Developing personalised braking and steering thresholds for driver support systems from SHRP2 NDS data

Personalized active collision avoidance trajectory planning and variable time domain control integrating driver characteristics

Driver assistance systems play an important role in enhancing vehicle active safety. However, most of the existing driver assistance systems overlook the impact of driver characteristics on control performance, making it difficult to optimize the intervention strength of the controller for different drivers to achieve optimal performance. This paper proposed a novel vehicle active collision avoidance control strategy considering driver characteristics. By adjusting the time domain parameters of the model predictive control (MPC), collision avoidance assistance can be more effectively tailored to different types of drivers. Firstly, the collected lane-changing and collision avoidance data of 10 drivers with varying levels of experience were analyzed and preprocessed. Based on this analysis, a comprehensive index of collision avoidance characteristics was established that integrated trajectory tracking ability and driver burden, enabling the derivation of the collision avoidance characteristic curve representing the driver's preference and habit was obtained. Secondly, a sixth-order polynomial trajectory planning method considering driver characteristics was proposed. This method was optimized under vehicle stability and driver matching constraints to generate personalized collision avoidance trajectories for different drivers. The proposed comprehensive index and personalized collision avoidance trajectory were incorporated into the active collision avoidance control system, and a personalized time-variable domain MPC controller was designed. Test results based on a driver-in-the-loop bench demonstrate that the proposed personalized MPC could better match diverse driving characteristics, enhance the driver's trajectory tracking ability in the process of collision avoidance, reduce the driving workload, thereby improving overall driving safety and comfort.

Evaluation Method of Naturalistic Driving Behaviour for Shared-Electrical Car

Evaluation of driving behaviour is helpful for policy development, and for designing infrastructure and an intelligent safety system for a car. This study focused on a quantitative evaluation method of driving behaviour based on the shared-electrical car. The data were obtained from the OBD interface via CAN bus and transferred to a server by 4G network. Eleven types of NDS data were selected as the indexes for driving behaviour evaluation. Kullback–Leibler divergence was calculated to confirm the minimum data quantity and ensure the effectiveness of the analysis. The distribution of the main driving behaviour parameters was compared and the change trend of the parameters was analysed in conjunction with car speed to identify the threshold for recognition of aberrant driving behaviour. The weights of indexes were confirmed by combining the analytic hierarchy process and entropy weight method. The scoring rule was confirmed according to the distribution of the indexes. A score-based evaluation method was proposed and verified by the driving behaviour data collected from randomly chosen drivers.