Browse Publications Technical Papers 2018-01-1586

Study on Important Indices Related to Driver Feelings for LKA Intervention Process 2018-01-1586

KEYWORDS: driver feelings, Characteristic Indices, correlation model, Random Forests algorithm ABSTRACT Lane Keeping Assistance (LKA) system is a very important part in Advanced Driver Assistance Systems (ADAS). It prevents vehicle from departing out of the lane by exerting intervention. But inappropriate performance during LKA intervention makes driver feel uncomfortable. The intervention of LKA can be divided into 3 parts: intervention timing, intervention process and intervention ending. Many researches have studied about intervention timing and ending, but factors such as yaw rate and steering wheel velocity during intervention process also affect driver feelings a lot. To increase driver acceptance of LKA, objective and subjective tests were designed and conducted to explore important indices which are highly correlated with driver feelings. Different kinds of LKA controller control intervention process in different ways. So firstly, to describe intervention process uniformly and objectively, this paper proposed 16 Characteristic Indices (CI), such as ‘maximum yaw rate’, to describe vehicle motion, steering wheel motion and other aspects during different LKA intervention processes. Then, to acquire driver feelings about LKA, a questionnaire including 3 questions about different aspects was designed for drivers to give subjective ratings (SR). Lastly, to describe the nonlinear correlation between CI and SR, Random Forests (RF) algorithm was used to establish the correlation model. Different from other modeling methods, RF can not only build the model by data training, but also give out the importance of each CI in the model. Through this method, important indices really affecting driver feelings during the LKA intervention process were explored. These indices can be optimized according to the acquired correlation model between CI and SR. What’s more, by the use of CI, the correlation model can predict driver feelings regardless of specific LKA controller type. This prediction can be used to offer necessary guidance to the development and calibration of LKA system.


Subscribers can view annotate, and download all of SAE's content. Learn More »


Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 43% off list price.
Login to see discount.
Special Offer: Purchase more aerospace standards and aerospace material specifications and save! AeroPaks off a customized subscription plan that lets you pay for just the documents that you need, when you need them.