the key features of pedestrian crossing behavior in the interaction process, a pedestrian crossing behavior prediction model integrating prediction layer and recognition layer is established based on fuzzy theory. The experimental results show that the PCRA model can accurately assess the pedestrian crossing risk and quantitatively predict the longitudinal available crossing range of pedestrian; the average advance time of the pedestrian crossing behavior prediction is 0.46 s,which achieves an effective prediction effect.

Key words: intelligent vehicles, pedestrian crossing prediction, P-IV interaction, explicit communication, risk assessment

中图分类号:

U469

王永胜, 刘金鑫, 卜德旭, 江发潮, 罗禹贡. 智能汽车显式沟通下的交互式行人穿行行为预测[J]. 机械工程学报, 2023, 59(8): 151-162.

WANG Yong-sheng, LIU Jin-xin, BU De-xu, JIANG Fa-chao, LUO Yu-gong. Interactive Pedestrian Crossing Behavior Prediction under the Explicit Communication of Intelligent Vehicles[J]. Journal of Mechanical Engineering, 2023, 59(8): 151-162.

参考文献

[1] 王永胜,罗禹贡,黄晨,等. 基于拓扑地图的自主泊车路径协调与优化策略[J].中国公路学报,2021,34(1):177-187. WANG Yongsheng,LUO Yugong,HUANG Chen,et al. A topological map-based path coordination and optimization strategy for autonomous parking[J]. China Journal of Highway and Transport,2021,34(1):177-187.
[2] WANG P,MOTAMEDI S,QI S,et al. Pedestrian interaction with automated vehicles at uncontrolled intersections[J]. Transportation Research Part F:Traffic Psychology and Behaviour,2021,77:10-25.
[3] FAAS S M,MATHIS L A,BAUMANN M. External HMI for self-driving vehicles:Which information shall be displayed[J]. Transportation Research Part F:Traffic Psychology and Behaviour,2020,68:171-186.
[4] RIDEL D,REHDER E,LAUER M,et al. A literature review on the prediction of pedestrian behavior in urban scenarios[C]//2018 21st International Conference on Intelligent Transportation Systems (ITSC). New York:IEEE,2018:3105-3112.
[5] GHORI O,MACKOWIAK R,BAUTISTA M,et al. Learning to forecast pedestrian intention from pose dynamics[C]//2018 IEEE Intelligent Vehicles Symposium (IV). New York:IEEE,2018:1277-1284.
[6] BONNIN S,WEISSWANGE T H,KUMMERT F,et al. General behavior prediction by a combination of scenario-specific models[J]. IEEE Transactions on Intelligent Transportation Systems,2014,15(4):1478-1488.
[7] LIU B,ADELI E,CAO Z,et al. Spatiotemporal relationship reasoning for pedestrian intent prediction[J]. IEEE Robotics and Automation Letters,2020,5(2):3485-3492.
[8] VÖLZ B,BEHRENDT K,MIELENZ H,et al. A data-driven approach for pedestrian intention estimation[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). New York:IEEE,2016:2607-2612.
[9] NEOGI S,HOY M,DANG K,et al. Context model for pedestrian intention prediction using factored latent-dynamic conditional random fields[J]. IEEE Transactions on Intelligent Transportation Systems,2021,22(11):6821-6832.
[10] ZHANG H,LIU Y,WANG C,et al. Research on a pedestrian crossing intention recognition model based on natural observation data[J]. Sensors,2020,20(6):1776.
[11] WANG L K,LIU L,YU D M,et al. Pedestrian trajectory prediction in crossing scenario using fuzzy logic and switching Kalman filter[J]. The Journal of China Universities of Posts and Telecommunications,2018,25(6):31-43.
[12] KIM K,LEE Y K,AHN H,et al. Pedestrian intention prediction for autonomous driving using a multiple stakeholder perspective model[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). New York:IEEE,2020:7957-7962.
[13] RIDEL D A,DEO N,WOLF D,et al. Understanding pedestrian-vehicle interactions with vehicle mounted vision:An LSTM model and empirical analysis[C]//2019 IEEE Intelligent Vehicles Symposium (IV). New York:IEEE,2019:913-918.
[14] CAMARA F,MERAT N,FOX C W. A heuristic model for pedestrian intention estimation[C]//2019 IEEE Intelligent Transportation Systems Conference (ITSC). New York:IEEE,2019:3708-3713.
[15] MILLARD-BALL A. Pedestrians,autonomous vehicles,and cities[J]. Journal of Planning Education and Research,2018,38(1):6-12.
[16] CAMARA F,BELLOTTO N,COSAR S,et al. Pedestrian models for autonomous driving part II:High-level models of human behavior[J]. IEEE Transactions on Intelligent Transportation Systems,2021,22(9):5453-5472.
[17] KWAK J Y,KO B C,NAM J Y. Pedestrian intention prediction based on dynamic fuzzy automata for vehicle driving at nighttime[J]. Infrared Physics & Technology,2017,81:41-51
[18] SUCHA M,DOSTAL D,RISSER R. Pedestrian-driver communication and decision strategies at marked crossings[J]. Accident Analysis & Prevention,2017,102:41-50.
[19] CARMONA J,GUINDEL C,GARCIA F,et al. eHMI:Review and guidelines for deployment on autonomous vehicles[J]. Sensors,2021,21(9):2912.
[20] TABONE W,WINTER J D,ACKERMANN C,et al. Vulnerable road users and the coming wave of automated vehicles:Expert perspectives[J]. Transportation Research Interdisciplinary Perspectives,2021,9:1-16.
[21] 胡宏宇,刁小桔,高菲,等. 自动驾驶汽车-行人交互研究综述[J]. 汽车技术,2021,552(9):1-9. HU Hongyu,DIAO Xiaoju,GAO Fei,et al. Review of interaction between autonomous vehicles and pedestrians[J]. Automobile Technology,2021,552(9):1-9.
[22] ROUCHITSAS A,ALM H. External human-machine interfaces for autonomous vehicle-to-pedestrian communication:A review of empirical work[J]. Frontiers in Psychology,2019,10:2757.
[23] DEB S,STRAWDERMAN L J,CARRUTH D W. Investigating pedestrian suggestions for external features on fully autonomous vehicles:A virtual reality experiment[J]. Transportation Research Part F:Traffic Psychology and Behaviour,2018,59:135-149.
[24] LAGSTRÖM T,MALMSTEN LUNDGREN V. AVIP-autonomous vehicles' interaction with pedestrians-An investigation of pedestrian-driver communication and development of a vehicle external interface[D]. Gothenborg:Chalmers University of Technology,2016.
[25] NGUYEN T T,HOLLÄNDER K,HOGGENMUELLER M,et al. Designing for projection-based communication between autonomous vehicles and pedestrians[C]//Proceedings of the 11th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. New York:ACM,2019:284-294.
[26] LANZER M,BABEL F,YAN F,et al. Designing communication strategies of autonomous vehicles with pedestrians:An intercultural study[C]//12th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. New York:ACM,2020:122-131.
[27] 米奇克,瓦伦托维兹. 汽车动力学[M]. 4版. 北京:清华大学出版社,2009. MITSCHKE M,WALLENTO H. Vehicle dynamics[M]. 4th ed. Beijing:Tsinghua University Press,2009.
[28] CHENG G Z,LIU B T,WU L X,et al. Noncooperative dynamic game model between drivers and crossing pedestrians[J]. Advances in Mechanical Engineering,2015,7(1):359528.
[29] JAYARAMAN S K,CREECH C,TILBURY D M,et al. Pedestrian trust in automated vehicles:Role of traffic signal and AV driving behavior[J]. Frontiers in Robotics and AI,2019(6):117.
[30] 梅伟生,刘锋,魏韡. 工程博弈论基础及电力系统应用[M]. 北京:科学出版社,2016. MEI Weisheng,LIU Feng,WEI Wei. Engineering game fundamentals and power system application[M]. Beijing,Science Press,2016.

智能汽车显式沟通下的交互式行人穿行行为预测

Interactive Pedestrian Crossing Behavior Prediction under the Explicit Communication of Intelligent Vehicles

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	伍文广, 张斌, 胡林, 张志勇. 人车交互的行人过街方位概率动态预测模型[J]. 机械工程学报, 2024, 60(10): 48-50.
[2]	林晨, 何智成, 黄怡菲, 林智桂, 付广, 黄晋. 多级参数融合网络的驾驶场景目标检测方法研究[J]. 机械工程学报, 2024, 60(10): 64-75.
[3]	白先旭, 潘宇翔, 陈浩, 李维汉, 石琴. 智能网联汽车预期功能安全风险评估3σ接受准则[J]. 机械工程学报, 2024, 60(10): 182-191.
[4]	曾迪, 郑玲, 李以农, 杨显通. 自动驾驶奖励函数贝叶斯逆强化学习方法[J]. 机械工程学报, 2024, 60(10): 245-260.
[5]	彭湃, 耿可可, 王子威, 柳智超, 殷国栋. 智能汽车环境感知方法综述[J]. 机械工程学报, 2023, 59(20): 281-303.
[6]	胡文, 邓泽健, 张邦基, 曹东璞, 杨彦鼎, 曹恺, 李深. 密集交通场景下无人驾驶重卡换道决策规划方法[J]. 机械工程学报, 2023, 59(12): 332-342.
[7]	臧勇, 蔡英凤, 孙晓强, 徐兴, 陈龙, 王海. 基于可拓博弈的智能汽车轨迹跟踪协调控制方法研究[J]. 机械工程学报, 2022, 58(8): 181-194.
[8]	杨俊儒, 褚端峰, 陆丽萍, 王金湘, 吴超仲, 殷国栋. 智能汽车人机共享控制研究综述[J]. 机械工程学报, 2022, 58(18): 31-55.
[9]	韩嘉懿, 赵健, 朱冰. 面向智能汽车人机协同转向控制的强化学习变阻抗人机交互方法[J]. 机械工程学报, 2022, 58(18): 141-149.
[10]	张利鹏, 苏泰, 严勇. 基于采样区域优化的智能车辆轨迹规划方法[J]. 机械工程学报, 2022, 58(14): 276-287.
[11]	山彤欣, 王震坡, 洪吉超, 曲昌辉, 张景涵, 周洋捷, 侯岩凯. 新能源汽车动力电池“机械滥用-热失控”及其安全防控技术综述[J]. 机械工程学报, 2022, 58(14): 252-275.
[12]	孙文君, 刘志亮, 王佳鑫, 秦勇. 服役过程中高速列车动态损失定量分析方法[J]. 机械工程学报, 2021, 57(8): 221-229.
[13]	梁艺潇, 李以农, KHAJEPOUR Amir, 郑玲. 基于转向与主动横摆力矩协调的四轮驱动智能电动汽车路径跟踪控制[J]. 机械工程学报, 2021, 57(6): 142-155.
[14]	张志达, 郑玲, 李以农, 吴行, 余颖弘. 基于鲁棒自适应SCKF的智能汽车目标状态跟踪研究[J]. 机械工程学报, 2021, 57(20): 181-193.
[15]	张雷, 王子浩, 孙逢春, 王震坡. 四轮轮毂电机驱动智能电动汽车转向失效容错控制研究[J]. 机械工程学报, 2021, 57(20): 141-152.