基于本体和BN的无人车行为决策方法

doi:10.12305/j.issn.1001-506X.2021.02.20

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (2): 452-465.doi: 10.12305/j.issn.1001-506X.2021.02.20

基于本体和BN的无人车行为决策方法

孙雪^1,²(), 黄志球^1,^2,³(), 沈国华^1,^2,³(), 王金永^1,²(), 徐恒^1,²()

1. 南京航空航天大学计算机科学与技术学院, 江苏南京 211106
2. 南京航空航天大学高安全系统的软件开发与验证技术工业和信息化部重点实验室, 江苏南京 211106
3. 软件新技术与产业化协同创新中心, 江苏南京 210093

收稿日期:2019-12-24 出版日期:2021-02-01 发布日期:2021-03-16
作者简介:孙雪(1995-),女,硕士研究生,主要研究方向为BN、组件重要度、本体。E-mail:sunxue1217016581@163.com|黄志球(1965-),男,教授,博士研究生导师,博士,主要研究方向为软件工程、形式化方法、云计算。E-mail:zqhuang@nuaa.edu.cn|沈国华(1976-),男,副教授,硕士研究生导师,博士,主要研究方向为软件需求追踪、软件度量。E-mail:ghshen@nuaa.edu.cn|王金永(1983-),男,博士研究生,主要研究方向为同步系统的需求建模与安全性分析。E-mail:jinyongw@nuaa.edu.cn|徐恒(1994-),男,博士研究生,主要研究方向为无人系统的需求建模与可靠性分析。E-mail:xh971801361@163.com
基金资助:
国家自然科学基金(61772270);国家重点研发计划(2016YFB1000802)

Behavior decision method of autonomous vehicle based on ontology and BN

Xue SUN^1,²(), Zhiqiu HUANG^1,^2,³(), Guohua SHEN^1,^2,³(), Jinyong WANG^1,²(), Heng XU^1,²()

1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211016, China
2. Key Laboratory of Safety-Critical Software Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
3. Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210093, China

Received:2019-12-24 Online:2021-02-01 Published:2021-03-16

摘要/Abstract

摘要：

和高速交通环境比,城市交通环境具有更高的复杂性和不确定性,因此无人驾驶车辆行为决策系统要能给出驾驶场景下安全有效的驾驶动作。本文提出一种将本体语义表示与贝叶斯网络(Bayesian network, BN)概率推理相结合的行为决策模型。从驾驶场景中的多源异构信息和领域专家经验出发,建立本体并进行概率扩展,将其转换为BN,通过BN推理得到当前驾驶场景下的最佳驾驶动作。该方法既实现了驾驶场景领域知识的形式化描述和共享,又考虑到了驾驶场景中存在的不确定性。最后，通过Prescan/Simulink联合仿真实验验证了所提方法在无人驾驶车辆行为决策上的有效性。

关键词: 无人驾驶车辆, 行为决策, 本体, 贝叶斯网络, Prescan联合仿真

Abstract:

Compared with expressway traffic environment, urban traffic environment has higher complexity and uncertainty. Therefore, autonomous vehicles need behavior decision system to give safe and effective driving actions in driving scenarios. In this paper, a behavior decision model combined ontology semantic and probabilistic reasoning of Bayesian network (BN) is proposed. Based on the multi-source heterogeneous information and domain expert experience in autonomous driving scene, the ontology is establishd and carried out probability expansion to convert ontology to BN, which can obtain the best driving action in the current driving scene through BN. This method not only realizes the formal description and sharing of driving scene domain knowledge, but also takes into account the uncertainty in driving scene. Finally, the effectiveness of the proposed method in autonomous vehicle behavior decision is verified by Prescan/Simulink joint simulation experiment.

Key words: autonomous vehicle, behavior decision-making, ontology, Bayesian network(BN), Prescan joint simulation

中图分类号:

TP311

孙雪, 黄志球, 沈国华, 王金永, 徐恒. 基于本体和BN的无人车行为决策方法[J]. 系统工程与电子技术, 2021, 43(2): 452-465.

Xue SUN, Zhiqiu HUANG, Guohua SHEN, Jinyong WANG, Heng XU. Behavior decision method of autonomous vehicle based on ontology and BN[J]. Systems Engineering and Electronics, 2021, 43(2): 452-465.

图/表 26

图1

图2

表1

表2

图3

图4

图5

图6

图7

图8

图9

表3

图10

图11

图12

图13

图14

图15

图16

图17

图18

图19

图20

图21

图22

图23

参考文献 30

1	耿新力.城区不确定环境下无人驾驶车辆行为决策方法研究[D].合肥:中国科学技术大学, 2017.
	GENG X L. Research on decision-making method of autonomous vehicle behavior in uncertain environment of urban area[D]. Hefei: China University of Science and Technology, 2017.
2	GIPPS P G . A model for the structure of lane-changing decisions[J]. Transportation Research, 1986, 20 (5): 403- 414. doi: 10.1016/0191-2615(86)90012-3
3	GINDELE T, JAGSZENT D, PITZER B, et al. Design of the planner of team annieway's autonomous vehicle used in the darpa urban challenge[C]//Proc.of the Intelligent Vehicles Symposium, 2008: 1131-1136.
4	FURDA A , VLACIC L . Enabling safe autonomous driving in real-world city traffic using multiple criteria decision making[J]. Intelligent Transportation Systems, 2011, 3 (1): 4- 17.
5	AMAND A, FILLIAT D, GUZMAN J I. Ontology-based context awareness for driving assistance system[C]//Proc.of the Intelligent Vehicles Symposium, 2014: 227-233.
6	黄璐.基于本体论的无人驾驶车辆场景评估与行为决策方法研究[D].合肥:中国科学技术大学, 2019.
	HUANG L. Research on the method of the assessment and behavior decision-making of the autonomous vehicle based on ontology[D]. Hefei: China University of Science and Technology, 2019.
7	ULBRICH S, MAURER M. Towards tactical lane change behavior planning for automated vehicles[C]//Proc.of the 18th Intelligent Transportation System, 2015: 989-995.
8	BRECHTEL S. Dynamic-making in continuous partially obser-vable domains: a novel method and its application for autonomous driving[D]. Karlsruhe: Karlsruhe Institute of Technologies, 2015.
9	NOH S , AN K . Decision-making framework for automated driving in highway environments[J]. Transactions on Intelligent Transporation Systems, 2018, 19 (1): 58- 71. doi: 10.1109/TITS.2017.2691346
10	BOUTON M, COSGUN A, KOCHENDERF-ERE M J. Belief state planning for autonomously navigating urban intersections[C]//Proc.of the Intelligent Vehicles Symposium, 2017: 825-830.
11	SYZDYKBAYEV M, HAJARI H, KARIMI H A. Ontology for collaborative navigation among autonomous cars, drivers and pedestrians in smart cities[C]//Proc.of the 4th International Conference on Smart and Sustainable Technologies, 2019.
12	RON P , CRAIG S , STEPHEN B , et al. Ontology-based methods for enhancing autonomous vehicle path planning[J]. Robotics & Autonomous Systems, 2004, 49 (1): 123- 133.
13	YAO H F, WANG H J, LV H L, et al. Research on situation awareness based on ontology for UUV[C]//Proc.of the International Conference on Mechatronics and Automation, 2016: 2500-2506.
14	LU H, HUA W L, BIAO Y, et al. Ontology-based driving scene modeling, situation assessment and decision making for autonomous vehicles[C]//Proc.of the 4th Asia-Pacific Conference on Intelligent Robot Systems, 2019: 57-62.
15	WANG Q , AYALEW B , WEISKIRCHER T . Predictive maneuver planning for an autonomous vehicle in public highway traffic[J]. Transactions on Intelligent Transportation System, 2019, 20 (4): 1303- 1315. doi: 10.1109/TITS.2018.2848472
16	FERREIRA P H , LOUZADA F . Maximum likehood estimation for bivariate SUR Tobit modeling in presence of two right-censored dependent variables[J]. Communications in Statistics-Simulation and Computation, 2019, 48 (1): 150- 168. doi: 10.1080/03610918.2017.1375521
17	BALAKRISHNAN N , ALAM F M A . Maximum likelihood estimation of the parameters of a multiple step-stress model from the Birnbaum-Saunders distribution under time-constraint: a comparative study[J]. Communications in Statistics-Simulation and Computation, 2019, 48 (5): 1535- 1559. doi: 10.1080/03610918.2017.1414252
18	张什永.贝叶斯网不确定性推理研究[D].合肥:中国科学技术大学, 2010.
	ZHANG S Y. Research on Bayesian networks of uncertain reasoning[D]. Hefei: China Unversity of Science and Technology, 2010.
19	杨喜权, 曹雪亚, 国頔娜, 等. 基于贝叶斯网络的本体不确定性推理[J]. 计算机应用, 2008, 28 (5): 1170- 1172.
	YANG X Q , CAO X Y , GUO D N , et al. Ontology uncertainty reasoning based on bayesian networks[J]. Computer Application, 2008, 28 (5): 1170- 1172.
20	LARIK A S, HAIDER S. Efforts to blend ontology with Bayesian networks: an overview[C]//Proc.of the International Conference on Advanced Computer Theory and Engineering, 2010: 598-602.
21	IBERRAKEN D, ADOUANE L, DENIS D. Safe autonomous overtaking maneuver based on inter-vehicular distance prediction and multi-level Bayesian decision-making[C]//Proc.of the International Conference on Intelligent Transportation Systems, 2018: 3259-3265.
22	KIM B , PARK K , YI K . Probabilistic threat assessment with environment description and rule-based multi-traffic prediction for integrated risk management system[J]. Intelligent Transportation Systems, 2017, 9 (3): 8- 22.
23	XIN Z , WEN L Y . A Bayesian network approach to causation analysis of road accidents using netica[J]. Advanced Transportation, 2017, 42 (3): 464- 472.
24	UUSITALO L . Advantages and challenges of Bayesian networks in environmental modelling[J]. Ecological Modelling, 2007, 203 (3): 312- 318.
25	KIM K , KIM B , LEE B , et al. Design of integerated risk management-based dynamic driving control of automated vehicles[J]. Intelligent Transportation Systems, 2017, 9 (1): 57- 73.
26	IBERRAKEN D, ADOUANE L, DENIS D. Multi-level Bayesian decision-making for safe and flexible autonomous navigation in highway environment[C]//Proc.of the International Conference on Intelligent Robots and Systems, 2018: 3984-3990.
27	PEREYRA M . Revisiting maximum-a-posteriori estimation in log-concave models[J]. Society for Industrial and Applied Mathematics, 2019, 12 (1): 650- 670.
28	XIONG G M, LI H, DING Z L. Subjective evaluation of vehicle active safety using prescan and simulink: lane departure warning system as an example[C]//Proc.of the International Conference on Vehicular Electronics and Safety, 2017: 208-213.
29	孙忠潇. Simulink仿真及代码生成技术入门到精通[M]. 北京: 北京航空航天大学出版社, 2015: 140- 152.
	SUN Z X . Simulation code generation technology from introduction to mastery[M]. Beijing: Beijing University of Aeronautics and Astronautics Press, 2015: 140- 152.
30	CHEN X M, MIAO Y S, JIN M, et al. Driving decision-making analysis of lane-changing for autonomous vehicle under complex urban environment[C]//Proc.of the 29th Chinese Control and Decision Conference, 2017: 6878-6883.

属性名	定义域	值域
在车道上	自身车辆类	车道类
有左车道	车道类	车道类
有障碍物	障碍物类	自身车辆类
有左车道线	车道类	车道线类
执行驾驶行为	车辆类	行为类
左前方障碍物	自身车辆类	障碍物类
有道路标志	车道类	道路标志类

属性名	定义域	值域
当前速度	自身车辆类	双精度浮点型
可以左变道	自身车辆类	布尔型
车道数量	车道类	双精度浮点型
车道线类型	车道线类	字符型
与障碍物的距离	障碍物	双精度浮点型
与路口的距离	路口	双精度浮点型
与障碍物的相对速度	障碍物	双精度浮点型

节点	节点含义
车道	道路车道数
车道线	道路线情况
障碍物	周围有无障碍车辆
左车道	车辆在左车道行驶
右车道	车辆在右车道行驶
前方车辆	无人驾驶车辆前方车辆可能采取的驾驶动作
右前方车辆	无人驾驶车辆右前方车辆可能采取的驾驶动作
右后方车辆	无人驾驶车辆右后方车辆可能采取的驾驶动作
自身车辆	无人驾驶车辆与周围车辆的相对速度和相对距离
横向行为	无人驾驶车辆可能采取的横向驾驶动作
纵向行为	无人驾驶车辆可能采取的纵向驾驶动作

[1]	刘满, 张宏军, 徐有为, 冯欣亮, 冯玉芳. 群队级兵棋实体智能行为决策方法研究[J]. 系统工程与电子技术, 2022, 44(8): 2562-2569.
[2]	罗弋洋, 赵青松, 李华超, 李勇, 孙建彬. 武器装备运用知识框架及建模方法[J]. 系统工程与电子技术, 2022, 44(3): 841-849.
[3]	庞维建, 李辉, 黄谦, 李朋, 马贤明. 基于本体的无人系统任务规划研究综述[J]. 系统工程与电子技术, 2022, 44(3): 908-920.
[4]	王姝婷, 刘晓冰, 周军华, 白朝阳, 翟翔. 基于本体的复杂产品维修工程案例知识表示及重用方法[J]. 系统工程与电子技术, 2022, 44(2): 557-568.
[5]	李懿凡, 钱华明, 黄洪钟, 张庭瑜, 黄土地. 基于广义连续时间贝叶斯网络的指挥控制网络系统可靠性分析[J]. 系统工程与电子技术, 2022, 44(12): 3880-3886.
[6]	王鹏, 孙紫荆, 张帆, 肖国松. 考虑概率型共因失效的多阶段任务系统可靠性分析模型[J]. 系统工程与电子技术, 2022, 44(12): 3887-3898.
[7]	乔殿峰, 梁彦, 马超雄, 杨心语, 汪冕, 李建国. 多域作战下的群目标意图识别与预测[J]. 系统工程与电子技术, 2022, 44(11): 3403-3412.
[8]	刘延钊, 黄志球, 沈国华, 王金永, 徐恒. 基于决策树和BN的自动驾驶车辆行为决策方法[J]. 系统工程与电子技术, 2022, 44(10): 3143-3154.
[9]	赵禄达, 王斌. 基于RS-DBN的电子对抗目标清单生成方法[J]. 系统工程与电子技术, 2021, 43(9): 2373-2382.
[10]	陈洪转, 赵爱佳, 李腾蛟, 蔡匆聪, 程硕, 徐春丽. 基于故障树的复杂装备模糊贝叶斯网络推理故障诊断[J]. 系统工程与电子技术, 2021, 43(5): 1248-1261.
[11]	赵长啸, 李浩, 董磊, 王鹏. 基于STPA-Bayes模型的机载平视显示系统安全性分析与评价[J]. 系统工程与电子技术, 2020, 42(5): 1083-1092.
[12]	曾强, 黄政, 魏曙寰. 融合专家先验知识和单调性约束的贝叶斯网络参数学习方法[J]. 系统工程与电子技术, 2020, 42(3): 646-652.
[13]	孟光磊, 周铭哲, 朴海音, 张慧敏. 基于协同战术识别的双机编队威胁评估方法[J]. 系统工程与电子技术, 2020, 42(10): 2285-2293.
[14]	孙海文, 谢晓方, 孙涛, 张龙杰. 小样本数据缺失状态下DBN舰艇编队防空目标威胁评估方法[J]. 系统工程与电子技术, 2019, 41(6): 1300-1308.
[15]	吕学志, 胡晓峰, 吴琳, 贺筱媛. 基于改进竞争性假设分析的战役企图分析方法[J]. 系统工程与电子技术, 2019, 41(3): 555-563.

基于本体和BN的无人车行为决策方法

Behavior decision method of autonomous vehicle based on ontology and BN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 26

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价