How to Use Driving Simulators Properly: Impacts of Human Sensory and Perceptual Capabilities on Visual Fidelity

Fidelity has been a critical concern of researchers throughout the history of driving simulation. Understanding the limits of a driving simulation system is a prerequisite for conducting valid driving simulator studies. This paper proposes a novel and interdisciplinary methodology to ensure validity of studies using driving simulators (primarily for traffic control devices and other object detection tasks) based on the visual limits of human sensory and perceptual capabilities, and the characteristics of raster graphics. This methodology decomposes the perceptual issues of a stimulus into perceptual issues of different visual properties like luminance, hue, or text of the stimulus. By systematically analyzing the mechanism of human vision in driving simulators, the perceptual principle is proposed to ensure perceivable visual details in human-in-the-loop driving simulation systems. Additionally, the graphic principle is proposed to ensure perceivable features of a target object in the virtual driving environment. Both principles quantify the minimum requirements of visual fidelity with two measurements: angular resolution and matrix dimensions. The enriched results from existing pertinent studies are analyzed and organized to yield support of both principles. This research focuses on the minimum requirements for four factors; namely the visual acuity of drivers, the specifications of display systems, the configurations of graphics systems, and the design of virtual scenarios, as well as the relationship among all these factors to assess the visual fidelity in driving simulation systems. Within the realm of human perception, this work can provide criteria for proper design, calibration, and usage of driving simulators.     

An algorithm for combining autonomous vehicles and controlled events in driving simulator experiments

Autonomous vehicles can be used to create realistic simulations of surrounding vehicles in driving simulators. However, the use of autonomous vehicles makes it difficult to ensure reproducibility between subjects. In this paper, an effort is made to solve the problem by combining autonomous vehicles and controlled events. A controlled event can be compared to a theatre play. The aim is to achieve the same initial play conditions for each subject, which can be problematic since the traffic situation around the subject will be dependent upon each subject’s actions while driving in autonomous traffic. This paper presents an algorithm that achieves the transition from autonomous traffic to a predefined start condition for a play. The algorithm has been tested in the Swedish National Road and Transport Research Institute (VTI) driving simulator III with promising results. In most of the cases we examined the algorithm could reconstruct the specified start condition and conduct the transition from autonomous to controlled mode in a inconspicuous way. Some problems were observed regarding moving unwanted vehicles away from the closest area around the simulator vehicle, and this part of the algorithm has to be enhanced. The experiment also showed that the subjects drove faster in the presence of controlled everyday life traffic normally used in the VTI driving simulator than in autonomous traffic.     

An integrated traffic-driving simulation framework: Design,implementation, and validation

This paper first describes the process of integrating two distinct transportation simulation platforms, Traffic Simulation models and Driving Simulators, so as to broaden the range of applications for which either type of simulator is applicable. To integrate the two distinct simulation platforms, several technical challenges needed to be overcome including reconciling differences in update frequency, coordinate systems, and the fidelity levels of the vehicle dynamics models and graphical rendering requirements of the two simulators. Following the successful integration, the integrated simulator was validated by having several human subjects drive a 2.5 mile long segment of a signalized arterial in both the virtual environment of the integrated simulator, and in the real-world during the evening “rush hour”. Several aspects of driving behavior were then compared between the human subjects’ driving in the “virtual” and the real world. The comparisons revealed generally similar behavior, in terms of average corridor-level travel time, deceleration/acceleration patterns, lane-changing behavior, as well as energy consumption and emissions production. The paper concludes by suggesting possible extensions of the developed prototype which the researchers are currently pursuing, including integration with a computer networking simulator, to facilitate Connected Vehicle (CV) and Vehicle Ad-hoc Network (VANET) related studies, and a multiple participant component that allows several human drivers to interact simultaneously within the integrated simulator.     

Comparison of pattern recognition techniques for the classification of impact acoustic emissions

Current day condition monitoring applications involving wood are mostly carried out through visual inspection and if necessary some impact acoustic examination is carried out. These inspections are mainly done intuitively by skilled personnel. In this paper, a pattern recognition approach has been considered to automate such intuitive human skills for the development of robust and reliable methods within the area. The study presents a comparison of several pattern recognition techniques combined with various stationary feature extraction techniques for classification of impact acoustic emissions. Further issues concerning feature fusion are discussed as well. It is hoped that this kind of broad analysis could be used to handle a wide spectrum of tasks within the area, and would provide a perfect ground for future research directions. A brief introduction to the techniques is provided for the benefit of the readers unfamiliar with the techniques.Pattern classifiers such as support vector machines, etc. are combined with stationary feature extraction techniques such as linear predictive cepstral coefficients, etc. Results from support vector machines in combination with linear predictive cepstral coefficients delivered good classification rates. However, Gaussian mixture models delivered higher classification rates when feature fusion is proposed.     

Utilizing naturalistic driving data for in-depth analysis of driver lane-keeping behavior in rain: Non-parametric MARS and parametric logistic regression modeling approaches

It is known that adverse weather conditions can affect driver performance due to reduction in visibility and slippery surface conditions. Lane keeping is one of the main factors that might be affected by weather conditions. Most of the previous studies on lane keeping have investigated driver lane-keeping performance from driver inattention perspective. In addition, the majority of previous lane-keeping studies have been conducted in controlled environments such as driving simulators. Therefore, there is a lack of studies that investigate driver lane-keeping ability considering adverse weather conditions in naturalistic settings. In this study, the relationship between weather conditions and driver lane-keeping performance was investigated using the SHRP2 naturalistic driving data for 141 drivers between 19 and 89 years of age. Moreover, a threshold was introduced to differentiate lane keeping and lane changing in naturalistic driving data. Two lane-keeping models were developed using the logistic regression and multivariate adaptive regression splines (MARS) to better understand factors affecting driver lane-keeping ability considering adverse weather conditions. The results revealed that heavy rain can significantly increase the standard deviation of lane position (SDLP), which is a very widely used method for analyzing lane-keeping ability. It was also found that traffic conditions, driver age and experience, and posted speed limits have significant effects on driver lane-keeping ability. An interesting finding of this study is that drivers have a better lane-keeping ability in roadways with higher posted speed limits. The results from this study might provide better insights into understanding the complex effect of adverse weather conditions on driver behavior.     

Development of a representative urban driving cycle construction methodology for electric vehicles: A case study in Xi’an

This paper develops a systematic and practical construction methodology of a representative urban driving cycle for electric vehicles, taking Xi’an as a case study. The methodology tackles four major tasks: test route selection, vehicle operation data collection, data processing, and driving cycle construction. A qualitative and quantitative comprehensive analysis method is proposed based on a sampling survey and an analytic hierarchy process to design test routes. A hybrid method using a chase car and on-board measurement techniques is employed to collect data. For data processing, the principal component analysis algorithm is used to reduce the dimensions of motion characteristic parameters, and the K-means and support vector machine hybrid algorithm is used to classify the driving segments. The proposed driving cycle construction method is based on the Markov and Monte Carlo simulation method. In this study, relative error, performance value, and speed-acceleration probability distribution are used as decision criteria for selecting the most representative driving cycle. Finally, characteristic parameters, driving range, and energy consumption are compared under different driving cycles.     

Crash prediction with behavioral and physiological features for advanced vehicle collision avoidance system

Real-time crash prediction is the key component of the Vehicle Collision Avoidance System (VCAS) and other driver assistance systems. The further improvements of predictability requires the systemic estimation of crash risks in the driver-vehicle-environment loop. Therefore, this study designed and validated a prediction method based on the supervised learning model with added behavioral and physiological features. The data samples were extracted from 130 drivers’ simulator driving, and included various features generated from synchronized recording of vehicle dynamics, distance metrics, driving behaviors, fixations and physiological measures. In order to identify the optimal configuration of proposed method, the Discriminant Analysis (DA) with different features and models (i.e. linear or quadratic) was tested to classify the crash samples and non-crash samples. The results demonstrated the significant improvements of accuracy and specificity with added visual and physiological features. The different models also showed significant effects on the characteristics of sensitivity and specificity. These results supported the effectiveness of crash prediction by quantifying drivers’ risky states as inputs. More importantly, such an approach also provides opportunities to integrate the driver state monitoring into other vehicle-mounted systems at the software level.     

Understanding the impacts of mobile phone distraction on driving performance: A systematic review

The use of mobile phones while driving—one of the most common driver distractions—has been a significant research interest during the most recent decade. While there has been a considerable amount research and excellent reviews on how mobile phone distractions influence various aspects of driving performance, the mechanisms by which the interactions with mobile phone affect driver performance is relatively unexamined. As such, the aim of this study is to examine the mechanisms involved with mobile phone distractions such as conversing, texting, and reading and the driving task, and subsequent outcomes. A novel human-machine framework is proposed to isolate the components and various interactions associated with mobile phone distracted driving. The proposed framework specifies the impacts of mobile phone distraction as an inter-related system of outcomes such as speed selection, lane deviations and crashes; human-car controls such as steering control and brake pedal use and human-environment interactions such as visual scanning and navigation. Eleven literature-review/meta-analyses papers and 62 recent research articles from 2005 to 2015 are critically reviewed and synthesised following a systematic classification scheme derived from the human-machine system framework. The analysis shows that while many studies have attempted to measure system outcomes or driving performance, research on how drivers interactively manage in-vehicle secondary tasks and adapt their driving behaviour while distracted is scant. A systematic approach may bolster efforts to examine comprehensively the performance of distracted drivers and their impact over the transportation system by considering all system components and interactions of drivers with mobile phones and vehicles. The proposed human-machine framework not only contributes to the literature on mobile phone distraction and safety, but also assists in identifying the research needs and promising strategies for mitigating mobile phone-related safety issues. Technology based countermeasures that can provide real-time feedback or alerts to drivers based on eye/head movements in conjunction with vehicle dynamics should be an important research direction.     

A rule-based neural network approach to model driver naturalistic behavior in traffic

This paper proposes a rule-based neural network model to simulate driver behavior in terms of longitudinal and lateral actions in two driving situations, namely car-following situation and safety critical events. A fuzzy rule based neural network is constructed to obtain driver individual driving rules from their vehicle trajectory data. A machine learning method reinforcement learning is used to train the neural network such that the neural network can mimic driving behavior of individual drivers. Vehicle actions by neural network are compared to actions from naturalistic data. Furthermore, this paper applies the proposed method to analyze the heterogeneities of driving behavior from different drivers’ data.Driving data in the two driving situations are extracted from Naturalistic Truck Driving Study and Naturalistic Car Driving Study databases provided by the Virginia Tech Transportation Institute according to pre-defined criteria. Driving actions were recorded in instrumented vehicles that have been equipped with specialized sensing, processing, and recording equipment.     

A dynamic cordon pricing scheme combining the Macroscopic Fundamental Diagram and an agent-based traffic model

Pricing is considered an effective management policy to reduce traffic congestion in transportation networks. In this paper we combine a macroscopic model of traffic congestion in urban networks with an agent-based simulator to study congestion pricing schemes. The macroscopic model, which has been tested with real data in previous studies, represents an accurate and robust approach to model the dynamics of congestion. The agent-based simulator can reproduce the complexity of travel behavior in terms of travelers’ choices and heterogeneity. This integrated approach is superior to traditional pricing schemes. On one hand, traffic simulators (including car-following, lane-changing and route choice models) consider travel behavior, i.e. departure time choice, inelastic to the level of congestion. On the other hand, most congestion pricing models utilize supply models insensitive to demand fluctuations and non-stationary conditions. This is not consistent with the physics of traffic and the dynamics of congestion. Furthermore, works that integrate the above features in pricing models are assuming deterministic and homogeneous population characteristics. In this paper, we first demonstrate by case studies in Zurich urban road network, that the output of a agent-based simulator is consistent with the physics of traffic flow dynamics, as defined by a Macroscopic Fundamental Diagram (MFD). We then develop and apply a dynamic cordon-based congestion pricing scheme, in which tolls are controlled by an MFD. And we investigate the effectiveness of the proposed pricing scheme. Results show that by applying such a congestion pricing, (i) the savings of travel time at both aggregated and disaggregated level outweigh the costs of tolling, (ii) the congestion inside the cordon area is eased while no extra congestion is generated in the neighbor area outside the cordon, (iii) tolling has stronger impact on leisure-related activities than on work-related activities, as fewer agents who perform work-related activities changed their time plans. Future work can apply the same methodology to other network-based pricing schemes, such as area-based or distance-traveled-based pricing. Equity issues can be investigated more carefully, if provided with data such as income of agents. Value-of-time-dependent pricing schemes then can also be determined.     

Computer vision approach for the classification of bike type (motorized versus non‐motorized) during busy traffic in the city of Shanghai

This article describes a novel approach for the binary classification of two‐wheeler road users in a dense mixed traffic intersection. The classification is a supervised procedure to differentiate between motorized and non‐motorized (human‐powered) bikes. Road users were first detected and tracked using object recognition methods. Classification features were then selected from the collected trajectories. The features include maximum speed, cadence frequency in addition to acceleration‐based parameters. Experiments were conducted on a video data set from Shanghai, China, where cyclists as well as motorcycles tend to share the main road facilities. A sensitivity analysis was performed to assess the quality of the selected features in improving the accuracy of the classification. A performance analysis demonstrated the robustness of the proposed classification method with a correct classification rate of up to 93%. This research contributes to the literature of automated data collection and can benefit the applications in many transportation‐related fields such as shared space facility planning, simulation models for two‐wheelers, and behavior analysis and road safety studies. Copyright © 2015 John Wiley & Sons, Ltd.     

Length-based vehicle classification using event-based loop detector data

Length-based vehicle classification is an important topic in traffic engineering, because estimation of traffic speed from single loop detectors usually requires the knowledge of vehicle length. In this paper, we present an algorithm that can classify vehicles passing by a loop detector into two categories: long vehicles and regular cars. The proposed algorithm takes advantage of event-based loop detector data that contains every vehicle detector actuation and de-actuation “event”, therefore time gaps between consecutive vehicles and detector occupation time for each vehicle can be easily derived. The proposed algorithm is based on an intuitive observation that, for a vehicle platoon, longer vehicles in the platoon will have relatively longer detector occupation time. Therefore, we can identify longer vehicles by examining the changes of occupation time in a vehicle platoon. The method was tested using the event-based data collected from Trunk Highway 55 in Minnesota, which is a high speed arterial corridor controlled by semi-actuated coordinated traffic signals. The result shows that the proposed method can correctly classify most of the vehicles passing by a single loop detector.     

Identification of occupant posture using a Bayesian classification methodology to reduce the risk of injury in a collision

Recent studies have shown that smart restraint systems, which will recognize and then adapt to a specific collision and occupant combination, have a strong opportunity to significantly reduce occupant injuries during a traffic accident. As a step toward the development of these adaptive restraint systems, this study proposes a novel methodology for the classification of pre-crash occupant posture. Various occupant postures were simulated with a human model and the corresponding data was recorded using sensor models implemented in a mid-size car interior. The sensor data was then used to train two Bayesian classifiers which categorized an unknown occupant posture as one of nine predefined classes. The posture classifiers and a look-up table which contained optimized restraint laws for each class were combined to form catalog controllers for the restraint systems. The benefit of these restraint systems with catalog controllers vs. a restraint system optimized at a nominal posture was estimated by analyzing crash simulations with the occupant in 200 different postures. While the minimum error rate classifier showed the highest correct classification rate (90%), the Bayesian minimum risk classifier estimated the highest average injury reduction (21%). As expected, the highest injury reduction (up to 45%) was recorded for the posture classes closest to the windshield, whereas the lowest injury reduction was found for the classes closest to the nominal position. While the proposed restraint system with a catalog controller requires considerable “offline” computational effort, it is more versatile in terms of using complex human models and injury criteria and is much faster during the brief decision window available than recent “online” controllers proposed previously in literature.     

A driving cycle detection approach using map service API

Following advancements in smartphone and portable global positioning system (GPS) data collection, wearable GPS data have realized extensive use in transportation surveys and studies. The task of detecting driving cycles (driving or car-mode trajectory segments) from wearable GPS data has been the subject of much research. Specifically, distinguishing driving cycles from other motorized trips (such as taking a bus) is the main research problem in this paper. Many mode detection methods only focus on raw GPS speed data while some studies apply additional information, such as geographic information system (GIS) data, to obtain better detection performance. Procuring and maintaining dedicated road GIS data are costly and not trivial, whereas the technical maturity and broad use of map service application program interface (API) queries offers opportunities for mode detection tasks. The proposed driving cycle detection method takes advantage of map service APIs to obtain high-quality car-mode API route information and uses a trajectory segmentation algorithm to find the best-matched API route. The car-mode API route data combined with the actual route information, including the actual mode information, are used to train a logistic regression machine learning model, which estimates car modes and non-car modes with probability rates. The experimental results show promise for the proposed method’s ability to detect vehicle mode accurately.     

Vehicle classification from low-frequency GPS data with recurrent neural networks

The categorization of the type of vehicles on a road network is typically achieved using external sensors, like weight sensors, or from images captured by surveillance cameras. In this paper, we leverage the nowadays widespread adoption of Global Positioning System (GPS) trackers and investigate the use of sequences of GPS points to recognize the type of vehicle producing them (namely, small-duty, medium-duty and heavy-duty vehicles). The few works which already exploited GPS data for vehicle classification rely on hand-crafted features and traditional machine learning algorithms like Support Vector Machines. In this work, we study how performance can be improved by deploying deep learning methods, which are recently achieving state of the art results in the classification of signals from various domains. In particular, we propose an approach based on Long Short-Term Memory (LSTM) recurrent neural networks that are able to learn effective hierarchical and stateful representations for temporal sequences. We provide several insights on what the network learns when trained with GPS data and contextual information, and report experiments on a very large dataset of GPS tracks, where we show how the proposed model significantly improves upon state-of-the-art results.     

Improved waveform‐feature‐based vehicle classification using a single‐point magnetic sensor

Vehicle classification systems have important roles in applications related to real‐time traffic management. They also provide essential data and necessary information for traffic planning, pavement design, and maintenance. Among various classification techniques, the length‐based classification technique is widely used at present. However, the undesirable speed estimates provided by conventional data aggregation make it impossible to collect reliable length data from a single‐point sensor during real‐time operations. In this paper, an innovative approach of vehicle classification will be proposed, which achieved very satisfactory results on a single‐point sensor. This method has two essential parts. The first concerns with the procedure of smart feature extraction and selection according to the proposed filter–filter–wrapper model. The model of filter–filter–wrapper is adopted to make an evaluation on the extracted feature subsets. Meanwhile, the model will determine a nonredundant feature subset, which can make a complete reflection on the differences of various types of vehicles. In the second part, an algorithm for vehicle classification according to the theoretical basis of clustering support vector machines (C‐SVMs) was established with the selected optimal feature subset. The paper also uses particle swarm optimization (PSO), with the purpose of searching for an optimal kernel parameter and the slack penalty parameter in C‐SVMs. A total of 460 samples were tested through cross validation, and the result turned out that the classification accuracy was over 99%. In summary, the test results demonstrated that our vehicle classification method could enhance the efficiency of machine‐learning‐based data mining and the accuracy of vehicle classification. Copyright © 2014 John Wiley & Sons, Ltd.     

Evaluating the impact of legislation prohibiting hand-held cell phone use while driving

As of November 2008, the number of cell phone subscribers in the US exceeded 267 million, nearly three times more than the 97 million subscribers in June 2000. This rapid growth in cell phone use has led to concerns regarding their impact on driver performance and road safety. Numerous legislative efforts are under way to restrict hand-held cell phone use while driving. Since 1999, every state has considered such legislation, but few have passed primary enforcement laws. As of 2008, six states, the District of Columbia (DC), and the Virgin Islands have laws banning the use of hand-held cell phones while driving. A review of the literature suggests that in laboratory settings, hand-held cell phone use impairs driver performance by increasing tension, delaying reaction time, and decreasing awareness. However, there exists insufficient evidence to prove that hand-held cell phone use increases automobile-accident-risk. In contrast to other research in this area that uses questionnaires, tests, and simulators, this study analyzes the impact of hand-held cell phone use on driving safety based on historical automobile-accident-risk-related data and statistics, which would be of interest to transportation policy-makers. To this end, a pre-law and post-law comparison of automobile accident rate measures provides one way to assess the effect of hand-held cell phone bans on driving safety; this paper provides such an analysis using public domain data sources. A discussion of what additional data are required to build convincing arguments in support of or against legislation is also provided.     

Automated classification based on video data at intersections with heavy pedestrian and bicycle traffic: Methodology and application

Pedestrians and cyclists are amongst the most vulnerable road users. Pedestrian and cyclist collisions involving motor-vehicles result in high injury and fatality rates for these two modes. Data for pedestrian and cyclist activity at intersections such as volumes, speeds, and space–time trajectories are essential in the field of transportation in general, and road safety in particular. However, automated data collection for these two road user types remains a challenge. Due to the constant change of orientation and appearance of pedestrians and cyclists, detecting and tracking them using video sensors is a difficult task. This is perhaps one of the main reasons why automated data collection methods are more advanced for motorized traffic. This paper presents a method based on Histogram of Oriented Gradients to extract features of an image box containing the tracked object and Support Vector Machine to classify moving objects in crowded traffic scenes. Moving objects are classified into three categories: pedestrians, cyclists, and motor vehicles. The proposed methodology is composed of three steps: (i) detecting and tracking each moving object in video data, (ii) classifying each object according to its appearance in each frame, and (iii) computing the probability of belonging to each class based on both object appearance and speed. For the last step, Bayes’ rule is used to fuse appearance and speed in order to predict the object class. Using video datasets collected in different intersections, the methodology was built and tested. The developed methodology achieved an overall classification accuracy of greater than 88%. However, the classification accuracy varies across modes and is highest for vehicles and lower for pedestrians and cyclists. The applicability of the proposed methodology is illustrated using a simple case study to analyze cyclist–vehicle conflicts at intersections with and without bicycle facilities.     

Impact of traveler advisory systems on driving speed: some new evidence

This paper explores the effects of driving behavior using in-vehicle and out-of-vehicle traffic advisory information relating to adverse weather and incident conditions. A full-size, fixed-based driving simulator is used to collect data on drivers’ speed behavior under four different advisory-information conditions: in-vehicle messages, out-of-vehicle messages, both types of messages, and no messages. The findings of this study suggest an interesting phenomenon in that, while messages are significant in reducing speeds in the area of adverse conditions, drivers tend to compensate for this speed reduction by increasing speeds downstream when such adverse conditions do not exist. As a result, the net safety effects of such message systems are ambiguous.     

Discriminant analysis of purchasers of general aviation aircraft avionics

Using data from the Federal Aviation Administration's national sample of general aviation (GA) aircraft owners (1975), this study explores the factors that influence aircraft owners' equipment purchase decisions for eight different types of communication and navigation instrumentation. The discriminant function is developed for noncompany owners of GA aircraft and is applied to data for company owners to generate the classification results. The results for almost all types of avionics suggest that the discriminant function—based on owner's type of use of aircraft, the aircraft's age, type of aircraft, and intensity of use—effectively discriminates between the equipped and nonequipped groups. The classification results, tested against both a proportional chance and pure chance criteria, are for the most part statistically significant at the 0.01 level. Thus the discriminant functions effectively identifies individuals most apt to purchase a particular type of avionics. Hence, it could be used by the avionics manufacturing industry to establish market profiles and by the FAA in estimating the expected demand on their ground facility services and equipment.