Augmenting Policy Making for Autonomous Vehicles Through Geoinformatics and Psychographics

Conference Paper · August 2018with 27 Reads 
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
DOI: 10.1109/Agro-Geoinformatics.2018.8475980
Conference: 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics)
Cite this publication

Do you want to read the rest of this conference paper?

Request Full-text Paper PDF
ResearchGate has not been able to resolve any citations for this publication.
  • National Survey on Distracted Driving Attitude and Behaviours
    • P Schroeder
    • M Wilbur
    • R Peña
  • Ten Ways Autonomous Driving Could Redefine the Automotive world
    • B Michele
    • W Dominik
  • Modeling pedestrian crossing speed profiles considering speed change behavior for the safety assessment of signalized intersections
    • W Iryo-Asano
    • Miho
  • Article
    Fatigued driving contributes to a substantial number of motor vehicle accidents each year. Music listening is often employed as a countermeasure during driving in order to mitigate the effects of fatigue. Though music listening has been established as a distractor in the sense that it increases cognitive load during driving, it is possible that increased cognitive load is desirable under particular circumstances. For instance, during situations that typically result in cognitive underload, such as driving in a low-traffic monotonous stretch of highway, it may be beneficial for cognitive load to increase, thereby necessitating allocation of greater cognitive resources to the task of driving and attenuating fatigue. In the current study, we employed a song-naming game as a countermeasure to fatigued driving in a simulated monotonous environment. During the first driving session, we established that driving performance deteriorates in the absence of an intervention following 30min of simulated driving. During the second session, we found that a song-naming game employed at the point of fatigue onset was an effective countermeasure, as reflected by simulated driving performance that met or exceeded fresh driving behavior and was significantly better relative to fatigued performance during the first driving session.
  • Article
    The subjective categories that drivers use to distinguish between different road types have been shown to influence the speeds they choose to drive but as yet we do not understand the road features that drivers use to make their discriminations. To better understand how drivers describe and categorise the roads they drive, 55 participants were recruited to drive a video of familiar urban roads in a driving simulator at the speed they would drive these roads in their own cars (using the accelerator and brake pedal in the driving simulator to adjust their speed). The participants were then asked to sort photos of the roads they had just driven into piles so that their driving would be the same on all roads in one pile but different to the other piles. Finally, they answered a series of questions about each road to indicate what speed they would drive, the safe speed for the road, their speed limit belief as well as providing ratings of comfort, difficulty and familiarity. Overall, drivers' categorisation of roads was informed by a number of factors including speed limit belief, road features and markings (including medians), road width, and presence of houses, driveways and footpaths. The participants' categories were congruent with what they thought the speed limits were, but not necessarily the actual speed limits. Mismatches between actual speed limits and speed limit beliefs appeared to result from category-level expectations about speed limits that took precedence over recent experience in the simulator. Roads that historically had a 50km/h speed limit but had been reduced to 40km/h were still regarded as 50km/h roads by the participants, underscoring the point that simply posting a sign with a lower speed limit is not enough to overcome drivers' expectations and habits associated with the visual appearance of a road. The findings provided insights into how drivers view and categorise roads, and identify specific areas that could be used to improve speed limit credibility.
  • Article
    Full-text available
    Background: Few previous studies have directly compared crash rates of older and younger novice drivers. To inform discussion about whether Graduated Driver Licensing (GDL) policies that are applied in the US for younger novice drivers should be applied to older novice drivers, we conducted a longitudinal study to examine overall, nighttime, and multiple passenger crash rates over the initial four years of licensure differ for novice drivers licensed at different ages. Methods: Using data from the New Jersey Traffic Safety Outcomes (NJ-TSO) data warehouse, we selected all NJ drivers who obtained their initial intermediate driver's license from 2006 through 2014 and had at least one month of follow-up from the date of licensure to study end or death (n=1,034,835). Novice drivers were grouped based on age at licensure: age 17; 18-20; 21-24; and 25 or older. We estimated monthly rates for overall crashes (per 10,000 licensed drivers) as well as: late night crashes (11:01 p.m.-4:59 a.m.); early night crashes (9:00 p.m.-11:00 p.m.); and multiple passenger crashes (two or more passengers). Average monthly rates were calculated for specific relevant time periods and Poisson regression models were used to compare rates: (1) between novice driver groups with the same time since licensure; (2) over the first 48 months of licensure within each novice driver group; and (3) between same-aged 21-year-old drivers with varying lengths of licensure. Results: Although initial (three months post-licensure) overall crash rates of novice NJ drivers age 21 and older were higher than rates of same-aged experienced drivers, they were substantially lower than initial rates for 17- to 20-year-old novice drivers, who are licensed under GDL policies. Moreover, older novice drivers experience much less steep crash reductions over the first year of licensure than younger novice drivers. Nighttime crash rates among the 21- to 24-year old and aged 25 and older novice driver groups were stable over the first year of licensure. For novice drivers under age 21, early night crash rates declined rapidly over the course of licensure, while changes in late night crashes were much smaller. First-year multiple passenger crash rates were highest for drivers licensed at age 18-20, and novice driver groups experienced varying amounts of reduction in multiple passenger crashes over time. Conclusions: Study findings support NJ's current GDL policies for 17- to 20-year-old novice drivers and the potential for added benefits from beginning the nighttime restriction at 9:00 p.m. Conversely, there was a lack of compelling evidence for additional policies for drivers licensed at age 21-24 and no evidence to indicate a need for additional GDL policies for NJ novices aged 25 years and older.
  • Article
    This paper presents the design, analysis and results of a driving simulator experiment conducted to study the interaction between drivers and pedestrians in a mixed-street environment. Ninety-six students of the American University of Beirut (AUB) participated in the experiment that took place in the Transportation and Infrastructure Laboratory of AUB. The study looked at the driver-pedestrian interaction from the driver's perspective, by quantifying the effects of different scenario variables on the driving behavior of the participants. Kruskall-Wallis test shows that drivers' behavior in proximity of pedestrians tends to be statistically significantly less aggressive when their approach velocity is lower, curb-side parking is not allowed, a crosswalk exists, and the number of pedestrians crossing the street is higher. A discrete choice model for the yielding behavior of the drivers was also developed as a function of different predictor variables. Five out of the six predictors considered (except for gender) had a statistically significant effect on the yielding behavior, particularly the effects of curb-side parking, number of pedestrians crossing, and approach velocity. The model was then used to evaluate the effect of policy variables on the yielding probabilities of the drivers. The results of this study enrich current knowledge and understanding of drivers' behavior and their interaction with pedestrians, especially with studying the effects of scenario variables that were not addressed before; this would help planners propose and evaluate safety measures and traffic calming techniques to reduce the risks on pedestrians. The study also confirms the effectiveness of driving simulators in studying driver-pedestrian interactions.
  • Article
    Crash severity prediction models enable different agencies to predict the severity of a reported crash with unknown severity or the severity of crashes that may be expected to occur sometime in the future. This paper had three main objectives: comparison of the performance of four statistical and machine learning methods including Multinomial Logit (MNL), Nearest Neighbor Classification (NNC), Support Vector Machines (SVM) and Random Forests (RF), in predicting traffic crash severity; developing a crash costs-based approach for comparison of crash severity prediction methods; and investigating the effects of data clustering methods comprising K-means Clustering (KC) and Latent Class Clustering (LCC), on the performance of crash severity prediction models. The 2012-2015 reported crash data from Nebraska, United States was obtained and two-vehicle crashes were extracted as the analysis data. The dataset was split into training/estimation (2012-2014) and validation (2015) subsets. The four prediction methods were trained/estimated using the training/estimation dataset and the correct prediction rates for each crash severity level, overall correct prediction rate and a proposed crash costs-based accuracy measure were obtained for the validation dataset. The correct prediction rates and the proposed approach showed NNC had the best prediction performance in overall and in more severe crashes. RF and SVM had the next two sufficient performances and MNL was the weakest method. Data clustering did not affect the prediction results of SVM, but KC improved the prediction performance of MNL, NNC and RF, while LCC caused improvement in MNL and RF but weakened the performance of NNC. Overall correct prediction rate had almost the exact opposite results compared to the proposed approach, showing that neglecting the crash costs can lead to misjudgment in choosing the right prediction method.
  • Article
    Full-text available
    In this paper, we propose a visualization method for driving behavior that helps people to recognize distinctive driving behavior patterns in continuous driving behavior data. Driving behavior can be measured using various types of sensors connected to a control area network. The measured multi-dimensional time series data are called driving behavior data. In many cases, each dimension of the time series data is not independent of each other in a statistical sense. For example, accelerator opening rate and longitudinal acceleration are mutually dependent. We hypothesize that only a small number of hidden features that are essential for driving behavior are generating the multivariate driving behavior data. Thus, extracting essential hidden features from measured redundant driving behavior data is a problem to be solved to develop an effective visualization method for driving behavior. In this paper, we propose using deep sparse autoencoder (DSAE) to extract hidden features for visualization of driving behavior. Based on the DSAE, we propose a visualization method called a driving color map by mapping the extracted 3-D hidden feature to the red green blue (RGB) color space. A driving color map is produced by placing the colors in the corresponding positions on the map. The subjective experiment shows that feature extraction method based on the DSAE is effective for visualization. In addition, its performance is also evaluated numerically by using pattern recognition method. We also provide examples of applications that use driving color maps in practical problems. In summary, it is shown the driving color map based on DSAE facilitates better visualization of driving behavior.
  • Article
    Full-text available
    Over the past decade, vision-based vehicle detection techniques for road safety improvement have gained an increasing amount of attention. Unfortunately, the techniques suffer from robustness due to huge variability in vehicle shape (particularly for motorcycles), cluttered environment, various illumination conditions, and driving behavior. In this paper, we provide a comprehensive survey in a systematic approach about the state-of-the-art on-road vision-based vehicle detection and tracking systems for collision avoidance systems (CASs). This paper is structured based on a vehicle detection processes starting from sensor selection to vehicle detection and tracking. Techniques in each process/step are reviewed and analyzed individually. Two main contributions in this paper are the following: survey on motorcycle detection techniques and the sensor comparison in terms of cost and range parameters. Finally, the survey provides an optimal choice with a low cost and reliable CAS design in vehicle industries.
  • Article
    Full-text available
    The first aim of the present study was to investigate the applicability of the three-factor structure (aggressive violations, ordinary violations, and errors) of the Manchester Driver Behaviour Questionnaire (DBQ) and then to compare these driving behaviours across the six countries (Finland, Great Britain, Greece, Iran, The Netherlands, and Turkey). The third aim of the present study was to evaluate the role of driving styles in the relationship between traffic cultures (countries) and the number of traffic accidents utilizing a mediational framework. The fourth aim of this paper was to investigate the relationship between the three factors of DBQ and the number of traffic accidents in each country. Two hundred and forty-two drivers were chosen from each of the six countries, matched for age and sex. The results of confirmatory factor analyses showed that the fit of the three-factor model of DBQ was partially satisfactory in each country. Exploratory factor analyses together with target (Procrustes) rotation and factorial agreement indexes showed that the “ordinary violations” factor was fully congruent and the “errors” factor was fairly congruent across countries. Reliabilities of the scales were at the same level as in the original British data. ANOVA results revealed differences between drivers from “safe” Western/Northern European and Southern European/Middle Eastern countries on DBQ items and scales. Results demonstrated that driving style mediates the relationship between traffic culture (i.e. country) and the number of accidents. Poisson and negative binomial regression analyses also showed that the importance of driver characteristics and behaviours in predicting the number of traffic accidents varies from country to country.
  • Article
    Full-text available
    From a psychological viewpoint, several behaviour change techniques may be used to change unsate driver behaviour, e.g. informing, persuading rewarding, punishing etc. The motivation underlying the behaviour determines to a large degree how successful these behaviour change strategies may be. In the article, three broad classes of explanation for driver behaviour are distinguished: reasoned or planned behaviour, impulsive or emotional behaviour and habitual behaviour. Reasoned behaviour is under voliitional control of the driven and is determined by intention to commit the behaviour, which is in turn dependent on attitudes and subjective norms. Emotional behaviour may take range of expressive forms, varying from impulsive reactions to unexpected traffic situations to aggressive driving behaviours elicited by perceived norm-violations of other road users. Habitual behaviour occurs mindlessly, without forethought or conscious information-processing. The transfer of objective knowledge, the cornerstone of persuasive road safety campagns and road safety education, may be useful in itself in changing reasoned driver behaviour, but may be amiss in changing unplanned, emotionally or habitually driven behaviours. For addressing these types of behaviour, other or additional strategies are considered.
  • Conference Paper
    PROMETHEUS is a research programme launched by the European automotive industry, intended to work out concepts and draw up possible solutions aimed at improving all areas of European road traffic, i.e. making driving in Europe safer, more economical, more environmentally acceptable, more comfortable and more efficient. PROMETHEUS stands for `programme for a European traffic with highest efficiency and unprecedented safety'. Information technology is used to provide onboard drives assistance-in particular an anti-lock braking system to prevent locking of wheels-inter-vehicle communications; and vehicle-roadside communications. The stages of the project, and its progress so far, are outlined