Potential risk assessment of vision-occluded scenarios for autonomous vehicles

被引：0
作者：
Wang D.-G. [1 ]
Fu W.-P. [1 ,2 ]
Zhou J.-C. [1 ]
Gao Z.-Q. [1 ]
Song Q.-Y. [1 ]
机构：
[1] School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Shaanxi, Xi’an
[2] School of Engineering, Xi’an International University, Shaanxi, Xi’an
来源：
Kongzhi Lilun Yu Yingyong/Control Theory and Applications | 2023年 / 40卷 / 06期
基金：
中国国家自然科学基金;
关键词：
autonomous vehicles; knowledge graph; logical reasoning; potential risk assessment; Rayesian network;
D O I：
10.7641/CTA.2022.20178
中图分类号：
学科分类号：
摘要：
The autonomous vehicles safety is challenged by the potential risks arising from the visually occluded areas. A new method of potential risks assessment is put forward based on “Knowledge Graph + Logical Reasoning + Bayesian Reasoning” in the face of difficult to accurately and effectively predict and assess such potential risks, a potential risk prediction model and a potential risk probability inference model are constructed in the paper. The potential risk prediction model describes the interaction between driving entities by constructing the knowledge graph of urban scenarios for autonomous driving, and then infers whether there are potential risks during driving with SWI-Prolog inference engine after the description is semantic transformed; The potential risk probability reasoning model can quantify potential risks by inferring the probability of such risks replying on Bayesian Network. The field experiment prove that inference and assessment of potential risks conducted by the proposed method is similar to that conducted by human drivers, and can even compensate for human driver’s unawareness of potential risks. The method is applicable to complex urban traffic. The results of risk assessment have potential application value as they can provide effective basis for the behavioral decision-making of the automatic driving system. © 2023 South China University of Technology. All rights reserved.
引用
收藏
页码：1023 / 1033
页数：10
相关论文
共 21 条
  • [1] WANG J, HUANG H, LI Y, Et al., Driving risk assessment based on naturalistic driving study and driver attitude questionnaire analysis, Accident Analysis & Prevention, 145, (2020)
  • [2] ZHANG Jiaxu, ZHOU Shiying, SHI Zhengtang, Et al., Path planning and tracking control for corner overtaking of driverless vehicle using sliding mode technique with conditional integrators, Control Theory & Applications, 38, 2, pp. 197-205, (2021)
  • [3] YU M Y, VASUDEVAN R, JOHNSON R M., Occlusion-aware risk assessment for autonomous driving in urban environments, IEEE Robotics and Automation Letters, 4, 2, pp. 2235-2241, (2019)
  • [4] SCHRATTER M, BOUTON M, KOCHENDERFER M J, Et al., Pedestrian collision avoidance system for scenarios with occlusions, The 30th IEEE Intelligent Vehicles Symposium, pp. 1054-1060, (2019)
  • [5] LEFEVRE S, VASQUEZ D, LAUGIER C., A survey on motion prediction and risk assessment for intelligent vehicles, Robomech Journal, 1, 1, pp. 1-14, (2014)
  • [6] LI G, YANG Y, ZHANG T, Et al., Risk assessment based collision avoidance decision-making for autonomous vehicles in multiscenarios, Transportation Research Part C: Emerging Technologies, 122, (2021)
  • [7] BRECHTEL S, GINDELE T, DILLMANN R., Probabilistic decision-making under uncertainty for autonomous driving using continuous POMDPs, The 17th International IEEE Conference on Intelligent Transportation Systems, pp. 392-399, (2014)
  • [8] YU M Y, VASUDEVAN R, JOHNSON R M., Risk assessment and planning with bidirectional reachability for autonomous driving, International Conference on Robotics and Automation, pp. 5363-5369, (2020)
  • [9] SHANG Weichao, Research on identification and risk assessment of potential dangerous scenes on urban roads, (2021)
  • [10] ONDRUSKA P, POSNER I., Deep tracking: Seeing beyond seeing using recurrent neural networks, (2016)
123