基于大语言模型的智能汽车仿真测试

doi:10.19562/j.chinasae.qcgc.2025.04.001

Abstract

Abstract:

In this paper a simulation testing method for intelligent vehicle based on a large language model is proposed to address the issues of heavy reliance on human resources and prominent efficiency bottlenecks in existing scenario based testing methods. Firstly， a simulation testing architecture for intelligent vehicle based on a large language model is designed， and corresponding data and simulation layers are established. On this basis， an intelligent car simulation testing process based on a large language model is constructed. Knowledge mining， model fine-tuning， and knowledge base enhancement retrieval application processes are designed for knowledge question answering tasks. Application paths for scenario type analysis， scenario element generation， and scenario toolchain invocation are designed for scenario generation tasks. For testing and evaluation tasks， a comprehensive application framework for testing scenario analysis， evaluation system construction， and simulation testing execution is designed. Finally， each task is tested. The results show that the testing method proposed in this paper can effectively solve different types of testing tasks and improve testing efficiency.

Key words: intelligent vehicle, simulation testing, large language model, scenario generation, automatic testing

Bing Zhu,Rui Tang,Jian Zhao,Peixing Zhang,Wenxu Li,Jiasheng Li,Xuefeng Xu. Virtual Simulation Testing Method for Intelligent Vehicle Based on Large Language Model[J].Automotive Engineering, 2025, 47(4): 587-597.

Figures/Tables 15

References 28

1	崔明阳，黄荷叶，许庆，等.智能网联汽车架构、功能与应用关键技术［J］.清华大学学报（自然科学版），2022，62（3）：493-508.
	CUI Mingyang， HUANG Heye， XU Qing， et al. Survey of intelligent and connected vehicle technologies： architectures， functions and applications［J］. Journal of Tsinghua University （Science and Technology）， 2022， 62（3）： 493-508.
2	朱冰，张培兴，赵健，等.基于场景的自动驾驶汽车虚拟测试研究进展［J］.中国公路学报，2019，32（6）：1-19.
	ZHU B， ZHANG P X， ZHAO J， et al. Review of scenario-based virtual validation methods for automated vehicles［J］. China Journal of Highway and Transport， 2019， 32（6）： 1-19.
3	ZHAO W X， ZHOU K， LI J， et al. A survey of large language models［J］. arXiv preprint arXiv：， 2023.
4	WEN L， FU D， LI X， et al. Dilu： a knowledge-driven approach to autonomous driving with large language models［J］. arXiv preprint arXiv：， 2023.
5	SHAO H， HU Y， WANG L， et al. Lmdrive： closed-loop end-to-end driving with large language models［J］. arXiv preprint arXiv：， 2023.
6	LIU X， JI K， FU Y， et al. P-tuning v2： prompt tuning can be comparable to fine-tuning universally across scales and tasks［J］. arxiv preprint arxiv：， 2021.
7	YANG J， JIN H， TANG R， et al. Harnessing the power of LLMs in practice： a survey on ChatGPT and beyond［J］. ACM Transactions on Knowledge Discovery from Data， 2024， 18（6）： 1-32.
8	MENZEL T， BAGSCHIK G， MAURER M. Scenarios for development， test and validation of automated vehicles［C］. 2018 IEEE Intelligent Vehicles Symposium （IV）. IEEE， 2018： 1821-1827.
9	International Organization for Standardization. Road vehicles－test scenarios for automated driving systems-vocabulary：ISO 34501：2022 ［S］. Geneva： ISO， 2022.
10	CORSO A， DU P， DRIGGS-CAMPBELL K， et al. Adaptive stress testing with reward augmentation for autonomous vehicle validatio［C］. 2019 IEEE Intelligent Transportation Systems Conference （ITSC）. IEEE， 2019： 163-168.
11	朱冰，汤瑞，赵健，等.基于代理遗传优化的智能驾驶系统加速测试方法［J］.同济大学学报（自然科学版），2024，52（4）：501-511.
	ZHU B， TANG R， ZHAO J， et al. Accelerated test method of intelligent driving system based on surrogate genetic optimization model ［J］. Journal of Tongji University （Natural Science）， 2024， 52（4）： 501-511.
12	ZHU B， ZHANG P， ZHAO J， et al. Hazardous scenario enhanced generation for automated vehicle testing based on optimization searching method［J］. IEEE Transactions on Intelligent Transportation Systems， 2021， 23（7）： 7321-7331.
13	方培俊，蔡英凤，陈龙，等. 基于车辆动力学混合模型的智能汽车轨迹跟踪控制方法［J］. 汽车工程， 2022， 44（10）： 1469-1483.
	FAHG P J， CAI Y F， CHEN L， et al. Trajectory tracking control method for intelligent vehicles based on a hybrid vehicle dynamics model ［J］. Automotive Engineering， 2022， 44（10）： 1469-1483.
14	ZHU B， SUN Y， ZHAO J， et al. Millimeter-wave radar in-the-loop testing for intelligent vehicles［J］. IEEE Transactions on Intelligent Transportation Systems， 2021， 23（8）： 11126-11136.
15	赵树廉，来飞，李克强，等. 基于数字孪生技术的智能汽车测试方法研究［J］. 汽车工程， 2023， 45（1）： 42-51.
	ZHAO S L， LAI F， LI K Q， et al. Research on intelligent vehicle test methods based on digital twin technology ［J］. Automotive Engineering， 2023， 45 （1）： 42-51.
16	陈君毅，李如冰，邢星宇，等. 自动驾驶车辆智能性评价研究综述［J］. 同济大学学报（自然科学版）， 2019， 47（12）： 1785-1790，1824.
	CHEN J Y， LI R B， XING X Y， et al. Survey on intelligence evaluation of autonomous vehicles［J］. Journal of Tongji University （Natural Science）， 2019， 47（12）： 1785-1790，1824.
17	朱冰，范天昕，张培兴，等.智能网联汽车标准化建设进程综述［J］.汽车技术，2023（7）：1-16.
	ZHU B， FAN T X， ZHANG P X， et al. Review of the standardization construction process of intelligent connected vehicles ［J］. Automotive Technology， 2023 （7）： 1-16.
18	胡大林，何丰，薛晓卿，等. 自动驾驶车辆模拟仿真测试平台技术要求： T/CMAX 121—2019［S］. 北京：中关村智通智能交通产业联盟， 2019.
	HU D L， HE F， XUE X Q， et al. Technical requirement for automatic driving vehicle simulation test platform in Beijing： T/CMAX 121—2019［S］. Beijing： CMAX， 2019.
19	International Organization for Standardization. Road vehicles－test scenarios for automated driving systems－scenario based safety evaluation framework：ISO 34502：2022 ［S］. Geneva： ISO， 2022.
20	中国汽车工程学会. 智能网联汽车V2X系统预警应用功能测试与评价方法： T/CSAE 246—2022［S］. 北京：中国汽车工程学会， 2022.
	China-SAE. Functional test and evaluation method of V2X system warning application of intelligent connected vehicle： T/CSAE 246—2022［S］. Beijing： China-SAE， 2022.
21	中国汽车工程学会. 《智能网联汽车激光雷达感知评测要求及方法》标准立项［EB/OL］. （2021-07-14）［2022-12-01］. http：//www.caicv.org.cn/index.php/newsInfo？id=381.
	China-SAE. Technical requirement and testing method of intelligent connected vehicle lidar perception standard project establishment［EB/OL］. （2021-07-14）［2022-12-01］. http：//www.caicv.org.cn/index.php/newsInfo？id=381.
22	International Organization for Standardization. Road vehicles－functional safety：ISO26262：2018 ［S］. Geneva： ISO， 2018.
23	International Organization for Standardization. Road vehicles－safety of the intended functionality：ISO21448：2018 ［S］. Geneva： ISO， 2018.
24	DOSOVITSKIY A， ROS G， CODEVILLA F， et al. CARLA： An open urban driving simulator［C］. Conference on Robot Learning. PMLR， 2017： 1-16.
25	LUO H， TANG Z， PENG S， et al. ChatKBQA： a generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models［J］. arXiv preprint arXiv：， 2023.
26	ZENG A， LIU X， DU Z， et al. GLM-130B： an open bilingual pre-trained model［J］. arXiv preprint arXiv：， 2022.
27	BAI J， BAI S， CHU Y， et al. Qwen technical report［J］. arXiv preprint arXiv：， 2023.
28	OUYANG L， WU J， JIANG X， et al. Training language models to follow instructions with human feedback［J］. Advances in Neural Information Processing Systems， 2022， 35： 27730-27744.

序号	主车速度/（km·h^-1）	两车间距/m	降雨强度/（mm·h^-1）
1	65	45	0
2	80	25	60
3	35	35	40
4	40	55	100
5	50	20	80
6	70	50	20
7	20	30	40
8	60	60	0
9	75	40	80
10	30	25	60
11	55	35	20
12	45	25	60
13	25	50	80

生成方式	知识索引成功率	要素设计成功率	场景生成成功率	场景需求满足率
覆盖性需求-A	96.0%	93.8%	94.4%	100%
关键性需求-A	96.0%	93.8%	82.2%	100%
覆盖性需求-B		86.0%	77.9%	7.5%
关键性需求-B		86.0%	15.1%	11.2%

AEB算法	知识索引成功率	仿真执行成功率	结果评价成功率	报告生成成功率
雷达测距	96.0%	91.3%	93.2%	80.0%
相机测距	94.0%	92.3%	94.7%	82.0%

[1]	Xianghao Meng,Ling Niu,Junqiang Xi,Danni Chen,Chao Lü. Risk Prediction of Heterogeneous Traffic Participants Based on Spatio-Temporal Graph Neural Networks [J]. Automotive Engineering, 2024, 46(9): 1537-1545.
[2]	Xiujian Yang,Yongrui Bai. Trajectory Planning for Intelligent Vehicle in Dynamic Unstructured Environment Based on the Graph Search and Optimization Methods [J]. Automotive Engineering, 2024, 46(9): 1564-1575.
[3]	Jing Zhao,Hao Liang,Tianxiao Xu,Yayue Xiao,Bowen Jiang. Research on Domain Specific Modeling Language for Intelligent Vehicle Cyber-Physical System [J]. Automotive Engineering, 2024, 46(8): 1370-1381.
[4]	Jialiang Zhu,Qiaobin Liu,Fan Yang,Lu Yang,Weihua Li. Two-Dimensional Collision Risk Prediction for Intelligent Vehicles Considering the Influence of Heterogeneous Vehicle Types [J]. Automotive Engineering, 2024, 46(8): 1414-1421.
[5]	Xiaolin Fan,Xudong Zhang,Yuan Zou,Xin Yin,Yingqun Liu. A Mapping and Planning Method Based on Simplified Visibility Graph [J]. Automotive Engineering, 2024, 46(7): 1249-1258.
[6]	Shuen Zhao,Sheng Wang,Yao Leng. Multi-objective Explicit Model Predictive Control for Intelligent Vehicle Trajectory Tracking [J]. Automotive Engineering, 2024, 46(5): 784-794.
[7]	Bing Zhu,Yinzi Huang,Jian Zhao,Peixing Zhang,Jingwei Xue. A Criticality Assessment Model for the Intelligent Vehicle Test Scenario Based on the Onboard Camera Images [J]. Automotive Engineering, 2024, 46(4): 557-563.
[8]	Ting Chikit,Yafei Wang,Yichen Zhang,Mingyu Wu,Yile Wang. Energy-Saving Planning Method for Autonomous Driving Mining Trucks Based on Composite Dynamic Sampling [J]. Automotive Engineering, 2024, 46(4): 588-595.
[9]	Wenxuan Shen,Rui Dai,Puyuan Tan,Qing Zhou. A Review of Reclined Occupant Crash Injuries and Impact Protection [J]. Automotive Engineering, 2024, 46(12): 2241-2256.
[10]	Zhongjie Liu,Zhiguo Zhao,Qin Yu. Vehicle Assisted Driving Behavior Decision-Making Based on Dynamic Risk Assessment [J]. Automotive Engineering, 2024, 46(11): 2005-2016.
[11]	Hongmao Qin,Shu Jiang,Tiantian Zhang,Heping Xie,Yougang Bian,Yang Li. Path Tracking Control of Intelligent Vehicle Based on Learning Model Predictive Control [J]. Automotive Engineering, 2024, 46(10): 1804-1815.
[12]	Zhong Zhang,Xiaojian Wu,Huihua Jiang,Chao Zhang,Yukang Wan. Model Predictive Anti-disturbance Control for Longitudinal Motion of Intelligent Vehicles Under Multi-source Disturbances [J]. Automotive Engineering, 2024, 46(10): 1816-1828.
[13]	Junhui Zhang,Xiaoman Guo,Yuxi Liu,Mingqiang Zheng,Yuhan Qian,Yuxuan Ding. Driver-Automation Shared Lane-Keeping Robust Control [J]. Automotive Engineering, 2024, 46(10): 1853-1862.
[14]	Jianping Hao,Yanzhao Su,Zhihua Zhong,Jin Huang. Service-Oriented Architecture and Service Scheduling Mechanism for Intelligent Vehicles [J]. Automotive Engineering, 2023, 45(9): 1563-1572.
[15]	Gaoshi Zhao,Long Chen,Yingfeng Cai,Yubo Lian,Hai Wang,Qingchao Liu,Chenglong Teng. Trajectory Prediction Technology Integrating Complex Network and Memory-Augmented Network [J]. Automotive Engineering, 2023, 45(9): 1608-1616.

Virtual Simulation Testing Method for Intelligent Vehicle Based on Large Language Model

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 28

Related Articles 15

Metrics

Comments

Recommended 0

序号	主车速度/（km·h^-1）	两车间距/m	降雨强度/（mm·h^-1）
1	65	45	0
2	80	25	60
3	35	35	40
4	40	55	100
5	50	20	80
6	70	50	20
7	20	30	40
8	60	60	0
9	75	40	80
10	30	25	60
11	55	35	20
12	45	25	60
13	25	50	80

序号	主车速度/（km·h^-1）	两车间距/m	降雨强度/（mm·h^-1）
1	65	45	0
2	80	25	60
3	35	35	40
4	40	55	100
5	50	20	80
6	70	50	20
7	20	30	40
8	60	60	0
9	75	40	80
10	30	25	60
11	55	35	20
12	45	25	60
13	25	50	80

序号	主车速度/（km·h^-1）	两车间距/m	降雨强度/（mm·h^-1）
1	65	45	0
2	80	25	60
3	35	35	40
4	40	55	100
5	50	20	80
6	70	50	20
7	20	30	40
8	60	60	0
9	75	40	80
10	30	25	60
11	55	35	20
12	45	25	60
13	25	50	80