Analyzing the Influencing Factors and Workload Variation of Takeover Behavior in Semi-Autonomous Vehicles.

Hui Zhang,Chaozhong Wu,Yijun Zhang,Yiying Xiao

doi:10.3390/ijerph19031834

Hui Zhang, Chaozhong Wu + Show 2 more

Open Access

https://doi.org/10.3390/ijerph19031834

Copy DOI

Abstract

There are many factors that will influence the workload of drivers during autonomous driving. To examine the correlation between different factors and the workload of drivers, the influence of different factors on the workload variations is investigated from subjective and objective viewpoints. Thirty-seven drivers were recruited to participant the semi-autonomous driving experiments, and the drivers were required to complete different NDRTs (Non-Driving-Related Tasks): mistake finding, chatting, texting, and monitoring when the vehicle is in autonomous mode. Then, we introduced collision warning to signal there is risk ahead, and the warning signal was triggered at different TB (Time Budget)s before the risk, at which time the driver had to take over the driving task. During driving, the NASA-TLX-scale data were obtained to analyze the variation of the driver’s subjective workload. The driver’s pupil-diameter data acquired by the eye tracker from 100 s before the TOR (Take-Over Request) to 19 s after the takeover were obtained as well. The sliding time window was set to process the pupil-diameter data, and the 119-s normalized average pupil-diameter data under different NDRTs were fitted and modeled to analyze the variation of the driver’s objective workload. The results show that the total subjective workload score under the influence of different factors is as follows: obstacle-avoidance scene > lane-keeping scene; TB = 7 s and TB = 3 s have no significant difference; and mistake finding > chatting > texting > monitoring. The results of pupil-diameter data under different factors are as follows: obstacle-avoidance scene > lane-keeping scene; TB = 7 s > TB = 3 s; and monitoring type (chatting and monitoring) > texting type (mistake finding and texting). The research results can provide a reference for takeover safety prediction modeling based on workload.

Highlights

With the development of advanced driving assistance systems, the vehicle is becoming increasingly intelligent, and autonomous driving has become a research hotspot in the field of transportation in recent years [1]
In the stages 2–4, there is a significant correlation with NDRT (p < 0.01), indicating that different tasks have an impact on the workload occupied by the driver when taking over the vehicle again
This study is based on the shared driving simulated experiment and uses the driver’s subjective and objective cognitive load data, seeks the subjective and objective cognitive load-influencing factors in the takeover process, reveals the variations of driver’s workload before and after takeover when performing NDRTs, and further explores the interaction mechanism of different NDRTs, TB, etc., on cognitive load and takeover performance

Summary

Introduction

With the development of advanced driving assistance systems, the vehicle is becoming increasingly intelligent, and autonomous driving has become a research hotspot in the field of transportation in recent years [1]. It can release them from the main driving task, and they can perform different NDRTs [2], improving the comfort of driving. In September 2016, it updated the standard to classify vehicles into six levels based on intelligence degree, ranging from level 0 to level 5 They are driver, assisted, partially automated, highly automated, fully automated, and autonomous, respectively [3].

Methods

Results

Conclusion