The research in advanced driver assistance systems (ADAS) has progressed to design architectures for driver specific performance. Personalised ADASs in this aspect have been developed with adaptation ...to driver attributes, state, style, behaviour, skill and so on. For the lane keeping task, the driver driving style while navigating a high/low curvature track plays an important part in the design of a lane keeping assist system. Considering this aspect, a robust co-operative control approach is formulated to design a personalised lane keeping assist with adaptation to driver style. Based on statistical analysis of lateral jerk and steer feel, a fuzzy rule based identification procedure for the classification of the driver style as clam, moderate, aggressive or very aggressive is designed. Using the identified driving style, a modulation function is proposed to adapt the assist torque. The assist torque is generated based on a robust higher order sliding mode approach as a feedback control for the driver-vehicle system. Closed-loop stability of the proposed driver-vehicle design in the presence of disturbances is established. Co-operative control between human driver-autonomous controller for the lane keeping task over the Satory test track with adaption to driver style is then shown for validation of the proposed architecture.
•Snapchat while driving was prevalent social media behaviour in focus groups.•Legal sanctions had little impact on Snapchat while driving.•Not being caught predicts the use of Snapchat while ...driving.•Belief of safely being able to use Snapchat while driving predicts the behaviour.
This research utilised a qualitative and quantitative study to examine a sample of young drivers’ perceptions of deterrent forces, both legal and non-legal, for the behaviour of phone use while driving. First, focus groups were conducted with 60 drivers between the ages of 17 and 25 years who resided in Queensland, Australia. This qualitative study utilised an inductive approach to elicit participants’ perceptions without omitting important ideas. Legal sanctions were associated with low perceptions of enforcement certainty. Meanwhile, the only non-legal sanction to emerge was the concept of “safety”; many participants were deterred from using their phone while driving for fear of injury or death to themselves or others. The types of social media most likely to be engaged in were explored and sending videos or photos via the application Snapchat emerged as the most common social media application used among the sample. Consequently, the subsequent quantitative study focused on deterrent forces associated with Snapchat use while driving. A survey was utilised with a separate sample of young drivers aged 17–25 years (n = 503). The impact of the threat of legal sanctions on Snapchat use while driving was examined through classical deterrence theory and Stafford and Warr’s (1993) reconceptualised deterrence theory. The non-legal factor of perceived safety was also included in the quantitative study. None of the classical deterrence variables (e.g., certainty, severity and swiftness) reached significance while all the reconceptualised deterrence variables (e.g., direct and indirect punishment and punishment avoidance), as well as perceived safety, were significant predictors of Snapchat use while driving. It is suggested that perceptions of certainty of apprehension need to be increased for phone use while driving. The findings show the current impact of deterrent initiatives for phone use while driving as well as provide the first examination of deterrents for the specific mobile phone behaviour of Snapchat use while driving.
•Classical deterrence theory has three elements: certainty, severity and swiftness.•Geographical context affects the perceptions of certainty.•Those from regional areas less likely to believe they ...will be caught breaking rules.•Young drivers believe enforcement cameras increase the certainty they will be caught.•Police agencies should take actions to increase perceptions regarding certainty.
Deterrence theory is the predominant theory used to underpin road policing initiatives. However, survey research indicates that this approach may not be as effective for young drivers. This study uses focus groups, conducted in both metropolitan and regional locations in two Australian states (Queensland and Victoria), to explore three components of classical deterrence theory: certainty, severity & swiftness. The results suggest that geographical context affected perceptions of certainty with individuals from regional locations less likely to indicate that they would be caught by police for committing a traffic offence. Additionally, the use of cameras to detect road offences increased perceptions of certainty for young drivers. The results of this study suggest that police agencies should focus on undertaking actions to increase the perceptions of certainty swiftness and severity of punishment, particularly in regional areas, for young drivers who engage in illegal behaviour on the road. Where appropriate, these actions should take into account the geographical context. There may also be value in considering augmenting deterrence theory with other theoretical perspectives for this group.
This paper presents a novel single-switch discontinuous current-source gate driver (CSD) with voltage boosting capability appropriate for ultra-low voltage applications. The power MOSFET gate current ...using this CSD does not deviate during both turn-on and turn-off transitions. Thus, in comparison to the previous CSDs, the effective gate current is much higher and nearly constant during switching transitions, which would reduce both turn-on and turn-off transient intervals and consequently the switching losses. Other advantages of this CSD are low number of components, high Cdv/dt immunity and the ability to increase the gate-source voltage to more than the gate-drive source voltage which reduces the <inline-formula><tex-math notation="LaTeX">\mathbf {R_{DS(on)}}</tex-math></inline-formula> (drain-source on-resistance). The power MOSFET fast transition intervals and low <inline-formula><tex-math notation="LaTeX">\mathbf {R_{DS(on)}}</tex-math></inline-formula> have contributed to improved efficiency. The proposed CSD is analyzed and theoretical analysis is verified by the stimulation and experimental results at 1MHz.
Driver fatigue and inattention have long been recognised as the main contributing factors in traffic accidents. This study presents a novel system which applies convolutional neural network (CNN) to ...automatically learn and predict pre-defined driving postures. The main idea is to monitor driver hand position with discriminative information extracted to predict safe/unsafe driving posture. In comparison to previous approaches, CNNs can automatically learn discriminative features directly from raw images. In the authors' works, a CNN model was first pre-trained by an unsupervised feature learning method called sparse filtering, and subsequently fine-tuned with classification. The approach was verified using the Southeast University driving posture dataset, which comprised of video clips covering four driving postures, including normal driving, responding to a cell phone call, eating, and smoking. Compared with other popular approaches with different image descriptors and classification methods, the authors' scheme achieves the best performance with an overall accuracy of 99.78%. To evaluate the effectiveness and generalisation performance in more realistic conditions, the method was further tested using other two specially designed datasets which takes into account of the poor illuminations and different road conditions, achieving an overall accuracy of 99.3 and 95.77%, respectively.
Objective:
The aim of this study was to outline a conceptual framework for understanding driving style and, on this basis, review the state-of-the-art research on driving styles in relation to road ...safety.
Background:
Previous research has indicated a relationship between the driving styles adopted by drivers and their crash involvement. However, a comprehensive literature review of driving style research is lacking.
Method:
A systematic literature search was conducted, including empirical, theoretical, and methodological research, on driving styles related to road safety.
Results:
A conceptual framework was proposed whereby driving styles are viewed in terms of driving habits established as a result of individual dispositions as well as social norms and cultural values. Moreover, a general scheme for categorizing and operationalizing driving styles was suggested. On this basis, existing literature on driving styles and indicators was reviewed. Links between driving styles and road safety were identified and individual and sociocultural factors influencing driving style were reviewed.
Conclusion:
Existing studies have addressed a wide variety of driving styles, and there is an acute need for a unifying conceptual framework in order to synthesize these results and make useful generalizations. There is a considerable potential for increasing road safety by means of behavior modification. Naturalistic driving observations represent particularly promising approaches to future research on driving styles.
Application:
Knowledge about driving styles can be applied in programs for modifying driver behavior and in the context of usage-based insurance. It may also be used as a means for driver identification and for the development of driver assistance systems.
•An ensemble Bi-directional LSTM model is proposed for driver intention inference.•Driver lane change intention can be precisely predicted before the acutal maneuver.•Driver lane change behavior and ...critical moments are statistically analyzed.•The proposed EBiRNN method show advantages over conventional methods.•Different prediction horizons and real-time inference results are analyzed.
With the rapid development of intelligent vehicles, drivers are increasingly likely to share their control authorities with the intelligent control unit. For building an efficient Advanced Driver Assistance Systems (ADAS) and shared-control systems, the vehicle needs to understand the drivers’ intent and their activities to generate assistant and collaborative control strategies. In this study, a driver intention inference system that focuses on the highway lane change maneuvers is proposed. First, a high-level driver intention mechanism and framework are introduced. Then, a vision-based intention inference system is proposed, which captures the multi-modal signals based on multiple low-cost cameras and the VBOX vehicle data acquisition system. A novel ensemble bi-directional recurrent neural network (RNN) model with Long Short-Term Memory (LSTM) units is proposed to deal with the time-series driving sequence and the temporal behavioral patterns. Naturalistic highway driving data that consists of lane-keeping, left and right lane change maneuvers are collected and used for model construction and evaluation. Furthermore, the driver's pre-maneuver activities are statistically analyzed. It is found that for situation-aware, drivers usually check the mirrors for more than six seconds before they initiate the lane change maneuver, and the time interval between steering the handwheel and crossing the lane is about 2 s on average. Finally, hypothesis testing is conducted to show the significant improvement of the proposed algorithm over existing ones. With five-fold cross-validation, the EBiLSTM model achieves an average accuracy of 96.1% for the intention that is inferred 0.5 s before the maneuver starts.
•Automated driving has the potential to improve traffic safety in the long term.•For the foreseeable future, partially AD present unwitting consequences.•Drivers’ role will change and lead to ...potential confusion or traffic conflicts.•Human factors research is needed address new questions of partial automation.•Integration within the broader cyber-physical world is an emerging challenge.•This paper identifies areas that require explicit and urgent scientific exploration.
Driver assist technologies have reached the tipping point and are poised to take control of most, if not all, aspects of the driving task. Proponents of automated driving (AD) are enthusiastic about its promise to transform mobility and realize impressive societal benefits. This paper is an attempt to carefully examine the potential of AD to realize safety benefits, to challenge widely-held assumptions and to delve more deeply into the barriers that are hitherto largely overlooked. As automated vehicle (AV) technologies advance and emerge within a ubiquitous cyber-physical world they raise additional issues that have not yet been adequately defined, let alone researched. Issues around automation, sociotechnical complexity and systems resilience are well known in the context of aviation and space. There are important lessons that could be drawn from these applications to help inform the development of automated driving. This paper argues that for the foreseeable future, regardless of the level of automation, a driver will continue to have a role. It seems clear that the benefits of automated driving, safety and otherwise, will accrue only if these technologies are designed in accordance with sound cybernetics principles, promote effective human-systems integration and gain the trust by operators and the public.
This is the sixth in a series of reviews of research on graduated driver licensing (GDL) published in the Journal of Safety Research, the present review covering the period mid-2012 through 2016. In ...the two decades since GDL programs began to be introduced on a widespread basis in the United States, a vast amount of research has been published. The current review discusses recent research and the present state of knowledge on the following topics: characteristics of the novice driver population; effects of GDL on crashes for ages 16–19; the learner and intermediate periods; night and passenger restrictions; cellphone laws; GDL for older novices; enforcement of GDL rules; and programs attempting to influence GDL compliance and safe driving practices in general. GDL stands out as a successful policy for reducing teen driver crashes and is worth building on to extend its benefits. Strengthening existing GDL programs has the most potential for producing further crash reductions.
Introduction: In mid-2007 the State of New South Wales (NSW) in Australia introduced modifications to the existing graduated driver licensing system, lengthening the mandatory number of supervised ...hours for learner drivers aged under 25 years from 50 to 120 and extending the minimum learner period from 6 to 12 months. Additional driving restrictions were also introduced for young drivers in the two provisional licensed periods, P1, P2. This paper aims to evaluate this change by comparing the crash and offense experiences of young learner drivers before and after it occurred. Method: From driver licensing files supplied by the NSW transport authority two cohorts of persons obtaining their initial learner's permits in the year prior to the changes and in the subsequent year were constructed with demographic data, dates of transition to the driving phases, dates of crashes, and dates and types of traffic offenses. Both cohorts comprised around 100,000 individuals. Crash rates per 100 years of person-time under observation post P1 with their standard errors were calculated. Using a survival-analytic approach the proportion of crashes of all types were graphed in three month periods post P1. Sexes were treated separately as were initial learner ages of 16, 17, 18–21, and 22–24 years. The distribution of traffic offense types during P1 and P2 phases were also compared. With such large numbers formal statistical testing was avoided. Results: No meaningful differences in the crash or offense experiences of the two cohorts in either sex or at any age were observed. Delaying progress to unsupervised driving has road safety benefits. Conclusions: At least in conditions similar to those in NSW, requiring more than 50 h of supervised driving seems to have few road safety benefits. Practical applications: Licensing authorities should be cautious in extending the mandated number of supervised driving hours beyond 50.
•We evaluated changes in 2007 to the graduated driver licensing system in an Australian state from its licensing database.•Crash and offence profiles of affected learners licensed in the years prior to and after the changes were compared.•No substantial year to year changes were observed in the crash rates, probabilities of crashing or offense distributions.