The invention relates to an L3-level automatic driving vehicle driver trust degree evaluation method, which comprises the following steps: step 1, obtaining the driver trust degree of an automatic driving takeover experiment by introducing a subjective trust scale, and carrying out quantitative analysis on the subjective trust degree; step 2, grading the subjective credibility by adopting a K-means clustering method; step 3, extracting key frames of driving takeover; step 4, encoding the extracted driver state; and 5, establishing a driver trust degree evaluation method based on a Kalman filtering algorithm. The method can provide reference for objective real-time evaluation of the driver trust degree in the emergency takeover scene, and is beneficial to improving the safety and reliability of the automatic driving vehicle.
本发明涉及一种L3级自动驾驶车辆驾驶员信任度评估方法,包括如下步骤:步骤一、通过引入主观信任量表,获取自动驾驶接管实验的驾驶员信任度,对主观信任度进行量化分析;步骤二、采用K‑means聚类方法对主观信任度进行分级;步骤三、对驾驶接管的关键帧进行提取;步骤四、对提取的驾驶员状态进行编码;步骤五、建立基于卡尔曼滤波算法的驾驶员信任度评估方法。本发明能够为紧急接管场景下驾驶员信任度客观实时评估提供参考,有利于提高自动驾驶车辆的安全性与可靠性。
L3-level automatic driving vehicle driver trust degree evaluation method and system
L3级自动驾驶车辆驾驶员信任度评估方法及系统
2023-10-31
Patent
Electronic Resource
Chinese
L3-level automatic driving vehicle driver non-driving posture recognition method and system
European Patent Office | 2023
|Automatic driving vehicle driving safety degree quantification system
European Patent Office | 2023
|DRIVER-LESS AUTOMATIC DRIVING SYSTEM FOR VEHICLE, AND VEHICLE
European Patent Office | 2018
|Driver active intervention driving processing method for L3 + level automatic driving
European Patent Office | 2024
|Automatic driving mode takeover method, driver monitoring system and vehicle
European Patent Office | 2023
|