Xu Bin, Zhou Hang, Zhou Yuanlong, Wang Yunhao, Li Zhen
School of Automobile, Chang'an University, Xi'an 710064, China.
Sensors (Basel). 2025 Sep 5;25(17):5529. doi: 10.3390/s25175529.
With the development of technology, comfort has gradually developed into the main criterion for evaluating intelligent vehicle performances. In this study, a field test was carried out under five common driving conditions, and 60 participants took part. Passenger posture data, vehicle motion data and passenger subjective comfort data were collected. A paired sample T-test and a ridge regression algorithm were used to explore the relationship between passenger posture swing parameters and subjective comfort. The results show that under the same driving conditions, the speed of posture swing was significantly higher for passengers who experienced discomfort. Furthermore, we found that the change in angular velocity was the main cause of passenger discomfort under different driving conditions. This suggested that the design of intelligent vehicle algorithms should focus on the angular velocity variation among passengers. Finally, based on traditional machine learning algorithms and deep learning algorithms, this paper establishes two models for predicting comfort through passenger posture instability. The accuracy of the machine learning model in predicting passenger comfort was 87.1%, while that for the deep learning model was 89%. The findings are useful in providing a theoretical basis for improving the comfort of intelligent vehicles.
随着技术的发展，舒适性已逐渐发展成为评估智能汽车性能的主要标准。在本研究中，在五种常见驾驶条件下进行了现场测试，60名参与者参与其中。收集了乘客姿势数据、车辆运动数据和乘客主观舒适度数据。使用配对样本T检验和岭回归算法来探索乘客姿势摆动参数与主观舒适度之间的关系。结果表明，在相同驾驶条件下，感到不适的乘客姿势摆动速度明显更高。此外，我们发现角速度的变化是不同驾驶条件下乘客不适的主要原因。这表明智能车辆算法的设计应关注乘客之间的角速度变化。最后，基于传统机器学习算法和深度学习算法，本文建立了两个通过乘客姿势不稳定性预测舒适度的模型。机器学习模型预测乘客舒适度的准确率为87.1%，而深度学习模型的准确率为89%。这些发现有助于为提高智能车辆的舒适性提供理论依据。
