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。
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.
L3级自动驾驶车辆驾驶员信任度评估方法及系统
20.06.2025
Patent
Elektronische Ressource
Chinesisch