Method for calculating expected car following distance in driver car following behavior analysis

Abstract

The invention relates to a method for calculating the expected car following distance in driver car following behavior analysis. On the basis that drivers design multiple different driving scenes during data collection on a car surrounding simulation testing platform, driving data is collected aiming at the drivers; the car following behavior feature parameter data set of each driver is extracted from the driving data; the feature behavior parameter data sets of all the drivers are clustered into several different driving classifications, and are adopted as training data sets; then the training data sets are utilized for carrying out classification judgment on the current drivers to be classified. Different car following behaviors are classified, the efficiency of collecting car following behavior data is improved, the cost is low, and good safety is achieved. The longitudinal driving behaviors of the drivers can be simulated through the Gussian process, the individualized expected car following distance can be provided for the current drivers, and the active adaptive capacity of an auxiliary driving system to different drivers is improved.

Description

technical field [0001] The invention relates to the field of intelligent driving, in particular to a method for calculating an expected following distance in the analysis of a driver's following behavior. Background technique [0002] The existing advanced driver assistant system (Advanced Driver Assistant System, ADAS) does not consider the driver's individual requirements, resulting in most drivers not being able to fully trust it, often intervening or even shutting down the assisted driving system many times during the driving process. Therefore, the learning and classification of driver behavior, especially the analysis of longitudinal driving behavior, can provide personalized support for adaptive cruise control and collision warning systems in ADAS, realize the active adaptability of driver assistance systems to different drivers, and enhance Driving comfort experience, improve the driver's confidence in the driving assistance system. [0003] The data collection of d...

AI Technical Summary

Problems solved by technology

[0003] The data collection of driver's following behavior based on real vehicles often consumes huge manpower and financial resources, and the economy is poor; at the same time, the following operation of some radical drivers often brings traffic safety hazards and poor safety; in addition, due to the external traffic environment The data of the same driver’s car-following behavior collected on the same road section at different times may be completely inconsistent, which brings great differences to the analysis of the driver’s car-following behavior. Determinism; Finally, collecting driver following behavior data requires expensive sensors such as lidar and millimeter-wave radar and data acquisition equipment that meets real-time requirements, as well as complicated installation and commissioning work, which is complex and costly

Images