Search

Nowadays, with more and more attention being paid to the characteristics and experience of drivers, a large number of driver classification algorithms have emerged. However, these methods basically cannot be adjusted independently to each driver. Therefore, this paper proposes a self-learning lane change motion planning system considering the driver’s personality. Firstly, the method of driver data acquisition and processing is determined to obtain and extract the lane change data. Then, the planning system built in this paper is explained from two aspects: lane change trigger and lane change trajectory. According to the artificial potential field theory, an obstacle driving risk field is established to evaluate the acceptance of environmental risks of different drivers, and to achieve personalized lane change triggers through online statistics. At the same time, the safety of lane change is ensured by establishing the safety distance model of the target lane. On the other hand, the driver characteristic coefficient Jc and the driver reaction and operation time td are introduced into the traditional Gaussian-distributed model to establish a personalized lane change trajectory planning model, in which the parameters are obtained from offline and online learning. Offline learning is based on DTW for trajectory matching, and uses AP clustering to obtain the generalized parameters; Online learning uses LSTM to achieve personalized updates. Finally, this paper selected 15 drivers for verification, and the results show that the motion planning system can well reproduce the lane change behavior of the driver.

Regarding changes of subjective and objective parameters of comfort during short and long-term driving, the arbitrariness of traditional subjective evaluation methods, as well as the defects of objective method where issues can be qualitatively but not quantitatively analyzed. By measuring pressure distribution and electromyography during short and long-term driving respectively, the article obtained pressure indicators, electromyography characteristic parameters and the corresponding subjective evaluations of drivers. The variation of subjective and objective parameters of comfort, the difference in terms of comfort and the fatigable body parts were tested. By means of correlation analysis completed the indicators screen. Proposed a new comprehensive weighting method-AHP to limit entropy method, established the mapping relations between subjective comfort and objective indicators, which based on pressure distribution and physiological information during short-term and long-term driving. Obtained a quantitative evaluation method that applies pressure distribution, physiological information and subjective evaluation to effectively evaluate driving comfort, and thus provided a theoretical basis for evaluating driving comfort.

Early studies on intelligent control methods for automatic starting control for vehicles mainly focus on traditional parametric adjustment. However, attempts toward the combination of learning algorithms and models are rare. When drivers’ starting behavior is not considered and tedious parameters are merely used for drive control, the effects result in discomfort for drivers. Therefore, to imitate drivers’ starting behavior when dealing with automatic drive control in vehicles, we must first develop an acceleration fitting based on DFT by analyzing the starting characteristics. Then, we design an iterative learning algorithm to achieve automatic starting control of vehicles. Finally, a simulation test is conducted based on CARSIM to verify the validity and feasibility of the proposed method.