Gregoire S. Larue

An IEEE 802.11p empirical performance model for Cooperative Systems applications

IEEE 802.11p is the new standard for Inter-Vehicular Communications (IVC) using the 5.9 GHz frequency band, as part of the DSRC framework; it will enable applications based on Cooperative Systems. Simulation is widely used to estimate or verify the potential benefits of such cooperative applications, notably in terms of safety for the drivers. We have developed a performance model for 802.11p that can be used by simulations of cooperative applications (e.g. collision avoidance) without requiring intricate models of the whole IVC stack. Instead, it provide a a straightforward yet realistic modelisation of IVC performance. Our model uses data from extensive field trials to infer the correlation between speed, distance and performance metrics such as maximum range, latency and frame loss. Then, we improve this model to limit the number of profiles that have to be generated when there are more than a few couples of emitter-receptor in a given location. Our model generates realistic performance for rural or suburban environments among small groups of IVC-equipped vehicles and road side units.

Improving Near-Miss Event Detection Rate at Railway Level Crossings

Even though crashes between trains and road users are rare events at railway level crossings, they are one of the major safety concerns for the Australian railway industry. Nearmiss events at level crossings occur more frequently, and can provide more information about factors leading to level crossing incidents. In this paper we introduce a video analytic approach for automatically detecting and localizing vehicles from cameras mounted on trains for detecting near- miss events. To detect and localize vehicles at level crossings we extract patches from an image and classify each patch for detecting vehicles. We developed a region proposals algorithm for generating patches, and we use a Convolutional Neural Network (CNN) for classifying each patch. To localize vehicles in images we combine the patches that are classified as vehicles according to their CNN scores and positions. We compared our system with the Deformable Part Models (DPM) and Regions with CNN features (R-CNN) object detectors. Experimental results on a railway dataset show that the recall rate of of our proposed system is 29% higher than what can be achieved with DPM or R-CNN detectors.

Predicting Reduced Driver Alertness on Monotonous Highways

Impaired driver alertness increases the likelihood of a driver making mistakes and reacting too late to unexpected events. This is a particular concern on monotonous roads, where a drivers attention can decrease rapidly. Although effective countermeasures dont currently exist, the development of in-vehicle sensors opens avenues for monitoring driving behavior in real time. The aim of this study is to predict driver alertness levels using surrogate measures collected from in-vehicle sensors. Electroencephalographic activity is used as a reference to evaluate alertness. Based on a sample of 25 drivers, the authors collected data in a driving simulator instrumented with an eye-tracking system, a heart-rate monitor, and an electrodermal activity device. They tested various classification models, from linear regressions to Bayesians and data mining techniques. Results indicate that neural networks were the most efficient model for detecting lapses in alertness. Findings also show that reduced alertness can be predicted up to five minutes in advance with 90 percent accuracy using surrogate measures such as time to line crossing, blink frequency, and skin conductance level. Such a method could be used to warn drivers of their alertness levels through the development of an in-vehicle device that monitors, in real time, driver behavior on highways.

IEEE 802.11p Empirical Performance Model from Evaluations on Test Tracks

IEEE 802.11p is the new standard for intervehicular communications (IVC) using the 5.9 GHz frequency band; it is planned to be widely deployed to enable cooperative systems. 802.11p uses and performance have been studied theoretically and in simulations over the past years. Unfortunately, many of these results have not been confirmed by on-tracks experimentation. In this paper, we describe field trials of 802.11p technology with our test vehicles; metrics such as maximum range, latency and frame loss are examined. Then, we propose a detailed modelisation of 802.11p that can be used to accurately simulate its performance within Cooperative Systems (CS) applications.

Integrating driving and traffic simulators for the study of railway level crossing safety interventions: a methodology

Safety at Railway Level Crossings (RLXs) is an important issue within the Australian transport system. Crashes at RLXs involving road vehicles in Australia are estimated to cost

Fuzzy Logic to Evaluate Driving Maneuvers: An Integrated Approach to Improve Training

10 million each year. Such crashes are mainly due to human factors; unintentional errors contribute to 46% of all fatal collisions and are far more common than deliberate violations. This suggests that innovative intervention targeting drivers is particularly promising to help improve RLX safety. In recent years there has been a rapid development of a variety of affordable technologies which can be used to increase driver’s risk awareness around crossings. To date, no research has evaluated the potential effects of such technologies at RLXs in terms of safety, traffic and acceptance of the technology. Integrating driving and traffic simulations is a safe and affordable approach for evaluating these effects. This methodology will be implemented in a driving simulator, where we recreated realistic driving scenario with typical road environments and realistic traffic. This paper presents a methodology for evaluating comprehensively potential benefits and negative effects of such interventions: this methodology evaluates driver awareness at RLXs, driver distraction and workload when using the technology. Subjective assessment on perceived usefulness and ease of use of the technology is obtained from standard questionnaires. Driving simulation will provide a model of driving behaviour at RLXs which will be used to estimate the effects of such new technology on a road ...

How Consistent Are Drivers In Their Driving?A Driver Training Perspective

Driver training is one of the interventions aimed at mitigating the number of crashes that involve novice drivers. Our failure to understand what is really important for learners, in terms of risky driving, is one of the many drawbacks restraining us from building better training programs. Currently, there is a need to develop and evaluate advanced driving assistance systems that could comprehensively assess driving competencies. The aim of this paper is to present a novel intelligent driver training system that analyzes crash risks for a given driving situation, providing avenues for the improvement and personalization of driver training programs. The analysis takes into account numerous variables synchronously acquired from the driver, the vehicle, and the environment. The system then segments out the maneuvers within a drive. This paper further presents the fuzzy set theory to develop the safety inference rules for each maneuver executed during the drive, and presents a framework and its associated prototype that can be used to comprehensively view and assess complex driving maneuvers and then provides a comprehensive analysis of the drive used to give feedback to novice drivers.

Driver Behaviors at Level Crossings from Fixed and Moving Driving Simulators

This paper describes how the value and effectiveness of driver training as a means of improving driver behavior and road safety continues to fuel research and societal debates. Knowledge about what are the characteristics of safe driving that need to be learned is extensive. Research has shown that young drivers are over represented in crash statistics. The encouraging fact is that novice drivers have shown improvement in road scanning pattern after training. This paper presents a driver behavior study conducted on a closed circuit track. A group of experienced and novice drivers performed repeated multiple maneuvers (i.e. turn, overtake and lane change) under identical conditions. Variables related to the driver, vehicle and environment were recorded in a research vehicle equipped with multiple in vehicle sensors such as global positioning system (GPS) accelerometers, vision processing, eye tracker and laser scanner. Each group consistently exhibited a set of driving pattern characterizing a particular group. Behavior such as the indicator usage before lane change, following distance while performing a maneuver were among the consistent observed behavior differentiating novice from experienced drivers. This paper highlights the results of the study and emphasizes the need for effective driver training programs that focuses on young and novice drivers.

Validation of a Driving Simulator Study on Driver Behavior at Passive Rail Level Crossings

Many studies were conducted to evaluate safety at railway crossings equipped with different types of warning devices. In this study, a desktop driving simulator (fixed simulator) and an advanced simulator (moving simulator) were used to identify the impacts of two warning devices namely stop sign and in-vehicle audio warning on alerting drivers at railway crossings. Although these high-end technologies have been widely used for safety evaluation in many areas, there is a little research on their application and comparison at railway crossings. This paper reports the results of a comparison of the two simulators. As a preliminary result, vehicle speeds at given distance/time were analyzed. The results showed that when the warning started, drivers in the fixed simulator were slower than those in the moving simulator in responding. However, after four seconds of warning, the speed from both simulators showed statistically identical results. In summary, the different properties of the simulator lead drivers to react to warnings differently.

Impact of Waiting Times on Risky Driver Behaviour at Railway Level Crossings

Objective: The behavioral validation of an advanced driving simulator for its use in evaluating passive level crossing countermeasures was performed for stopping compliance and speed profile. Background: Despite the fact that most research on emerging interventions for improving level crossing safety is conducted in a driving simulator, no study has validated the use of a simulator for this type of research. Method: We monitored driver behavior at a selected passive level crossing in the Brisbane region in Australia for 3 months (N = 916). The level crossing was then replicated in an advanced driving simulator, and we familiarized participant drivers (N = 54) with traversing this crossing, characterized by low road and rail traffic. Results: We established relative validity for the stopping compliance and the approach speed. Conclusion: This validation study suggests that driving simulators are an appropriate tool to study the effects of interventions at passive level crossing with low road and rail traffic, which are prone to reduced compliance due to familiarity. Application: This study also provides support for the findings of previous driving simulator studies conducted to evaluate compliance and approach speeds of passive level crossings.