Speech Recognition and In-Vehicle Telematics Devices: Potential Reductions in Driver Distraction

Speech Recognition is frequently cited as a potential remedy to distraction resulting from drivers' operation of in-vehicle devices. This position typically assumes that the introduction of speech recognition will result in reduced cognitive workload and improved driving performance. Past research neither fully supports nor fully discounts this assumption. However, it is difficult to compare many of these studies, due to differences in device operation tasks, the pacing of those tasks, speech recognition system performance, and system interface designs. In an effort to directly address the effect of voice recognition on driver distraction, the present authors developed a capability to manipulate the performance characteristics of a speech recognition system through a Wizard of Oz speech recognition system and installed this system in a simulated driving environment. The sensitivity of the simulated driving environment and speech recognition accuracy manipulation were evaluated in an initial study comparing driver cognitive workload and driving performance during self-paced simulated operation of a personal digital assistant (PDA) during no PDA use, manual control of the PDA, and speech control of the PDA. In the Speech PDA condition, speech recognition accuracy was varied between drivers. Analysis of drivers' emergency braking response times and rated cognitive workload revealed significantly lower cognitive demand and better performance in the No PDA condition when compared to the Manual PDA condition. The Speech PDA condition resulted in response times and rated cognitive workload levels that were between the No PDA and Manual PDA conditions, but not significantly different from either of these conditions. Further analysis of emergency braking performance revealed a non-significant trend towards better performance in conjunction with higher speech recognition accuracy levels. The potential for reducing driver distraction through the careful development and evaluation of speech recognition systems is discussed.     

Computational intelligent brain computer interaction and its applications on driving cognition

Driving is one of the most common attention-demanding tasks in daily life. Driver's fatigue, drowsiness, inattention, and distraction are reported a major causal factor in many traffic accidents. Due to the drivers lost their attention, they had markedly reduced the perception, recognition and vehicle control abilities. In recent years, many computational intelligent technologies were developed for preventing traffic accidents caused by driver's inattention. Driver's drowsiness and distraction related studies had become a major interest research topic in automotive safety engineering. Many researches had investigated the driving cognition in cognitive neuro-engineering, but how to utilize the main findings of driving-related cognitive researches in traditional cognitive neuroscience and integrate with computational intelligence technologies for augmenting driving performance will become a big challenge in the interdisciplinary research area. For this reason, we attempt to integrate the driving cognition for real life application in this study. The implications of the driving cognition in cognitive neuroscience and computational intelligence for daily applications are also demonstrated through two common attention-related driving studies: (1) cognitive-state monitoring of the driver performing the realistic long-term driving tasks in a simulated realistic-driving environment; and (2) to extract the brain dynamic changes of driver's distraction effect during dual-task driving. Experimental results of these studies provide new insights into the understanding of complex brain functions of participants actively performing ordinary tasks in natural body positions and situations within real operational environments.     

司机分心驾驶检测研究进展

随着车辆工业和世界经济的快速发展,私家汽车数量不断增加,导致交通事故越来越多,且交通安全问题已经成为全球关注的焦点问题。司机分心驾驶检测的研究主要分为传统计算机视觉（CV）算法和深度学习算法两种。基于传统CV算法的司机分心检测通过尺度不变特征转换（SIFT）、方向梯度直方图（HOG）等特征算子提取图像特征,然后结合支持向量机（SVM）建立模型并对图像进行分类。然而传统CV算法具有对环境的要求高、运用范围较窄、参数多、计算量大的缺点。近年来深度学习在提取数据特征方面表现出速度快、精度高等优异的性能,因此研究人员开始将深度学习引入到司机分心驾驶检测中。基于深度学习的方法可以实现端到端的司机分心驾驶检测网络,而且取得了很高的准确度。介绍了传统CV算法和深度学习算法在司机分心驾驶检测的研究现状,首先,阐释了传统CV算法用于图像领域和司机分心驾驶检测研究的情况;接着,介绍了基于深度学习的司机分心驾驶研究;而后,从准确度、模型参数量等方面对不同司机分心驾驶检测方法进行比较分析;最后,对现有的研究进行了总结并提出了未来司机分心驾驶检测需要解决的三个问题：驾驶过程中司机分心状态以及分心程度划分规范需进一步完善,需要综合考虑人－车－路三者以及如何才能更有效地减少神经网络参数。     

Biomechanical patterns of text-message distraction

The objective of this study was to identify biomechanical measures that can distinguish texting distraction in a laboratory-simulated driving environment. The goal would be to use this information to provide an intervention for risky driving behaviour. Sixteen subjects participated in this study. Three independent variables were tested: task (texting, visual targeting, weighted and non-weighted movements), task direction (front and side) and task distance (close and far). Dependent variables consisted of biomechanical moments, head displacement and the length of time to complete each task. Results revealed that the time to complete each task was higher for texting compared to other tasks. Peak moments during texting were only distinguishable from visual targeting. Peak head displacement and cumulative biomechanical exposure measures indicated that texting can be distinguished from other tasks. Therefore, it may be useful to take into account both temporal and biomechanical measures when considering warning systems to detect texting distraction.     

Identification of aggressive driving behavior of online car-hailing drivers based on association classification

With the rapid development of online car-hailing, the related crashes have become a key issue with public concern. Identifying and predicting aggressive driving behaviors is critical to reduce traffic crashes. In this study, we propose a method to recognize aggressive driving behavior based on association classification, with multisource features being employed, including driver emotion, vehicle kinematic characteristics, and road environment. The model performs best in a 10-fold cross-test when the minimum support and minimum confidence are set as 0.01 and 0.8, respectively. Besides, we also compare the performance of aggressive driving behavior recognition classifiers constructed using association classification with other rule-based classification methods, including ID3, C4.5, CART, and Random Forest. The results show that association classification performs better than other classification competitors. Thirty-six if–then rules generated by the association classification are used to analyze the influencing factors and associated mechanisms of aggressive driving behavior. It is found that aggressive driving behavior is highly correlated with driver anger and disgust emotions. Aggressive driving behavior is more likely to occur when no passengers are in the car than the case with passengers. Driver entertainment behavior and passenger interference also affect driving behavior. Moreover, drivers are prone to aggressive driving when making a U-turn. This research not only proposed a new identification method for aggressive driving behavior but also provided a comprehensive understanding of the associated influencing factors which thus benefit the further research and development of safety assistance driving devices.     

Distraction pattern classification and comparisons under different conditions in the full-touch HMI mode

Understanding driver distraction patterns is an important part of human–machine interaction (HMI), which is beneficial for the development of control strategies in human–machine co-driving systems. However, comparatively few studies have focused on driver distraction patterns. To address this issue, this study proposes a framework to characterize distraction patterns using glance behavior and manual behavior, and classifies distraction patterns into: aggressive, moderate, and conservative patterns based on real road experiments. Subsequently, differences in distraction behavior and effects on lateral vehicle control ability across distraction pattern groups, as well as distraction behavior differences exhibited by drivers in the same distraction pattern group under different conditions, are analyzed. Firstly, the results show that the aggressive distraction patterns have a smaller number of eyes-off-road (NoEOR) incidences but longer mean single eyes-off-road time (MSEORT), maximum single eyes-off-road time (MaxEORT) and a higher percentage of long eyes-off-road (PoLEOR) incidences than the other patterns. There are slight differences in the single eyes-off-road times (EORTs) between the conservative and moderate patterns and in the manual behavior for the aggressive and moderate distraction patterns. Secondly, the same distraction pattern exhibited by drivers for different road and secondary task conditions has differences in terms of the behavioral performance. Finally, there is few differences in the lateral motion of a vehicle with different distraction patterns. Surprisingly, the standard deviation of the steering wheel angle (SDSWA) is the smallest in the aggressive distraction pattern.     

Drivers’ attitudes,preference, and acceptance of in-vehicle anger intervention systems and their relationships to demographic and personality characteristics

This research conducted focus group interviews and a questionnaire survey to investigate the potential demand of drivers for anger intervention systems (AISs) and explore the effects of demographic factors and personality traits on the preference and attitudes toward AISs. Results indicate that drivers prefer auditory intervention over tactile and visual interventions. Moreover, they favor emotion recording features but also have negative attitudes about accuracy and system security. In addition, age and some personality traits (i.e., types of driving anger and categories of driving anger expressions) play an important role in predicting the preference of intervention modalities or attitudes toward AISs and provide a new perspective on designing customized intervention systems. The outcome of this research provides practical implications regarding the design of in-vehicle anger intervention systems for the automotive industry to reduce drivers’ anger and improve driving safety.     

Modeling of operators' emotion and task performance in a virtual driving environment

Emotional human–computer interactions are attracting increasing interest with the improvement in the available technology. Through presenting affective stimuli and empathic communication, computer agents are able to adjust to users' emotional states. As a result, users may produce better task performance. Existing studies have mainly focused on the effect of only a few basic emotions, such as happiness and frustration, on human performance. Furthermore, most research explored this issue from the psychological perspective. This paper presents an emotion and performance relation model in the context of vehicle driving. This general emotion–performance model is constructed on an arousal–valence plane and is not limited to basic emotions. Fifteen paid participants took part in two driving simulation experiments that induced 115 pairs of emotion–performance sample. These samples revealed the following: (1) driving performance has a downward U-shaped relationship with both intensities of arousal and valence. It deteriorates at extreme arousal and valence. (2) Optimal driving performance, corresponding to the appropriate emotional state, matches the “sweet spot” phenomenon of the engagement psychology. (3) Arousal and valence are not perfectly independent across the entire 2-D emotion plane. Extreme valence is likely to stimulate a high level of arousal, which, in turn, deteriorates task performance. The emotion–performance relation model proposed in the paper is useful in designing emotion-aware intelligent systems to predict and prevent task performance degradation at an early stage and throughout the human–computer interactions.     

The impact of distraction mitigation strategies on driving performance

OBJECTIVES: An experiment was conducted to assess the effects of distraction mitigation strategies on drivers' performance and productivity while engaged in an in-vehicle information system task. BACKGROUND: Previous studies show that in-vehicle tasks undermine driver safety and there is a need to mitigate driver distraction. METHOD: An advising strategy that alerts drivers to potential dangers and a locking strategy that prevents the driver from continuing the distracting task were presented to 16 middle-aged and 12 older drivers in a driving simulator in two modes (auditory, visual) and two road conditions (curves, braking events). RESULTS: Distraction was a problem for both age groups. Visual distractions were more detrimental than auditory ones for curve negotiation, as depicted by more erratic steering, F (6, 155) = 26.76, p < .05. Drivers did brake more abruptly under auditory distractions, but this effect was mitigated by both the advising, t (155) = 8.37, p < .05, and locking strategies, t (155) = 8.49, p < .05. The locking strategy also resulted in longer minimum time to collision for middle-aged drivers engaged in visual distractions, F (6, 138) = 2.43, p < .05. CONCLUSIONS: Adaptive interfaces can reduce abrupt braking on curve entries resulting from auditory distractions and can also improve the braking response for distracted drivers. APPLICATION: These strategies can be incorporated into existing in-vehicle systems, thus mitigating the effects of distraction and improving driver performance.     

Examining the impact of cell phone conversations on driving using meta-analytic techniques

OBJECTIVE: The performance costs associated with cell phone use while driving were assessed meta-analytically using standardized measures of effect size along five dimensions. BACKGROUND: There have been many studies on the impact of cell phone use on driving, showing some mixed findings. METHODS: Twenty-three studies (contributing 47 analysis entries) met the appropriate conditions for the meta-analysis. The statistical results from each of these studies were converted into effect sizes and combined in the meta-analysis. RESULTS: Overall, there were clear costs to driving performance when drivers were engaged in cell phone conversations. However, subsequent analyses indicated that these costs were borne primarily by reaction time tasks, with far smaller costs associated with tracking (lane-keeping) performance. Hands-free and handheld phones revealed similar patterns of results for both measures of performance. Conversation tasks tended to show greater costs than did information-processing tasks (e.g., word games). There was a similar pattern of results for passenger and remote (cell phone) conversations. Finally, there were some small differences between simulator and field studies, though both exhibited costs in performance for cell phone use. CONCLUSION: We suggest that (a) there are significant costs to driver reactions to external hazards or events associated with cell phone use, (b) hands-free cell phones do not eliminate or substantially reduce these costs, and (c) different research methodologies or performance measures may underestimate these costs. APPLICATION: Potential applications of this research include the assessment of performance costs attributable to different types of cell phones, cell phone conversations, experimental measures, or methodologies.     

In-car usage-based insurance feedback strategies. A comparative driving simulator study

Usage-Based Insurances (UBI) enable policyholders to actively reduce the impact of vehicle insurance costs by adopting a safer and more eco-friendly driving style. UBI is especially relevant for younger drivers, who are a high-risk population. The effectiveness of UBI should be enhanced by providing in-car feedback optimised for individual drivers. Thirty young novice drivers were therefore invited to complete six experimental drives with an in-car interface that provided real-time information on rewards gained, their driving behaviour and the speed limit. Reward size was either displayed directly in euro, indirectly as a relatively large amount of credits, or as a percentage of the maximum available bonus. Also, interfaces were investigated that provided partial information to reduce the potential for driver distraction. Compared to a control no-UBI condition, behaviour improved similarly across interfaces, suggesting that interface personalisation after an initial familiarisation period could be feasible without compromising feedback effectiveness.

Practitioner Summary: User experiences and effects on driving behaviour of six in-car interfaces were compared. The interface provided information on driving behaviour and rewards in a UBI setting. Results suggest that some personalisation of interfaces may be an option after an initial familiarisation period as driving behaviour improved similarly across interfaces.     

Don’t Cry While You’re Driving: Sad Driving Is as Bad as Angry Driving

While driving research on affect has mostly focused on anger and road rage, there has been little empirical research on other affective states. Affect researchers widely acknowledge the “sadder but wiser” phenomenon, but there is little evidence if this tendency can be applied to the driving environment as well. The objective of the present study is to empirically test whether sadness enhances driving performance as the sadder but wiser notion might predict or sadness impairs driving performance as its negative valence or low arousal dimension might predict. The study consists of a simulated driving experiment with induced anger, sadness, and neutral affect to examine how anger and sadness influence driving-related risk perception, driving performance, and perceived workload. Sixty-one young drivers drove under three different road conditions with either induced anger, sadness, or neutral affect conditions. After affect induction, there was no difference in subjective risk perception across three affect conditions. However, participants in both affect conditions showed significantly more errors and took longer driving time than those in the neutral condition. Only participants with induced anger reported significantly higher physical workload and frustration than participants with neutral affect. Results are discussed in terms of affect mechanisms, design directions for the in-vehicle affect mitigation system, and limitations of the study.     

Effects of voice technology on test track driving performance: implications for driver distraction

This work compares the degradation in driving performance associated with secondary tasks performed with voice-based and visual/manual interfaces, including radio tuning, phone dialing, and more complex tasks involving a sequence of interactions with an in-vehicle computer system. Twenty-one participants drove an instrumented vehicle while performing a combination of car-following, peripheral target detection, and secondary tasks on a closed test track. Drivers compensated for increased task demands associated with secondary tasks by increasing their following distance. Performing secondary tasks also resulted in significant decrements to vehicle control, target detection, and car-following performance. The voice-based interface helped reduce the distracting effects of secondary task performance. Modest improvements were observed for measures of vehicle control and target detection but not for car following. The results indicated that performing in-vehicle tasks required diversion of both peripheral (visual and manual) and attentional (cognitive) resources from driving. The voice-based interface reduced the peripheral impairment but did not appreciably reduce the attentional impairment. Actual or potential applications of this research include improvements to the design of invehicle information systems and the development of evaluation protocols to assess their distraction potential.     

Occlusion as a measure for visual workload: an overview of TNO occlusion research in car driving

A process-oriented approach by systematically studying driver performance, distraction, and workload is the way to go for assessing safety effects of new telematics applications in vehicles. These systems may strive for drivers' attention and possibly lead to distraction from the primary task. Visual occlusion techniques appear to be an effective means of studying drivers' visual information processing performance. Studies to illustrate this include identifying the minimum visual information drivers need for driving (asking for visual information) and the evaluation of driver support systems such as heading control and adaptive cruise control with respect to visual workload. In other applications the occlusion technique is used to exclude 'visual array' information from the optic flow field. The temporary exclusion of part of the visual field of view was applied in evaluating the effects of different types of driver's side rearview mirrors.     

Speed-of-processing and driving simulator training result in improved driving performance

Useful field of view, a measure of processing speed and spatial attention, can be improved with training. We evaluated the effects of this improvement on older adults' driving performance. Elderly adults participated in a speed-of-processing training program (N = 48), a traditional driver training program performed in a driving simulator (N = 22), or a low-risk reference group (N = 25). Before training, immediately after training or an equivalent time delay, and after an 18-month delay each participant was evaluated in a driving simulator and completed a 14-mile (22.5-km) open-road driving evaluation. Speed-of-processing training, but not simulator training, improved a specific measure of useful field of view (UFOV), transferred to some simulator measures, and resulted in fewer dangerous maneuvers during the driving evaluation. The simulator-trained group improved on two driving performance measures: turning into the correct lane and proper signal use. Similar effects were not observed in the speed-of-processing training or low-risk reference groups. The persistence of these effects over an 18-month test interval was also evaluated. Actual or potential applications of this research include driver assessment and/or training programs and cognitive intervention programs for older adults.     

Effects of using head-up display in automobile context on attention demand and driving performance

This study aimed to investigate the difference in driving performance between drivers’ attention on the head-up display (HUD)/road under low/high road conditions via a driving simulator experiment. Experimental driving included four driving scenarios with attention-on-the-HUD followed by attention-on-the-road or vice versa under high or low driving load conditions. Each scenario took about a 30-min driving consisting of two 15-min sections for each attention location. Forty-eight participants, divided into four groups, drove one of the four scenarios once. Besides driving safely within speed limit, participants were also required to perform detection task and speed limit sign response task. Results revealed that drivers paying attention to the HUD, under both low and high driving load conditions, reacted faster to speed limit sign changes than when paying attention to the road. In addition, attention-to-the-HUD under low driving load condition caused the smallest variation in steering wheel angle and lateral acceleration. These differences can be attributed to the driver's enhanced awareness and the cognitive capture effect, and tended to diminish with increasing driving workload. Finally, attention shift of drivers and the so-called novelty effect for using new technology product were also found.     

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.     

Round-trip driving effects on driving performances and mental workload under different traffic rules

This study investigates the effect of switching between different traffic rules (left-versus right-hand traffic) on driving performance and mental workload. A driving simulation environment was developed according to the real environment. Two urban roads with different traffic systems were simulated. Twenty participants executed intersection turns and continuous car-following behavior in four simulated driving stages, including driving with familiar, unfamiliar, second time unfamiliar, and back to familiar traffic rules. The mean and standard deviations for speed, distance headway, and the standard deviation of lateral position were recorded as driving performance. Mental workload was determined using the NASA-TLX and Rating Scale Mental Effort questionnaires. One-way analysis of variance was used to evaluate the differences between the four driving stages using subjective and objective measures. The results showed that significant differences were obtained in all measures when driving in the four driving situations, except for the speed standard deviation. The car-following behavior was the most unsafe (significantly larger standard deviations for distance headway and mental workload) when driving in unfamiliar road traffic compared with the other stages. When driving under unfamiliar traffic rules for the second time, the mental workload was significantly relieved and the lane-keeping ability significantly improved. The results indicated that providing an adaptive runway for drivers to familiarize themselves with different traffic rules is necessary to improve driving performance and safety. These findings provide useful information for designing bridges linking two places with different traffic rules to increase traffic safety.     

Learning the Lane Change Task: comparing different training regimes in semi-paced and continuous secondary tasks

For road safety it is paramount that distraction by in-vehicle systems is limited. To reach this aim the Lane Change Task (LCT; Mattes, 2003) was developed. It is used as a test procedure to measure distraction due to secondary tasks in driving. The LCT is implemented as an ISO standard (ISO 26022: 2010) with the aim to provide an objective criterion for designing human-machine interactions (HMI) in a way which is not detrimental to driving. As different baseline performance in the LCT could not be sufficiently explained in recent studies, comparisons of different training regimes were conducted in order to examine training influences on LCT performance. Discriminable performance improvements in LCT were found depending on the secondary task used. A training regime of at least ten runs of LCT in single-task mode is recommended for effective training. This training should be supplemented by a training of the secondary tasks examined. An additional exploration of a dual-task situation is recommended.     

Mobile phones and driving: a review of contemporary research

This study reviews research on the effects of using a mobile phone when driving. First, it is should be pointed out that the availability of a mobile phone in a car is of great value, for example, in emergencies and accidents. However, the results from the research covered in this review show that using a mobile phone in a car while driving impairs driving performance significantly. To exemplify, a drivers attention to traffic and traffic information is impaired and the control of the car becomes less precise and smooth when talking over a phone. The conversation in itself impairs attention and manoeuvring performance as well as the motor activities needed for phoning. Based on the research available, the present review gives numerical estimates of the disturbing effects of different aspects of mobile phoning on driving performance. Contrary to what people assume, hand-held phones have not been shown to impair driving quality more than hands free phones. Instead, in contrast to public opinion, the content of a conversation is most important in determining the degree of distraction; complex conversations disturb driving much more than simple conversations. Analyses of accidents have shown that the impairment of driving while phoning leads to an increased risk of having an accident for both hand-held and hands free mobile telephones.