School of Automobile, Chang'an University, Xi'an 710064, China.
Int J Environ Res Public Health. 2020 Sep 18;17(18):6821. doi: 10.3390/ijerph17186821.
Comfort is a significant factor that affects passengers' choice of autonomous vehicles. The comfort of an autonomous vehicle is largely determined by its control algorithm. Therefore, if the comfort of passengers can be predicted based on factors that affect comfort and the control algorithm can be adjusted, it can be beneficial to improve the comfort of autonomous vehicles. In view of this, in the present study, a human-driven experiment was carried out to simulate the typical driving state of a future autonomous vehicle. In the experiment, vehicle motion parameters and the comfort evaluation results of passengers with different physiological characteristics were collected. A single-factor analysis method and binary logistic regression analysis model were used to determine the factors that affect the evaluation results of passenger comfort. A passenger comfort prediction model was established based on the bidirectional long short-term memory network model. The results demonstrate that the accuracy of the passenger comfort prediction model reached 84%, which can provide a theoretical basis for the adjustment of the control algorithm and path trajectory of autonomous vehicles.
舒适性是影响乘客选择自动驾驶汽车的重要因素。自动驾驶汽车的舒适性在很大程度上取决于其控制算法。因此，如果能够根据影响舒适性的因素预测乘客的舒适性，并调整控制算法，将有助于提高自动驾驶汽车的舒适性。有鉴于此，本研究开展了一项人为驾驶实验，以模拟未来自动驾驶汽车的典型驾驶状态。在实验中，收集了车辆运动参数和不同生理特征乘客的舒适性评价结果。采用单因素分析方法和二项逻辑回归分析模型，确定了影响乘客舒适性评价结果的因素。并基于双向长短期记忆网络模型建立了乘客舒适性预测模型。结果表明，该乘客舒适性预测模型的准确率达到 84%，可为自动驾驶汽车的控制算法和路径轨迹调整提供理论依据。
