Designing an integrated driver assistance system using image sensors

Road accidents cause a great loss to human lives and assets. Most of the accidents occur due to human errors, such as bad awareness, distraction, drowsiness, low training, and fatigue. Advanced driver assistance system (ADAS) can reduce the human errors by keeping an eye on the driving environment and warning a driver to the upcoming danger. However, these systems come only with modern luxury cars because of their high cost and complexity due to several sensors employed. Therefore, camera-based ADAS are becoming an option due to their lower cost, higher availability, numerous applications and ability to combine with other systems. Targeting at designing a camera-based ADAS, we have conducted an ethnographic study of drivers to know what information about the driving environment would be useful in preventing accidents. It turned out that information on speed, distance, relative position, direction, and size and type of the nearby objects would be useful and enough for implementing most of the ADAS functions. Several camera-based techniques are available for capturing the required information. We propose a novel design of an integrated camera-based ADAS that puts technologies??such as five ordinary CMOS image sensors, a digital image processor, and a thin display??into a smart system to offer a dozen advanced driver assistance functions. A basic prototype is also implemented using MATLAB. Our design and the prototype testify that all the required technologies are now available for implementing a full-fledged camera-based ADAS.     

How do environmental characteristics at intersections change in their relevance for drivers before entering an intersection: analysis of drivers’ gaze and driving behavior in a driving simulator study

Accident studies in Germany found that in about 90 % of intersection accidents, failure to acquire the relevant information of the driving situation was the main reason for drivers’ errors (Vollrath et al. in Ableitung von Anforderungen an Fahrerassistenzsysteme aus Sicht der Verkehrssicherheit. Wirtschaftsverlag NW, Bremerhaven, 2006). Studies of bicycle–car accidents assume that improper attention allocation strategies and unjustified expectations by drivers are important for this kind of error (Räsänen and Summala in Accid Anal Prev 30:657–666, 1998). Aim of the study was to examine the psychological processes of drivers’ attention allocation and driving behavior in different intersection situations varied by two environmental characteristics. A give way T-intersection was varied by (1) low and high traffic density of oncoming cars from the left and (2) number of task-relevant information areas (in addition to the oncoming cars from the left with or without pedestrians on the right). It was examined how these environmental characteristics change in their relevance for drivers while entering the intersections. The analysis was conducted in three intersection epochs (Approaching, Waiting, Accelerating). A total of 40 subjects (26 male, 14 female), ranged in age from 19 to 55 years (M = 31.0 years), participated in the study. The results showed that drivers’ attention allocation (e.g., mean gaze duration) and driving behavior (e.g., waiting time) systematically depends on these environmental characteristics which require different actions of the driver and change in their relevance when entering an intersection. The results support the idea of attention allocation strategies by drivers which are specific for certain driving situations. These findings can support approaches of driver modeling at intersections.     

Haptic gas pedal feedback

Active driver support systems either automate a control task or present warnings to drivers when their safety is seriously degraded. In a novel approach, utilising neither automation nor discrete warnings, a haptic gas pedal (accelerator) interface was developed that continuously presents car-following support information, keeping the driver in the loop. This interface was tested in a fixed-base driving simulator. Twenty-one drivers between the ages of 24 and 30 years participated in a driving experiment to investigate the effects of haptic gas pedal feedback on car-following behaviour. Results of the experiment indicate that when haptic feedback was presented to the drivers, some improvement in car-following performance was achieved, while control activity decreased. Further research is needed to investigate the effectiveness of the system in more varied driving conditions. Haptics is an under-used modality in the application of human support interfaces, which usually draw on vision or hearing. This study demonstrates how haptics can be used to create an effective driver support interface.     

Haptic gas pedal feedback

Active driver support systems either automate a control task or present warnings to drivers when their safety is seriously degraded. In a novel approach, utilising neither automation nor discrete warnings, a haptic gas pedal (accelerator) interface was developed that continuously presents car-following support information, keeping the driver in the loop. This interface was tested in a fixed-base driving simulator. Twenty-one drivers between the ages of 24 and 30 years participated in a driving experiment to investigate the effects of haptic gas pedal feedback on car-following behaviour. Results of the experiment indicate that when haptic feedback was presented to the drivers, some improvement in car-following performance was achieved, while control activity decreased. Further research is needed to investigate the effectiveness of the system in more varied driving conditions. Haptics is an under-used modality in the application of human support interfaces, which usually draw on vision or hearing. This study demonstrates how haptics can be used to create an effective driver support interface.     

Speech-based E-mail and driver behavior: effects of an in-vehicle message system interface

As mobile office technology becomes more advanced, drivers have increased opportunity to process information "on the move." Although speech-based interfaces can minimize direct interference with driving, the cognitive demands associated with such systems may still cause distraction. We studied the effects on driving performance of an in-vehicle simulated "E-mail" message system; E-mails were either system controlled or driver controlled. A high-fidelity, fixed-base driving simulator was used to test 19 participants on a car-following task. Virtual traffic scenarios varying in driving demand. Drivers compensated for the secondary task by adopting longer headways but showed reduced anticipation of braking requirements and shorter time to collision. Drivers were also less reactive when processing E-mails, demonstrated by a reduction in steering wheel inputs. In most circumstances, there were advantages in providing drivers with control over when E-mails were opened. However, during periods without E-mail interaction in demanding traffic scenarios, drivers showed reduced braking anticipation. This may be a result of increased cognitive costs associated with the decision making process when using a driver-controlled interface when the task of scheduling E-mail acceptance is added to those of driving and E-mail response. Actual or potential applications of this research include the design of speech-based in-vehicle messaging systems.     

Using eye movements to evaluate a PC-based risk awareness and perception training program on a driving simulator

OBJECTIVE: Evaluation of the effects of a PC-based training program on risk perception in a driving simulator. BACKGROUND: Novice drivers have a fatality rate some eight times higher than that of the most experienced group of drivers, primarily because of the novice driver's inability to predict ahead of time the risks that will appear in the roadway. Current driver education programs, at least those in the United States, do not emphasize the teaching of risk awareness skills to novice drivers. METHOD: A PC-based risk awareness and perception training program was developed and evaluated. The training involved using plan (top-down) views of 10 risky scenarios that helped novice drivers identify where potential risks were located and what information should be attended. Both the 24 trained novice drivers and 24 untrained novice drivers were evaluated on an advanced driving simulator. The eye movements of both groups of drivers were measured. The evaluation on the driving simulator included both scenarios used in the training and others not used in training. RESULTS: The set of trained novice drivers were almost twice as likely as untrained drivers to fixate appropriately either on the regions where potential risks might appear or on signs that warned of potentially risky situations ahead, both for the scenarios they had encountered in training and for novel scenarios. APPLICATION: The PC training program developed, which is portable and can be widely used, has great promise in improving risk perception for novice drivers on the road.     

Distraction from multiple in-vehicle secondary tasks: vehicle performance and mental workload implications

This study investigates the impact of multiple in-vehicle information systems on the driver. It was undertaken using a high fidelity driving simulator. The participants experienced, paced and unpaced single tasks, multiple secondary tasks and an equal period of ‘normal’ driving. Results indicate that the interaction with secondary tasks led to significant compensatory speed reductions. Multiple secondary tasks were shown to have a detrimental affect on vehicle performance with significantly reduced headways and increased brake pressure being found. The drivers reported interaction with the multiple in-vehicle systems to significantly impose more subjective mental workload than either a single secondary task or ‘normal driving’. The implications of these findings and the need to integrate and manage complex in-vehicle information systems are discussed.     

The relationships between organizational and individual variables to on-the-job driver accidents and accident-free kilometres

Highway fatalities are the leading cause of fatal work injuries in the US, accounting for approximately 1 in 4 of the 5900 job-related deaths during 2001. The present study focused on the contribution of organizational factors and driver behaviours to on-the-job driving accidents in a large Western Canadian corporation. A structural equation modelling (SEM) approach was used which allows researchers to test a complex set of relationships within a global theoretical framework. A number of scales were used to assess organizational support, driver errors, and driver behaviours. The sample of professional drivers that participated allowed the recording of on-the-job accidents and accident-free kilometres from their personnel files. The pattern of relationships in the fitted model, after controlling for exposure and social desirability, provides insight into the role of organizational support, planning, environment adaptations, fatigue, speed, errors and moving citations to on-the-job accidents and accident-free kilometres. For example, organizational support affected the capacity to plan. Time to plan work-related driving was found to predict accidents, fatigue and adaptations to the environment. Other interesting model paths, SEM limitations, future research and recommendations are elaborated.     

Assessment and monitoring of mental workload in subway train operations using physiological,subjective, and performance measures

Subway train operation is a complex, sociotechnical system that involves a variety of cognitively demanding tasks. The train operators are responsible for continuously monitoring the surrounding environment, maintaining awareness, processing information, and making decisions under risk. The resulting mental strain on operators can negatively affect their performance and the interaction of the human–machine system. The objective of this study was to evaluate if physiological, subjective, and performance measures could identify the level of mental workloads arising from routine and nonroutine operations in the subway system. A total of 11 subway train operators underwent different driving scenarios in a high‐fidelity simulator. The simulated tasks were divided into two categories: routine operations (preparing to drive and driving between stations without interruptions or emergencies) and nonroutine operation (responding to a tunnel fire, dealing with a high density of passengers, encountering a passenger/technician on the track, and responding to train failure). The mental workload was monitored and evaluated in these tasks using an electrocardiogram, subjective self‐rating scales, and driving performance. Both heart rate variability and performance measures (including reaction time and error rate) detected mental workload variations in the different operations. On the other hand, the subjective ratings (including NASA‐TLX) assessed the overall mental workload associated with a task, without explaining the mental demand variations within the task over time. Subway train drivers experienced different levels of mental workload during routine and nonroutine driving conditions. The findings of this study can be used to extract mental workload limits to optimize workload levels during train operations.     

The relationships between organizational and individual variables to on-the-job driver accidents and accident-free kilometres

Highway fatalities are the leading cause of fatal work injuries in the US, accounting for approximately 1 in 4 of the 5900 job-related deaths during 2001. The present study focused on the contribution of organizational factors and driver behaviours to on-the-job driving accidents in a large Western Canadian corporation. A structural equation modelling (SEM) approach was used which allows researchers to test a complex set of relationships within a global theoretical framework. A number of scales were used to assess organizational support, driver errors, and driver behaviours. The sample of professional drivers that participated allowed the recording of on-the-job accidents and accident-free kilometres from their personnel files. The pattern of relationships in the fitted model, after controlling for exposure and social desirability, provides insight into the role of organizational support, planning, environment adaptations, fatigue, speed, errors and moving citations to on-the-job accidents and accident-free kilometres. For example, organizational support affected the capacity to plan. Time to plan work-related driving was found to predict accidents, fatigue and adaptations to the environment. Other interesting model paths, SEM limitations, future research and recommendations are elaborated.     

Real-Time Warning System for Driver Drowsiness Detection Using Visual Information

Traffic accidents due to human errors cause many deaths and injuries around the world. To help in reducing this fatality, in this research, a new module for Advanced Driver Assistance System (ADAS) for automatic driver drowsiness detection based on visual information and Artificial Intelligence is presented. The aim of this system is to locate, to track and to analyze the face and the eyes to compute a drowsiness index, working under varying light conditions and in real time. Examples of different images of drivers taken in a real vehicle are shown to validate the algorithm.     

Distraction from multiple in-vehicle secondary tasks: vehicle performance and mental workload implications

This study investigates the impact of multiple in-vehicle information systems on the driver. It was undertaken using a high fidelity driving simulator. The participants experienced, paced and unpaced single tasks, multiple secondary tasks and an equal period of 'normal' driving. Results indicate that the interaction with secondary tasks led to significant compensatory speed reductions. Multiple secondary tasks were shown to have a detrimental affect on vehicle performance with significantly reduced headways and increased brake pressure being found. The drivers reported interaction with the multiple in-vehicle systems to significantly impose more subjective mental workload than either a single secondary task or 'normal driving'. The implications of these findings and the need to integrate and manage complex in-vehicle information systems are discussed.     

A comparison of the cell phone driver and the drunk driver

OBJECTIVE: The objective of this research was to determine the relative impairment associated with conversing on a cellular telephone while driving. BACKGROUND: Epidemiological evidence suggests that the relative risk of being in a traffic accident while using a cell phone is similar to the hazard associated with driving with a blood alcohol level at the legal limit. The purpose of this research was to provide a direct comparison of the driving performance of a cell phone driver and a drunk driver in a controlled laboratory setting. METHOD: We used a high-fidelity driving simulator to compare the performance of cell phone drivers with drivers who were intoxicated from ethanol (i.e., blood alcohol concentration at 0.08% weight/volume). RESULTS: When drivers were conversing on either a handheld or hands-free cell phone, their braking reactions were delayed and they were involved in more traffic accidents than when they were not conversing on a cell phone. By contrast, when drivers were intoxicated from ethanol they exhibited a more aggressive driving style, following closer to the vehicle immediately in front of them and applying more force while braking. CONCLUSION: When driving conditions and time on task were controlled for, the impairments associated with using a cell phone while driving can be as profound as those associated with driving while drunk. APPLICATION: This research may help to provide guidance for regulation addressing driver distraction caused by cell phone conversations.     

Drivers’ Performance Examination using a Personalized Adaptive Curve Speed Warning: Driving Simulator Study

ABSTRACT

A great number of traffic accidents occur during curve negotiation maneuvers. Most of these accidents could be avoided if drivers are provided with information that better guide them through the maneuver. Advanced Driver Assistance Systems (ADAS) such as Curve Speed Warning (CSW) have shown to be effective to improve safety on curve maneuvers by warning drivers of the speed required to make a safe curve maneuver. The effectiveness of such warning systems can potentially improve if the warnings are not only adapted to road and traffic condition but also adapted to individual drivers’ behavior. In this study, an Adaptive Curve Speed Warning (ACSW) system is developed that presents drivers a two-level visual and audio warning considering the variation in individual drivers’ perception-reaction time (PRT). The warning timing is adjusted according to a reward/punishment function to reinforce safer actions while providing an individualized in-time warning. Next, within a driving simulator environment, drivers’ performance using ACSW is compared to a CSW that does not consider PRT variation among drivers. Further, variation in drivers’ performance on curve maneuvers is discussed with respect to drivers’ approaching speed, variation in PRT, and braking behavior. Results show that drivers’ interaction with warning systems varies significantly based on their age and gender. In addition, results show how drivers approaching speed to a curve varies significantly based on road characteristics such as curve advisory speed and curve direction. Results from this study contribute to the development of more intelligent ADAS that could improve drivers’ comfort and safety.     

Effects of advertising billboards during simulated driving

There is currently a great deal of interest in the problem of driver distraction. Most research focuses on distractions from inside the vehicle, but drivers can also be distracted by objects outside the vehicle. Major roads are increasingly becoming sites for advertising billboards, and there is little research on the potential effects of this advertising on driving performance. The driving simulator experiment presented here examines the effects of billboards on drivers, including older and inexperienced drivers who may be more vulnerable to distractions. The presence of billboards changed drivers’ patterns of visual attention, increased the amount of time needed for drivers to respond to road signs, and increased the number of errors in this driving task.     

Examining cognitive interference and adaptive safety behaviours in tactical vehicle control

Concurrent mental workload degrades some aspects of driving performance, but drivers might be able to modify their behaviour adaptively to accommodate cognitive impairments. For example, they might maintain longer vehicle headway in dual-task conditions to compensate for slowed response times. Studies documenting such adaptive behaviours typically use steady-state driving scenarios such as car following. Yet, driving often involves tactical control situations in which drivers need to monitor multiple aspects of their traffic environment and to accommodate changing goals. In two simulator experiments, this study examined the impact of mental workload on safety margins (distances) that drivers keep when engaged in a tactical control task: passing other vehicles. Although drivers did increase their headway adaptively when engaged in steady-state car following (experiment 2), they did not adapt their behaviour to accommodate cognitive load when performing tactical control manoeuvres. Implications of this difference between steady-state and tactical control driving contexts, both for driving research and for driving safety, are discussed.     

Using eye movements to evaluate effects of driver age on risk perception in a driving simulator

Novice drivers (16-year-olds with < or = 6 months' driving experience) have the highest crash involvement rates per 100 million vehicle miles (161 million vehicle km). In the past, this was attributed to greater risk taking or poorly developed psychomotor skills. More recently, however, their high crash involvement rate has been hypothesized to be attributable largely to their relative inability to acquire and assess information in inherently risky situations. The current study seeks to evaluate this hypothesis by recording eye movements while 72 participants (24 novice drivers, 24 younger drivers, and 24 older drivers) drove through 16 risky scenarios in an advanced driving simulator. There were significant age-related differences in driver scanning behavior, consistent with the hypothesis that novice drivers' scanning patterns reflect their failure to acquire information about potential risks and their consequent failure to deal with these risks. Actual or potential applications of this research include modification of these scenarios for display on a PC as a basis for a training module that would enable novice drivers to recognize risky scenarios before they encounter them on the road, in the hope of reducing their high fatality rate.     

Toward overtrust-free advanced driver assistance systems

Avoiding human overtrust in machines is a vital issue to establish a socially acceptable advanced driver assistance system (ADAS). However, research has not clarified the effective way of designing an ADAS to prevent driver overtrust in the system. It is necessary to develop a theoretical framework that is useful to understand how a human trust becomes excessive. This paper proposes a trust model by which overtrust can be clearly defined. It is shown that at least three types of overtrust are distinguished on the basis of the model. As an example, this paper discusses human overtrust in an adaptive cruise control (ACC) system. By conducting an experiment on a medium-fidelity driving simulator, we observed two types of overtrust among the three. The first one is that some drivers relied on the ACC system beyond its limit of decelerating capability. The second one is that a driver relied on the ACC systems by expecting that it could decelerate against a stopped vehicle. It is estimated through data analysis how those kinds of overtrust emerged. Furthermore, the possible ways for prevention of human overtrust in ADAS are discussed.     

Influence of age and proximity warning devices on collision avoidance in simulated driving

OBJECTIVE: We conducted a set of experiments to examine the utility of several different uni- and multimodal collision avoidance systems (CASs) on driving performance of young and older adult drivers in a high-fidelity simulator. BACKGROUND: Although previous research has examined the efficacy of different CASs on collision avoidance, there has been a dearth of studies that have examined such devices in different driving situations with different populations of drivers. METHOD: Several different CAS warnings were examined in varying traffic and collision configurations both without (Experiment 1a) and with (Experiment 2) a distracting in-vehicle task. RESULTS: Overall, collision avoidance performance for both potential forward and side object collisions was best for an auditory/visual CAS, which alerted drivers using both modalities. Interestingly, older drivers (60-82 years of age) benefited as much as younger drivers from the CAS, and sometimes they benefited more. CONCLUSION: These data suggest that CASs can be beneficial across a number of different driving scenarios, types of collisions, and driver populations. APPLICATION: These results have important implications for the design and implementation of CASs for different driver populations and driving conditions.     

Comparative evaluation of performance measures for human driving skills

In this paper, we evaluate the adequacy of several performance measures for the evaluation of driving skills between different drivers. This work was motivated by the need for a training system that captures the driving skills of an expert driver and transfers the skills to novice drivers using a haptic-enabled driving simulator. The performance measures examined include traditional task performance measures, e.g., the mean position error, and a stochastic distance between a pair of hidden Markov models (HMMs), each of which is trained for an individual driver. The emphasis of the latter is on the differences between the stochastic somatosensory processes of human driving skills. For the evaluation, we developed a driving simulator and carried out an experiment that collected the driving data of an expert driver whose data were used as a reference for comparison and of many other subjects. The performance measures were computed from the experimental data, and they were compared to each other. We also collected the subjective judgement scores of the driver’s skills made by a highly-experienced external evaluator, and these subjective scores were compared with the objective performance measures. Analysis results showed that the HMM-based distance metric had a moderately high correlation between the subjective scores and it was also consistent with the other task performance measures, indicating the adequacy of the HMM-based metric as an objective performance measure for driving skill learning. The findings of this work can contribute to developing a driving simulator for training with an objective assessment function of driving skills.