| 引用本文: | 马艳丽,范璐洋,吕天玲,郭琳.车辆运行风险贝叶斯网络量化分级方法[J].哈尔滨工业大学学报,2020,52(3):33.DOI:10.11918/201810126 |
| MA Yanli,FAN Luyang,Lü Tianling,GUO Lin.Quantification classification method for driving risk quantization using Bayesian network[J].Journal of Harbin Institute of Technology,2020,52(3):33.DOI:10.11918/201810126 |
|
| 摘要: |
| 为评估自然驾驶过程中车辆运行存在的交通风险,采用贝叶斯网络对车辆运行风险进行量化研究. 首先开展自然驾驶试验,获取车辆距离控制指标、加速度、方向盘转向熵车辆控制数据及驾驶人视线转移时间、扫视速度、眨眼频率眼动数据. 然后,分析了各项指标的风险概率,确定各项指标阈值对应风险等级. 最后,构建了基于贝叶斯网络的车辆运行风险评估模型,给出了风险量化分级方法,确定了车辆运行风险等级,并对模型进行了敏感性分析. 结果表明:基于车辆控制和眼动表征的贝叶斯网络模型能够有效地对驾驶过程中车辆运行风险进行定量评估. 研究结果可评估自然驾驶过程中的车辆运行风险,并为运行风险进行量化分级. |
| 关键词: 交通工程 运行风险 贝叶斯网络 量化分级 自然驾驶 |
| DOI：10.11918/201810126 |
| 分类号:U491 |
| 文献标识码:A |
| 基金项目:国家重点基础研究发展计划(2017YFC0803901); 国家自然科学基金(51108136) |
|
| Quantification classification method for driving risk quantization using Bayesian network |
|
MA Yanli1,FAN Luyang1,2,Lü Tianling3,GUO Lin3
|
|
(1. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China; 2. Power China Chengdu Engineering Corporation Limited, Chengdu 610072, China; 3. Heilongjiang Administration of Work Safety, Harbin 150040, China)
|
| Abstract: |
| In order to evaluate the risk in the process of natural driving, Bayesian network was used to carry out quantitative research on driving risk. First, natural driving test was conducted to obtain the vehicle control data of vehicle spacing, acceleration, and steering entropy, as well as the eye movement data, including the driver’s sight transfer time, saccade speed, and blink frequency. Then, the risk rule of each index data was analyzed, and the risk level threshold of each index was determined. Finally, a vehicle operation risk assessment model based on Bayesian network was constructed, and the risk quantification classification method was proposed. The risk level of vehicle operation was determined, and the sensitivity of the model was analyzed. Results show that the Bayesian network model based on vehicle control and eye movement characterization could effectively conduct quantitative evaluation of driving risk in the driving process. The research results can provide theoretical and technical support for driving risk assessment and early warning in the natural driving process. |
| Key words: traffic engineering driving risk Bayesian network quantification classification natural driving |
