Driver Workload Research Articles

Predicting response latency using EEG alpha-band power and low-cost wearable physiological sensors.

Predicting response latency using EEG alpha-band power and low-cost wearable physiological sensors.

Switched Cooperative Driving Model towards Human Vehicle Copiloting Situation: A Cyberphysical Perspective

Development of highly automated and intelligent vehicles can lead to the reduction of driver workload. However, it also causes the out-of-the-loop problem to drivers, which leaves drivers handicapped in their ability to take over manual operations in emergency situations. This contribution puts forth a new switched driving strategy to avoid some of the negative consequences associated with out-of-the-loop performance by having drivers assume manual control at periodic intervals. To minimize the impact of the transitions between automated and manual driving on traffic operations, a switched cooperative driving model towards human vehicle copiloting situation is proposed by considering the vehicle dynamics and the realistic intervehicle communication in a cyberphysical view. The design method of the switching signal for the switched cooperative driving model is given based on the Lyapunov stability theory with the comprehensive consideration of platoon stability and human factors. The good agreement between simulation results and theoretical analysis illustrates the effectiveness of the proposed methods.

Classification of driving workload affected by highway alignment conditions based on classification and regression tree algorithm

ABSTRACTObjective: Guaranteeing a safe and comfortable driving workload can contribute to reducing traffic injuries. In order to provide safe and comfortable threshold values, this study attempted to classify driving workload from the aspects of human factors mainly affected by highway geometric conditions and to determine the thresholds of different workload classifications. This article stated a hypothesis that the values of driver workload change within a certain range.Methods: Driving workload scales were stated based on a comprehensive literature review. Through comparative analysis of different psychophysiological measures, heart rate variability (HRV) was chosen as the representative measure for quantifying driving workload by field experiments. Seventy-two participants (36 car drivers and 36 large truck drivers) and 6 highways with different geometric designs were selected to conduct field experiments. A wearable wireless dynamic multiparameter physiological detector (KF-2) was employed to detect physiological data that were simultaneously correlated to the speed changes recorded by a Global Positioning System (GPS) (testing time, driving speeds, running track, and distance). Through performing statistical analyses, including the distribution of HRV during the flat, straight segments and P-P plots of modified HRV, a driving workload calculation model was proposed. Integrating driving workload scales with values, the threshold of each scale of driving workload was determined by classification and regression tree (CART) algorithms.Results: The driving workload calculation model was suitable for driving speeds in the range of 40 to 120 km/h. The experimental data of 72 participants revealed that driving workload had a significant effect on modified HRV, revealing a change in driving speed. When the driving speed was between 100 and 120 km/h, drivers showed an apparent increase in the corresponding modified HRV. The threshold value of the normal driving workload K was between −0.0011 and 0.056 for a car driver and between −0.00086 and 0.067 for a truck driver.Conclusion: Heart rate variability was a direct and effective index for measuring driving workload despite being affected by multiple highway alignment elements. The driving workload model and the thresholds of driving workload classifications can be used to evaluate the quality of highway geometric design. A higher quality of highway geometric design could keep driving workload within a safer and more comfortable range. This study provided insight into reducing traffic injuries from the perspective of disciplinary integration of highway engineering and human factor engineering.

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Adapting in-vehicle systems (e.g., advanced driver assistance systems and in-vehicle information systems) to individual drivers’ workload can enhance both safety and convenience. To make this possible, it is a prerequisite to infer driver workload so that adaptive aiding can be provided to the driver at the right time and in an appropriate manner. Rather than developing an average model for all drivers, a personalized driver workload inference (PDWI) system considering individual drivers driving characteristics is developed using machine learning techniques via easily accessed vehicle related measurements (VRMs). The proposed PDWI system comprises two stages. In offline training, individual drivers workload is first automatically splitted into different categories according to its inherent data characteristics using fuzzy C-means (FCM) clustering. Then an implicit mapping between VRMs and different levels of workload is constructed via classification algorithms. In online implementation, VRMs samples are classified into different clusters, consequently driver workload type can be successfully inferred. A recently collected dataset from real-world naturalistic driving experiments is drawn to validate the proposed PDWI system. Comparative experimental results indicate that the proposed framework integrating FCM clustering and support vector machine classifier provides a promising workload recognition performance in terms of accuracy, precision, recall, ${F_{1}}$ -score, and prediction time. The interindividual differences in term of workload are also identified and can be accommodated by the proposed framework due to its adaptiveness.

Mind the gap: Drivers underestimate the impact of the behaviour of other traffic on their workload

This study examines the effect of traffic demand on driver workload by varying a range of characteristics of traffic behaviour, in particular focusing on the influence of a lane change performed by a neighbouring vehicle. To examine drivers' ability to manage their own workload in these traffic situations, a self-initiated, surrogate mobile phone task was presented to them, to coincide with changes in traffic demand. Results showed that whilst participants delayed the initiation of the task when the lane change was performed in close proximity to them, the delay was insufficient to mitigate the effects of the increased workload, leading to task errors. This was attributed to driver's willingness to engage in secondary tasks, even though their (self-reported) workload had not returned to baseline levels. The minimum workload recovery period was calculated as being 12 s after the onset of the adjacent vehicle's manoeuvre, and this has implications for the design of workload managers.

Driver workload estimation using a novel hybrid method of error reduction ratio causality and support vector machine

Measuring driver workload is of great significance for improving the understanding of driver behaviours and supporting the improvement of advanced driver assistance systems technologies. In this paper, a novel hybrid method for measuring driver workload estimation for real-world driving data is proposed. Error reduction ratio causality, a new nonlinear causality detection approach, is being proposed in order to assess the correlation of each measured variable to the variation of workload. A full model describing the relationship between the workload and the selected important measurements is then trained via a support vector regression model. Real driving data of 10 participants, comprising 15 measured physiological and vehicle-state variables are used for the purpose of validation. Test results show that the developed error reduction ratio causality method can effectively identify the important variables that relate to the variation of driver workload, and the support vector regression based model can successfully and robustly estimate workload.

Driver Workload and Secondary Task Modality while Driving on Horizontal Curves

High driver workload has been considered as a risk factor in motor vehicle crashes. To minimize the number of crashes and improve driving safety, it is necessary to investigate driver workload and the most influential factor that affects driver workload. In this study, we examined the effects of road geometry, driving performance (by both steering wheel and pedal controls), and secondary task modality type on driver workload. A hierarchical ordinary least squares multiple regression analysis revealed that visually demanding secondary task predicted higher driver workload. This finding could help in-vehicle interface designs to minimize driver workload and improve driving safety.

군집주행 환경에서 비자율차의 차로변경행태 분석

자율주행기술이 교통류에 미치는 영향을 분석하기 위해서는 자율차와 비자율차 간의 상호작용을 분석하는 것이 중요한 이슈이다. 특히 자율주행기술을 활용한 유용한 서비스 중의 하나인 군집주행은 주변의 비자율 차량의 주행행태에 영향을 미칠 수 있다. 본 연구의 목적은 군집주행 환경에서 비자율차의 차로변경행태 분석하는 것이며, 3단계의 실험 및 조사를 수행하였다. 1단계 영상기반 인지특성 분석을 통해 군집주행 환경에서 어떠한 반응행태를 보일 것인지를 조사하였으며, 2단계 주행시뮬레이션 실험을 통해 비자율차의 차로변경행태를 분석하였다. 차로변경행태를 분석하기 위해 차로변경시간과 교통류의 안전성을 나타낼 수 있는 지표인 가속소음을 이용하였으며, 자율차의 시스템 보급률(Market Penetration Rate, MPR)과 피실험자 인적요소에 따른 비자율차의 주행행태 차이를 비교 분석하였다. 마지막 단계인 NASA-TLX(NASA Task Load Index)를 통해 비자율차 운전자의 작업부하를 평가하였다. 분석결과 군집차량군 주변의 비자율차 운전자는 심리적인 부담감을 느끼며, MPR이 증가할수록 차로변경시간이 길어지고 30-40대 운전자 또는 여성 운전자의 경우 안전성이 낮아지는 것으로 나타났다. 본 연구에서 도출된 결과는 자율차와 비자율차의 상호작용을 반영한 보다 현실성 높은 교통시뮬레이션 실험 시 기초자료로 활용될 수 있고, 이를 기반으로 자율협력주행 환경에서 적용 가능한 교통운영관리전략 수립을 효과적으로 지원할 것으로 기대된다. Analysis of the interaction between the automated vehicles and manual vehicles is very important in analyzing the performance of automated cooperative driving environments. In particular, the automated vehicle platooning can affect the driving behavior of adjacent manual vehicles. The purpose of this study is to analyze the lane change behavior of the manual vehicles in automated vehicle platonning environment and to conduct the experiment and questionnaire surveys in three stages. In the first stage, a video questionnaire survey was conducted, and responsive behaviors of manual vehicles were investigated. In second stage, the driving simulator experiments were conducted to investigate the lane change behaviors of in automated vehicle platonning environments. To analyze the lane change behavior of the manual vehicles, lane change durations and acceleration noise, which are indicators of traffic flow stability, were used. The driving behavior of manual vehicles were compared across different market penetration rates (MPR) of automated vehicles and human factors. Lastly, NASA-TLX (NASA Task Load Index) was used to evaluate the workload of the manual vehicle drivers. As a result of the analysis, it was identified that manual vehicle drivers had psychological burdens while driving in automated vehicle platonning environments. Lane change durations were longer when the MPR of the automated vehicles increased, and acceleration noise were increased in the case of 30-40 years old or female drivers. The results from this study can be used as a fundamental for more realistic traffic simulations reflecting the interaction between the automated vehicles and manual vehicles. It is also expected to effectively support the establishment of valuable transportation management strategy in automated vehicle environments.

Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload

Driving is a safety critical task that requires a high level of attention from the driver. Although drivers have limited attentional resources, they often perform secondary tasks such as eating or using a mobile phone. When performing multiple tasks in the vehicle, the driver can become overloaded and the risk of a crash is increased. If a vehicle is aware that the driver is currently under high workload, the vehicle functionality can be changed in order to minimise any further demand. Traditionally, workload is measured using physiological sensors that require often intrusive and expensive equipment. Another approach may be to use vehicle telemetry data as a performance measure for workload. In this paper, the authors present the Warwick-JLR Driver Monitoring Dataset (DMD) and analyse it to investigate the feasibility of using vehicle telemetry data for determining the driver workload. They perform a statistical analysis of subjective ratings, physiological data, and vehicle telemetry data collected during a track study. A data mining methodology is then presented to build predictive models using this data, for the driver workload monitoring problem.

A Gain-Scheduling Driver Assistance Trajectory-Following Algorithm Considering Different Driver Steering Characteristics

In this paper, a gain-scheduling, robust, and shared controller is proposed to assist drivers in tracking vehicle reference trajectory. In the controller, the driver steering parameters such as delay time, preview time, and steering gain are assumed to be varying with respect to the different characteristics of drivers, vehicle states, and driving scenarios. Meanwhile, the modeling errors and uncertainties in the tire cornering stiffness are also considered in the driver–vehicle system model and the controller design. A global objective function, considering the tracking error, the driver's physical and mental workloads, and the control effort, is designed to optimize the overall performance of the driver–vehicle system. Constraint on eigenvalue placement is added to the controller design to improve the performance of the closed-loop driver–vehicle system. Simulation results under different maneuvers show that the controller can significantly improve the system performance and reduce the driver's workloads. The controller can reduce the delay time of the driver–vehicle system in emergency maneuvers, particularly for inexperienced drivers.

Driver behaviour and driver experience of partial and fully automated truck platooning \u2013 a simulator study

IntroductionThis paper builds our knowledge of truck driver behaviour in and experience of automated truck platooning, focusing on the effect of partially and fully automated truck platoons on driver workload, trust, acceptance, performance, and sleepiness.MethodsTwenty-four male drivers experienced three conditions in a truck driving simulator, i.e., baseline, partial automation, and full automation: the baseline condition was driving with standard cruise control; partial automation was automated longitudinal control ten metres behind the truck in front, with the driver having to steer; and full automation was automated longitudinal and lateral control. Each condition was simulated in three situations: light traffic, heavy traffic, and heavy traffic plus fog.ResultsThe experiment demonstrated that automation affects workload. For all workload measures, partial automation produced higher workload than did the full-automation or baseline condition. The two measures capturing trust, i.e., the Human Trust in Automated Systems Scale (HTASS) and Cooper–Harper Scales of Workload, Temporal Load, Situation Awareness, and Trust, were consistent and indicated that trust was highest under the baseline condition, with little difference between partial and full automation. Driver acceptance of both levels of automation was lower than acceptance of baseline. Drivers rated their situation awareness higher for both partial and full automation than for baseline, although both levels of automation led to higher sleepiness.ConclusionsWorkload was higher for partial than for full automation or the baseline condition. Trust and acceptance were generally highest in the baseline condition, and did not differ between partial and full automation. Drivers may believe that they have more situation awareness during automated driving than they actually do. Both levels of automation led to a higher degree of sleepiness than in the baseline condition. The challenge when implementing truck platooning is to develop a system, including human–machine interaction (HMI), that does not overburden the driver, properly addresses driver sleepiness, and satisfies current legislation. The system also must be trusted and accepted by drivers. To achieve this, the development of well-designed HMI will be crucial.

How is the Driver's Workload Influenced by the Road Environment?

This paper focuses on the study of the driver's workload while driving on a rural two-lane road with different traffic flows. The aim of the research is to examine a parameter that could be representative of the driving effort, quite sensible to the external factors that cause disturbance to the regular driving activity. To solve this problem, the authors used a specific instrumented vehicle for monitoring some physiological parameters of the driver (as the eye movements and the Galvanic Skin Resistance), referring their values to the road context. The results are very interesting and confirm that knowing the workload is useful to improve the road safety only if it is related to the external context, as well as road geometry, traffic, visibility, etc. Only in this way, the road administrators can deduce proper information to plan and direct accurate and productive upgrade working operations.

Effect of Installation Configuration of Guide-lights on Drivers Work Load and Visual Guide Performance

Effect of Installation Configuration of Guide-lights on Drivers Work Load and Visual Guide Performance

Research on Comfort and Safety Threshold of Pavement Roughness

Pavement roughness, which may cause vehicle vibrations and driving instability and even cause loss of control, is the main cause of unsafe and uncomfortable driving. In most countries, the international roughness index (IRI) is used to measure pavement roughness. Driving comfort and safety are currently evaluated with an empirical method of expert scoring, and reliable experimental measurements are not created. Based on previous work, which included evaluation of driving comfort and safety (driving workload) according to physiological and psychological indexes, as well as thresholds of driving comfort and safety, this paper determines the mathematical relationship between IRI and driving workload with experimental data of real vehicles to study the threshold of IRI for driving comfort and safety. Experimental data, including physiological and psychological indexes, driving speed, and IRI, of 12 car drivers and 12 truck drivers driving at a speed of 60 km/h were collected on a road with high alignment elements that had no impact on driving workload in northwest China. The mathematical relationships between IRI and driving workload of car drivers and truck drivers were determined, and thresholds of IRI on road segments at various risk levels for driving comfort and safety were obtained. The results show that standard IRI values for pavement maintenance in China are beyond the comfort and safety thresholds for both car drivers and truck drivers. Methods and conclusions in this paper could provide theoretical and technical support for the improvement of pavement service.

Case Study of Today’s Automotive Dealerships: Introduction and Delivery of Advanced Driver Assistance Systems

Vehicle manufacturers have developed advanced driver assistance systems (ADASs) to reduce driver workload and enhance safety. The delivery of these systems to consumers occurs through dealerships not owned by manufacturers. Limited research is available on how dealerships provide consumers with information and training on ADASs. In an exploratory study seeking information on new safety technologies, semistructured blind interviews of salespeople at 18 Boston, Massachusetts, area dealerships were conducted in the context of potential vehicle purchase across six vehicle brands. Although some dealerships were making concerted efforts to introduce and educate customers on ADASs, a number of salespeople interviewed were not well positioned to provide adequate information to their customers. In select instances, salespeople explicitly provided inaccurate information on safety-critical systems. The dealerships in the sample that represented mass-market brands (Ford and Chevrolet) were the poorest performers. Sales staff at Subaru dealers were well trained and had print and digital content to drive consumer engagement. Educational staff, or “geniuses,” at BMW dealers presented a potentially innovative way of segmenting the sales process from technology education. In the absence of some technology introduction and education at dealerships, consumers may remain underinformed or misinformed about the disruptive safety technologies that are rapidly being introduced across the vehicle fleet.

Dynamic coordinated control of a downhill safety assistance system for hybrid electric buses

When driving downhill, downhill safety assistance control can ensure a safe speed. A downhill safety assistance system was developed by our research group to help hybrid electric vehicles to maintain a stable speed when driving downhill. For hybrid electric buses, in addition to the pneumatic braking system, the motor can quickly provide an electrical braking torque, and the engine can be considered a mechanical brake. The downhill safety assistance system for hybrid electric buses maintains the desired downhill speed on different road slopes. However, when and how to activate or deactivate the downhill safety assistance system because of the driver’s operation or the road conditions was not discussed in combination with the energy management strategy for the vehicle. Additionally, there is currently no dynamic control strategy for the transition process when the braking modes of the downhill safety assistance system change, which can lead to instability. To address the limitations of previous studies, a dynamic coordinated control strategy of the downhill safety assistance system is proposed considering practical application, which focuses on the above two aspects to keep the entire system stable. To improve the ride comfort and the vehicle safety when the downhill safety assistance system works in conjunction with the energy management strategy for the vehicle, the proposed control strategy is developed to activate or deactivate the downhill safety assistance system based on the driver’s driving habits and operation and the road conditions in order to reduce the workload and to improve the driveability of the buses. To maintain the ride comfort during the transient process of shift in the braking mode and to maintain a stable speed over the overall course, the mode-shift coordinated control strategy of the downhill safety assistance system is presented, which combines the braking modes to ensure that the braking torque changes steadily without saltation. The experimental results validate the performance of the entire dynamic coordinated control strategy of the downhill safety assistance system with a high stability, and the statistics demonstrate that the downhill safety assistance system obviously improves the fuel economy and reduces the driver workload.

Simultaneous Achievement of Workload Reduction and Skill Enhancement in Backward Parking by Haptic Guidance

Advanced driver assistance systems (ADASs) have been developed and have subsequently decreased opportunities for driver skill development because of degraded situational awareness and less activity in the control loop. Beginning drivers must therefore engage in training. The idea has arisen that haptic shared control, which encourages a driver to operate the vehicle properly and with correct timing, should serve as a training system for daily driving. Such a system, however, might degrade performance, comfort, or safety because training aspects might increase the driver workload as a result of error correction feedback. The possibility of lowered usability is not acceptable for ADASs. This study was conducted to develop an assist system that achieves workload reduction and skill improvement. A haptic assistance system that applies guidance torque on the steering wheel was proposed and investigated for backward parking, which is a difficult driving situation. Driving simulator experiments were conducted. Results showed that both support and after-use effects were realized. This study provides knowledge for the development of driving systems using haptic assistant systems for which initial skill influences performance.

Classification of a Driver's cognitive workload levels using artificial neural network on ECG signals

An artificial neural network (ANN) model was developed in the present study to classify the level of a driver's cognitive workload based on electrocardiography (ECG). ECG signals were measured on 15 male participants while they performed a simulated driving task as a primary task with/without an N-back task as a secondary task. Three time-domain ECG measures (mean inter-beat interval (IBI), standard deviation of IBIs, and root mean squared difference of adjacent IBIs) and three frequencydomain ECG measures (power in low frequency, power in high frequency, and ratio of power in low and high frequencies) were calculated. To compensate for individual differences in heart response during the driving tasks, a three-step data processing procedure was performed to ECG signals of each participant: (1) selection of two most sensitive ECG measures, (2) definition of three (low, medium, and high) cognitive workload levels, and (3) normalization of the selected ECG measures. An ANN model was constructed using a feed-forward network and scaled conjugate gradient as a back-propagation learning rule. The accuracy of the ANN classification model was found satisfactory for learning data (95%) and testing data (82%).

Analysis of driver workload when using speech interfaces

Speech interfaces are useful for improving the accessibility of in-vehicle devices as they are considered to be less distracting than visual interfaces. However, there is still considerable cognitive demand when using a speech interface, which may increase the chance of a traffic accident. This study investigates driver workload induced by various tasks, including a speech interface used for music retrieval. Driving data were collected from 523 drivers operating an instrumented vehicle on urban streets and highways. The drivers were given each of the following secondary tasks while driving: a) repeating random strings of four letters they heard through an earphone, b) interacting with a spoken dialogue system to retrieve and play music, c) being directed to an unfamiliar place by a human navigator on a cell phone, and d) reading aloud words seen on signboards while driving. After driving, each driver subjectively rated the induced workload for each secondary task from 1 (lowest) to 5 (highest). Analysis of the results of their subjective evaluations showed that talking to a navigator on a cell phone resulted in the lowest average workload (about 1.6), which was almost the same as the driving without any secondary task. Repeating random strings of four letters and retrieving music using a speech interface produced the highest average workload (about 2.5).

A workload model to evaluate distracters and driver's aids

The aim of this study is to examine the use of a driver workload simulation model to provide commercial vehicle interface designers a tool to investigate the effects of various types of distracters and driver's aids under varying conditions, prior to test in a simulator or implementation in a prototype. To build the model, a driving scenario was first identified based on the National Highway Traffic Safety Association (NHTSA) driving route. The driving model was created using IMPRINT, a discrete event simulation tool that characterizes four classes of human resources that may contribute to driver workload: visual, auditory, cognitive and psychomotor (VACP). For this initial model we tested limited number and type of distractions. The initial use of a sample of driver aids and their importance to mitigating driver distractions has also been included. Relevance to IndustryThis study investigated the use of a driver workload simulation model to provide commercial vehicle interface designers a tool to investigate the impact of the multiple activities an operator performs while driving. A simulation model can predict the changes in driver workload due to multiple secondary tasks performed in varying driving conditions.