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.

To ensure that autonomous vehicles satisfy the requirements of the traffic environment, vehicle driving ability, and desired driver experience during obstacle avoidance, this paper proposes a trajectory planner that considers three aspects: driving passability, regional safety, and driving acceptance. Multiresolution state lattices and Bézier curve fitters are applied to a state lattice framework to generate candidate obstacle avoidance trajectory clusters. Trajectory evaluation is then carried out in the above three aspects by using trajectory passability, safety and driver behavior proximity, and a trajectory evaluation function is designed to evaluate and screen trajectory clusters. The trajectory passability is checked by the vehicle motion capability set, which is established based on the vehicle dynamics model. The trajectory safety is evaluated by the potential field function between the fitted trajectory and the vehicle driving environment boundary with consideration of the inevitable collision state. The parameters of the vehicle motion state for the fitted trajectory are matched with the driving data of real drivers with different driving styles to evaluate the proximity between the trajectory and driver behavior. The rationality and effectiveness of different driving styles of trajectory planners are verified by vehicle tests under different vehicle velocities and different obstacle disturbances.

No abstract