Application of Scenario Complexity Evaluation in Trajectory Prediction and Automated Driving Decision-Making

被引：0

作者：

Li, Daofei ^{[1
]}

Pan, Hao ^{[1
]}

机构：

[1] Institute of Power Machinery and Vehicular Engineering, Zhejiang University, Hangzhou

来源：

Qiche Gongcheng/Automotive Engineering | 2024年 / 46卷 / 09期

关键词：

autonomous driving decision making; graph model; scenario complexity; trajectory prediction; vehicle-in-the-loop experiment;

D O I：

10.19562/j.chinasae.qcgc.2024.09.003

中图分类号：

学科分类号：

摘要：

The evaluation of scenario complexity is crucial for improving adaptability and flexibility of au⁃ tonomous vehicles in coping with complex environments and enhancing the applicability of the algorithms. A graph-based algorithm for evaluating scenario complexity is developed in this paper ，which fully considers interactive to⁃ pology and categorizes traffic scenarios into three complexity levels. The reasonability and effectiveness are validat⁃ ed in ramp merging scenarios. To demonstrate its scalability，the evaluation algorithm is applied in the development of the trajectory prediction and decision-making algorithms of automated driving. The proposed algorithms are then tested using natural driving datasets and vehicle-in-the-loop experiments. The results indicate that scenario complex⁃ ity evaluation enables early estimation of prediction uncertainty，enhances the real-time and optimality of decision-making algorithms. In data replay tests，the complexity assessment module can reduce the failure rate and collision rate during lane merging by approximately 38% and 92%，respectively，indicating promising application prospects. © 2024 SAE-China. All rights reserved.

引用

页码：1556 / 1563

页数：7

共 18 条

[1] SEMNANI S H, LIU H, EVERETT M，, Et al., Multi−agent motion planning for dense and dynamic environments via deep reinforce⁃ ment learning［J］, IEEE Robotics and Automation Letters, 5, 2, pp. 3221-3226, (2020)
[2] XIAO T., Research on the path planning and the tracking control algorithm of the intelligent vehicle in complex environment［D］, (2019)
[3] LU M M., Predictive control of mutil−agent formation with dynam⁃ ic constraints in complex environment［D］, (2020)
[4] CHEN Y., Motion planning of autonomous vehicles in complex en⁃ vironment based on reinforcement learning［D］, (2020)
[5] Mental workload when driving in a simulator：effects of age and driving complexity［J］, Accident Analysis & Prevention, 41, 4, (2009)
[6] HE Y., Test scenario generation and optimiza⁃ tion technology for intelligent driving systems［J］, IEEE Intelli⁃ gent Transportation Systems Magazine, 14, 1, (2022)
[7] LIU Y, HANSEN J H L., Towards complexity level classification of driving scenarios using environmental information［C］, 2019 IEEE Intelligent Transportation Systems Conference （ITSC）, pp. 810-815, (2019)
[8] ZHANG H C., Research on complexity of road traffic environment based on gravity model［D］, (2016)
[9] CHENG Y, Et al., Traffic risk environment im⁃ pact analysis and complexity assessment of autonomous vehicles based on the potential field method［J］, International Journal of Environmental Research and Public Health, 19, 16, (2022)
[10] Dynamic driving environment complex⁃ ity quantification method and its verification［J］, Transportation Research Part C：Emerging Technologies, 127, (2021)

← 1 2 →