Lisheng Jin

Driver Cognitive Distraction Detection Using Driving Performance Measures

Driver cognitive distraction is a hazard state, which can easily lead to traffic accidents. This study focuses on detecting the driver cognitive distraction state based on driving performance measures. Characteristic parameters could be directly extracted from Controller Area Network-(CAN-)Bus data, without depending on other sensors, which improves real-time and robustness performance. Three cognitive distraction states (no cognitive distraction, low cognitive distraction, and high cognitive distraction) were defined using different secondary tasks. NLModel, NHModel, LHModel, and NLHModel were developed using SVMs according to different states. The developed system shows promising results, which can correctly classify the driver’s states in approximately 74%. Although the sensitivity for these models is low, it is acceptable because in this situation the driver could control the car sufficiently. Thus, driving performance measures could be used alone to detect driver cognitive state.

Driver Intention Recognition Method Using Continuous Hidden Markov Model

In order to make Intelligent Transportation System (ITS) work effectively, a driver intention recognition method is proposed. In this research, three different recognition models were developed based on Continuous Hidden Markov Model (CHMM), and could distinguish left and right lane change intention from normal lane keeping intention. Subjects performed lane change maneuvers and lane keeping maneuvers with driving simulator which simulated highway scenes, parameters that highly correlated with lane change behavior were collected and analyzed. A series of testings and comparisons were done to obtain the optimal model structure and feature set. Results show that, taking the steering wheel angel, steering wheel angle velocity and lateral acceleration as the optimal observation signals, the accuracy can achieve up 95%, and it proved very effective in terms of early intention recognition.

Driver Sleepiness Detection System Based on Eye Movements Variables

Driver sleepiness is a hazard state, which can easily lead to traffic accidents. To detect driver sleepiness in real time, a novel driver sleepiness detection system using support vector machine (SVM) based on eye movements is proposed. Eye movements data are collected using SmartEye system in a driving simulator experiment. Characteristic parameters, which include blinking frequency, gaze direction, fixation time, and PERCLOS, are extracted based on the data using a statistical method. 13 sleepiness detection models including 12 specific models and 1 general model are developed based on SVM. Experimental results demonstrate that eye movements can be used to detect driver sleepiness in real time. The detecting accuracy of the specific models significantly exceeds the general model (P < 0.001), suggesting that individual differences are an important consideration when building detection algorithms for different drivers.

Research on Evaluation Model for Secondary Task Driving Safety Based on Driver Eye Movements

This study was designed to gain insight into the influence of performing different types of secondary task while driving on driver eye movements and to build a safety evaluation model for secondary task driving. Eighteen young drivers were selected and completed the driving experiment on a driving simulator. Measures of fixations, saccades, and blinks were analyzed. Based on measures which had significant difference between the baseline and secondary tasks driving conditions, the evaluation index system was built. Method of principal component analysis (PCA) was applied to analyze evaluation indexes data in order to obtain the coefficient weights of indexes and build the safety evaluation model. Based on evaluation scores, the driving safety was grouped into five levels (very high, high, average, low, and very low) using K-means clustering algorithm. Results showed that secondary task driving severely distracts the driver and the evaluation model built in this study could estimate driving safety effectively under different driving conditions.

The Effects of Using In-Vehicle Computer on Driver Eye Movements and Driving Performance

This paper examined the effects of performing an e-mail receiving and sending task using in-vehicle computer (iPad4) on driving performance and driver eye movements to determine if performance decrements decreased with practice. Eighteen younger drivers completed the driving on driving simulator while interacting with or without an e-mail task. Measures of fixations, saccades, vehicle control, and completion time of the secondary task were analyzed. Results revealed that using in-vehicle computer featured “large touch-screen” to receive and send e-mail greatly weakened drivers distraction and decreased their ability to control the vehicle. There was also evidence that, however, drivers attempted to regulate their behavior when distracted by decreasing their driving speed and taking a large number of short fixations and a quick saccades towards the computer. The results suggest that performing e-mail receiving and sending tasks while driving is problematic and steps to prohibit this activity should be taken.

Research on safety evaluation model for in-vehicle secondary task driving

This paper presents a new method for evaluating in-vehicle secondary task driving safety. There are five in-vehicle distracter tasks: tuning the radio to a local station, touching the touch-screen telephone menu to a certain song, talking with laboratory assistant, answering a telephone via Bluetooth headset, and finding the navigation system from Ipad4 computer. Forty young drivers completed the driving experiment on a driving simulator. Measures of fixations, saccades, and blinks are collected and analyzed. Based on the measures of driver eye movements which have significant difference between the baseline and secondary task driving conditions, the evaluation index system is built. The Analytic Network Process (ANP) theory is applied for determining the importance weight of the evaluation index in a fuzzy environment. On the basis of the importance weight of the evaluation index, Fuzzy Comprehensive Evaluation (FCE) method is utilized to evaluate the secondary task driving safety. Results show that driving with secondary tasks greatly distracts the drivers attention from road and the evaluation model built in this study could estimate driving safety effectively under different driving conditions.

Analyzing Effects of Pressing Radio Button on Driver’s Visual Cognition

An approach is presented based on driver simulator and SmarteyeII eye tracking system to examine the effects of pressing in-vehicle radio button on driver’s visual cognition. Parameters of glance frequency, glance duration, eye movement speed, and visual line moving in different regions of interest (ROIs) in task of pressing the radio button, closely related with driver’s visual cognition, were collected and analyzed. Based on the experimental data, driver’s visualization model with secondary tasks was built by CogTool. Driver’s vision, eye movement, cognition, and hand motion were tracked and recorded by the model. Results of experiment and running model show that pressing the in-vehicle radio button while driving has adverse influence on driver’s visual cognition and occupies a lot of the driver’s visual resources.

RESEARCH ON IN-VEHICLE SECONDARY TASK ANALYSIS MODEL BASED ON PREVIEW THEORY

The behavior of secondary task has an important influence on driving safety. It is necessary to build a precise driving model for accurate analysis of the influence of a secondary task on driving performance. The vehicle preview trajectory curve and steering control strategy are based on two different preliminary aim modes: the far point and the near one. Through the adjustment of a vehicle’s acceleration and deceleration according to the distance between the vehicle and the lead vehicle, a controllable method of vehicle running speed is determined, which regards the lead vehicle tail center as its tracking target. Finally, the driving model is built and the experiment shows that the model developed in this study conforms to reality better. Based on the model and the software Distract-R, successful analysis of the effect of secondary task on driving performance is achieved.

Multi-Traffic Scene Perception Based on Supervised Learning

Traffic accidents are particularly serious on a rainy day, a dark night, an overcast and/or rainy night, a foggy day, and many other times with low visibility conditions. Present vision driver assistance systems are designed to perform under good-natured weather conditions. Classification is a methodology to identify the type of optical characteristics for vision enhancement algorithms to make them more efficient. To improve machine vision in bad weather situations, a multi-class weather classification method is presented based on multiple weather features and supervised learning. First, underlying visual features are extracted from multi-traffic scene images, and then the feature was expressed as an eight-dimensions feature matrix. Second, five supervised learning algorithms are used to train classifiers. The analysis shows that extracted features can accurately describe the image semantics, and the classifiers have high recognition accuracy rate and adaptive ability. The proposed method provides the basis for further enhancing the detection of anterior vehicle detection during nighttime illumination changes, as well as enhancing the driver’s field of vision on a foggy day.

Research on the control and coordination of four-wheel independent driving/steering electric vehicle

A four-wheel-independent-driving and four-wheel-independent-steering control and coordination system is proposed by combining a four-wheel-independent-steering control system and a four-wheel-independent-driving control system. The four-wheel-independent-steering control system includes a linear quadratic regulator controller that calculates four-wheel steering angles and a fuzzy logic parameter adjustor that adjusts the linear quadratic regulator control parameters based on the vehicle steering states. The four-wheel-independent-driving control system consists of three parts: a proportional–integral–derivative controller for tracking the desired vehicle speed, a sliding mode control controller, and its corresponding torque distributor for power-assisted steering. It is particularly necessary to point out that the sliding mode control controller only works when the activation condition is satisfied and the torque distribution strategy is developed on the basis of the four-wheel-independent-steering control system. Simulation studies have been conducted to evaluate the proposed system. The results show that the proposed system can improve handling stability of four-wheel-independent-driving–four-wheel-independent-steering vehicle effectively and have a strong robustness for driving on a mu-split road.