路测环境下无人驾驶小巴复杂场景运行评价

doi:10.16097/j.cnki.1009-6744.2024.04.029

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (4): 300-310.DOI: 10.16097/j.cnki.1009-6744.2024.04.029

• 工程应用与案例分析 • 上一篇

路测环境下无人驾驶小巴复杂场景运行评价

马千里^a,b，王通^a，邵帅^a，贾鹏^*a,b

大连海事大学，a.综合交通运输协同创新中心；b.航运经济与管理学院，辽宁大连116026

收稿日期:2024-05-28 修回日期:2024-07-11 接受日期:2024-07-22 出版日期:2024-08-25 发布日期:2024-08-22
作者简介:马千里(1989- )，男，河南许昌人，副教授。
基金资助:
国家自然科学基金(72204034)；中国博士后科学基金 (2023M730457)；中央高校基本科研业务费 (3132023526)。

Evaluation of Driverless Minibus Operation in Complex Scenarios Under Road Test Environment

MAQianli^a,b,WANG Tong^a,SHAO Shuai^a,JIAPeng^*a,b

a. Collaborative Innovation Center for Transport Studies; b. School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, Liaoning, China

Received:2024-05-28 Revised:2024-07-11 Accepted:2024-07-22 Online:2024-08-25 Published:2024-08-22
Supported by:
National Natural Science Foundation of China(72204034)；China Postdoctoral Science Foundation (2023M730457)；The Fundamental Research Funds for the Central Universities (3132023526)。

摘要/Abstract

摘要： 以无人驾驶小巴为代表的客运自动驾驶工具在公交微循环中发挥着重要作用，为实现无人驾驶技术的商业化规模运用，除了传统的车辆性能测试外，还需评估其在复杂场景下的表现。由于测试数据缺乏，评价模型适用场景单一和评价方法主观等问题，导致以往评价偏差较大。本文针对无人驾驶小巴的表现构建综合评价体系，并在实测数据的基础上，采用博弈论组合赋权的优劣解距离法(Techniquefor Order Preference by Similarity to Ideal Solution, TOPSIS)模型，对车辆在复杂场景下的表现进行综合评价。选取驾驶安全性、乘坐舒适性、车辆智能性及车辆高效性这4个评价维度，并细分为12个客观评价指标。首先，通过实地测试采集无人驾驶小巴在运行场景中的数据；其次，利用基于博弈论的组合赋权法，对层次分析法和熵权法获得的权重进行组合；最后，为验证模型的有效性，运用TOPSIS模型对3条具有不同复杂度的测试路线进行综合评价值的计算。结果显示，无人驾驶小巴表现评价中，准则层的重要程度排序为车辆智能性、驾驶安全性、乘坐舒适性、车辆高效性，指标层敏感指标则为自动驾驶状态、平均角速度。基于博弈论组合赋权的TOPSIS模型对不同场景复杂度路线进行的无人驾驶小巴表现评价结果与实际运行情况一致，展示了方法的有效性。

关键词: 智能交通, 车辆评价, 实地测试, 自动驾驶, 组合赋权法

Abstract: Autonomous minibuses play an important role in the micro-circulation of public transportation. To achieve commercial application of autonomous driving technology, in addition to traditional vehicle performance tests, it is also necessary to evaluate their performance in complex scenarios. Due to the lack of test data, the limited applicability of evaluation models, and the subjectivity of evaluation methods, previous evaluations have shown significant biases. This study developed a comprehensive evaluation system for the performance of autonomous minibuses and conducted a comprehensive evaluation based on field test data using a TOPSIS model combined with game theory weighting. Four evaluation dimensions were selected: driving safety, ride comfort, vehicle intelligence, and vehicle efficiency, which were further divided into 12 objective evaluation indicators. First, data were collected through field tests in the operating scenarios of autonomous minibuses. Second, the game theory-based combined weighting method was used to combine the weights obtained from the analytic hierarchy process and the entropy weighting method. Finally, to verify the effectiveness of the model, the TOPSIS model was used to calculate the comprehensive evaluation values of three test routes with different complexity. The results show that in the performance evaluation of autonomous minibuses, the order of importance at the criterion level is vehicle intelligence, driving safety, driving comfort, and vehicle efficiency, while the sensitive indicators at the index level are autopilot state and average angular velocity. The results of the performance evaluation of autonomous minibuses on routes with different scenario complexities using the game theory based combined weighting TOPSIS model were consistent with the actual operating conditions, demonstrating the effectiveness of the method.

Key words: intelligent transportation, vehicle evaluation, field testing, autonomous driving, combined empowerment approach

中图分类号:

U467.1

马千里, 王通, 邵帅, 贾鹏. 路测环境下无人驾驶小巴复杂场景运行评价[J]. 交通运输系统工程与信息, 2024, 24(4): 300-310.

MAQianli, WANG Tong, SHAO Shuai, JIAPeng. Evaluation of Driverless Minibus Operation in Complex Scenarios Under Road Test Environment[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 300-310.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.04.029

http://www.tseit.org.cn/CN/Y2024/V24/I4/300

参考文献

[1]刘柯良,陈坚,邱智宣,等.城市路内违章停车时空特征及影响因素作用模型[J].交通运输系统工程与信息,2024,24(2):234-248. [LIUKL,CHENJ,QIUZX, etal.Spatio-temporalcharacterizationofurbanon-street illegal parkingandmodelingof role influencing factors [J]. Journal of TransportationSystemsEngineering and InformationTechnology,2024,24(2):234-248.]

[2] TIAN Q Y, WANG D Z W, LIN Y H. Optimal deployment of autonomous buses into a transit service network[J]. Transportation Research Part E: Logistics and Transportation Review, 2022, 165: 102865.

[3] BEAUCHAMP É, SAUNIER N, CLOUTIER M S. Study of automated shuttle interactions in city traffic using surrogate measures of safety[J]. Transportation Research Part C: Emerging Technologies, 2022, 135: 103465.

[4] ZHANG Y X, CHEN X M, ZHAO Y T, et al. A methodology for measuring the environmental effect of autonomous bus considering platooning[J]. Transportation Research Part D: Transport and Environment, 2022, 107: 103300.

[5] HABI H V, MESSER H. Recurrent neural network for rain estimation using commercial microwave links[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(5): 3672-3681.

[6]李茹,马育林,田欢,等.基于熵值和G1法的自动驾驶车辆综合智能定量评价[J]. 汽车工程,2020, 42(10): 1327-1334. [LI R, MA Y L, TIAN H. Comprehensive intelligent quantitative evaluation of autonomous vehicle based on entropy and G1 methods[J]. Automotive Engineering, 2020, 42(10): 1327-1334.]

[7]KOOPMAN P, WAGNER M. Autonomous vehicle safety: An interdisciplinary challenge[J]. IEEE Intelligent Transportation Systems Magazine, 2017, 9(1): 90-96.

[8]王荣,孙亚夫,宋娟.自动驾驶车辆道路测试场景评价方法与试验验证[J]. 汽车工程,2021, 43(4): 620-628. [WANG R, SUN Y F, SONG J. Evaluation method and test verification of road test scenes for autonomous vehicles[J]. Automotive Engineering, 2021, 43(4): 620 628.]

[9] 魏子茹,卢延辉,王鹏宇,等.基于CRITIC法的灰色关联理论在无人驾驶车辆测试评价中的应用[J].机械工程学报,2021, 57(12): 99-108. [WEI Z R, LU Y H, WANG P Y, et al. Application of grey correlation theory based on critic method in autonomous vehicles test and evaluation[J]. Journal of Mechanical Engineering, 2021, 57(12): 99-108.]

[10] 朱冰, 张培兴,刘斌,等.基于自然驾驶数据的自动驾驶汽车安全性评价方法[J].中国公路学报,2022,35 (7): 283-291. [ZHU B, ZHANG P X, LIU B, et al. Safety evaluation method of automated vehicle based on naturalistic driving data[J]. China Journal of Highway and Transport，2022, 35(7): 283-291.]

[11] 冯焕焕,邓建华,葛婷. 引入驾驶风格的熵权法多属性换道决策模型[J]. 交通运输系统工程与信息, 2020, 20(2): 139-144. [FENG H H, DENG J H, GE T. Multiattributes lane-changing decision model based on entropy weight with driving styles[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(2): 139-144.]

[12] ZHAO D, HUANG X, PENG H, et al. Accelerated evaluation of automated vehicles in car-following maneuver[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(3): 733-744.

[13] WANG X, ZHANG S, PENG H. Comprehensive safety evaluation of highly automated vehicles at the roundabout scenario[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 20873-20888.

[14] SUN C, CUI Y, DÀO N, et al. Medium-fidelity evaluation and modeling for perception systems of intelligent and connected vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(1): 1711-1721.

[1]	李哲, 苟杨扬, 李震尧, 李敖, 岑威, 高建平. 车联网公交系统动态时空优先控制研究[J]. 交通运输系统工程与信息, 2024, 24(5): 56-64.
[2]	刘淼淼, 刘晓晨, 朱明月, 魏泽平, 邓辉, 姚民坤, 吴思霖, 李昂, 石赞, 龚筱萸. 基于动态轨迹规划的自动驾驶车辆协同换道方法[J]. 交通运输系统工程与信息, 2024, 24(5): 65-78.
[3]	赵红专, 张继康, 潘佳雯, 袁泉, 许恩永, 魏金占, 周旦, 刘承堃. 基于改进视觉算法的自动驾驶风险预判模型[J]. 交通运输系统工程与信息, 2024, 24(5): 79-90.
[4]	胡正华, 周继彪, 毛新华, 张敏捷. 基于图像序列分析的城市道路交通事故预测[J]. 交通运输系统工程与信息, 2024, 24(5): 91-102.
[5]	刘东, 张大鹏, 万芸, 肖峰. 基于深度强化学习的单线路公交动态驻站控制策略研究[J]. 交通运输系统工程与信息, 2024, 24(5): 173-184.
[6]	刘美岐, 金楷然, 李雅澜, 郭戈. 城市道路智能网联车辆轨迹鲁棒控制方法[J]. 交通运输系统工程与信息, 2024, 24(4): 31-40.
[7]	温惠英, 张昕怡, 黄俊达, 许鹏鹏. 考虑动态交互作用的智能车辆轨迹预测[J]. 交通运输系统工程与信息, 2024, 24(4): 60-68.
[8]	魏书樵, 倪颖, 孙剑, 邱红桐. 基于生成对抗模仿学习的路段非机动车行为仿真[J]. 交通运输系统工程与信息, 2024, 24(4): 105-115.
[9]	赵朔, 奇格奇, 李培豪, 关伟. 基于脑电通道注意力机制的驾驶行为识别研究[J]. 交通运输系统工程与信息, 2024, 24(4): 283-291.
[10]	董红召, 杨嘉炜, 全程. 车联网下公交专用道复用的动态清空控制方法[J]. 交通运输系统工程与信息, 2024, 24(3): 12-20.
[11]	刘江, 张楚, 蔡伯根, 王剑, 陆德彪. 基于样本增强的列车卫星定位伪距欺骗检测方法[J]. 交通运输系统工程与信息, 2024, 24(3): 32-42.
[12]	李建市, 徐友春, 齐尧, 谢德胜, 李华. 起伏道路条件下无人车纵向速度控制方法研究[J]. 交通运输系统工程与信息, 2024, 24(3): 43-52.
[13]	张金雷, 杨健, 刘晓冰, 陈瑶, 杨立兴, 高自友. 基于计算机视觉的轨道交通站内火灾检测与定位[J]. 交通运输系统工程与信息, 2024, 24(3): 53-63.
[14]	陈喜群, 朱奕璋, 谢宁珂, 耿茂思, 吕朝锋. 基于异构多智能体自注意力网络的路网信号协调顺序优化方法[J]. 交通运输系统工程与信息, 2024, 24(3): 114-126.
[15]	辛琪, 王嘉琪, 杨文科, 徐猛, 袁伟. 信控路段混行交通生态驾驶深度强化学习模型[J]. 交通运输系统工程与信息, 2024, 24(3): 127-139.

路测环境下无人驾驶小巴复杂场景运行评价

Evaluation of Driverless Minibus Operation in Complex Scenarios Under Road Test Environment

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