Crash Avoidance Systems Research Articles

Vehicle to Vehicle Communication for Crash Avoidance System

The Dramatic increase in the traffic flow raises demand on innovative technologies that can improve safety and efficiency of transportation systems. Road safety can be substantially enhanced by the deployment of wireless communication technologies for vehicular networks, which enable new services such as collision detection traffic management, and further communication facilities between moving vehicles. Aiming at providing reliable wireless communications for vehicular networks the RF communication will serve as an underlying protocol for future inter-vehicular applications worldwide. This paper presents an implementation of a complete vehicle to vehicle communication, designed according to the specification. In addition to this a blind spot detection system for protection against misshapen like vehicle collisions that causes loss of human lives is being implemented. The blind spot detection system will be useful while changing the lane. Ultrasonic sensors, Raspberry pi, RF module and GPS modules are used to implement the complete design The main aim of V2V communication is to prevent accidents by allowing vehicles in transit to send position and speed data to one another. The vehicle’s driver may simply receive a warning should there be a risk of an accident or the vehicle itself may take preemptive actions as braking to slow down.

Intelligent Model for Avoiding Road Accidents Using Artificial Neural Network

Accidents typically occurred on roads, resulting in significant societal losses. Road accidents are a worldwide issue that result in the loss of precious human lives and property. The purpose of this paper is to create an intelligent system-based on Machine Learning model for avoiding road accidents, as well as a system that effectively reduces road accidents severities. The Artificial Neural Network (ANN) algorithm, along with others such as Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Nave Bayes (NB), Stochastic Gradient Descent (SGD), Random Forest (RF), Gradient Boosting (GB), and AdaBoost, is used to create an intelligence system. Many driving collaborator procedures, installed in a few vehicles, assist drivers in avoiding vehicle crashes by providing early cautioning messages. The intelligence road crash avoidance system model is built on dataset of 29 columns and 1048575 rows. Preprocessing, feature selection, and feature extraction performed with the help of heat map and correlation matrix are used to select features. Linear Discriminant Analysis (LDA) is used for feature extraction. The testing dataset revealed that the proposed ANN method outperforms other algorithms with an accuracy of 0.856. Intelligent systems aid in the prevention of traffic accidents, which aids police officers and researchers in developing new policies.

New and used vehicle buyers’ awareness, understanding, and trust in advanced driver assistance systems

IntroductionThere is concern that the effectiveness of crash avoidance systems will decrease or the potential benefits of adaptive cruise control (ACC) will fail to emerge as motor vehicles with the systems age. This is partly based on assumptions that these vehicles will eventually be bought on the used vehicle market, and the experience of buyers who purchase them used will differ from that of the first owners. But there is a lack of research on the topic. The purpose of this study was to compare driver trust, understanding, and awareness of crash avoidance systems and ACC between owners who purchased new versus used vehicles. MethodConsumers who purchased model year 2016–2019 vehicles with standard advanced driver assistance systems (ADAS) completed surveys that measured experience with the systems. In our analyses, we controlled for owner age group and gender, the importance that the vehicle they planned to buy had the technologies equipped, and how well they believed the seller explained the technologies. ResultsAs expected, respondents who purchased new vehicles had consistently more trust, awareness, and understanding of the systems relative to respondents who bought used. Results suggest that the perceived importance of ADAS early in the buying experience and a good explanation of the technology from the seller to the buyer may help reduce these differences. However, knowledge and awareness of ADAS was imperfect among new vehicle buyers, and concerns about the effectiveness and feasibility of training underscores the importance of improving understanding and use through system design. ConclusionThe significant association between increased trust in the systems and understanding and awareness of the technology, regardless of type of purchase, suggests that efforts to confer knowledge of ADAS early in the ownership experience will be beneficial to both groups of buyers.

Teen driver crashes potentially preventable by crash avoidance features and teen-driver-specific safety technologies

Introduction: Vehicle technologies have the potential to help address the disproportionate crash risk that teen drivers face. While crash avoidance features benefit the general population, several address crash scenarios for which teen drivers are particularly at risk, such as rear-end and lane-drift crashes. Other emerging technologies have been designed for teen drivers by addressing certain crash or injury risk factors associated with risky driving behavior, such as speeding or not wearing a seat belt. Methods: Using nationwide U.S. crash data from 2016 to 2019, this study examined the maximum potential safety benefits of three currently available crash avoidance features (front crash prevention, lane departure prevention, and blind spot monitoring) and three teen-driver-specific technologies (speeding prevention, extended seatbelt reminders and interlocks, and nighttime curfew violation alerts). Results: Teen-driver-specific features have the largest potential for reducing teen driver injuries and fatalities, followed by lane departure prevention, front crash prevention, and blind spot monitoring; however, altogether these technologies have the potential to prevent 78% of teen driver fatalities, 47% of injured teen drivers, and 41% of crashes involving teen drivers. Conclusions: Crash avoidance features and teen-driver-specific vehicle technologies appear to address different risk factors and crash scenarios, which emphasizes the importance of utilizing both types of safety features to reduce the crash risk of teen drivers. Practical applications: Wider acceptance, accessibility, and use of these technologies are needed for their safety potential to be realized. More manufacturers should offer and advertise teen-driver-specific technology suites that integrate crash avoidance systems and safety features that address risky driving behavior. While this study shows the maximum potential safety benefits of these technologies, further research is needed to understand the behavioral implications as teens learn to drive with these features.

Safety Assessment and a Parametric Study of Forward Collision-Avoidance Assist Based on Real-World Crash Simulations

In this study, we selected four real-world rear-end crash scenarios with different crash characteristics. The vehicles involved in those crashes were not equipped with any crash avoidance systems. We then used the accident reconstruction method to build those crash scenarios in PC-Crash software. Then, different FCW/AEB safety algorithms have been defined for a subject vehicle model in each crash scenario and each scenario was simulated for a set of input parameters such as vehicle speed, brake intensity, and driver reaction time. The range and distribution of input parameters were extracted from the related field crash data and available literature. A total number of 16000 simulations have been conducted which produced input-output datasets for further investigations. Finally, the effects of input parameters on simulation outcomes including crash occurrence, AEB activation, injury risk, and vehicle damage have been quantified using the Boruta algorithm. The results indicated that the overall effectiveness of the AEB system was a 57% reduction of rear-end crashes, a 52% reduction of injury severity (striking vehicle’s passengers), and a 47% reduction of damages for striking vehicles. The results also showed that the available AEB algorithms were more effective for the average speed equal to or less than 80 kmph. The speed of the subject vehicle, type of AEB algorithm, sensor detection range, and driver reaction time were the most important parameters on crash outcomes. In addition, the results indicated that the performance of FCW had a direct impact on the effectiveness of the AEB system for the integrated FCW + AEB system.

ACCIDENT DETECTION SYSTEM USING IOT BASED CLOUD COMPUTING TECHNOLOGY

The increase of accidents is due to dynamic traffic conditions on roads in day-to-day life. we proposed an accident detection system model on IoT and cloud. In this scenario, we suggest a model for accident detection, which will demonstrate crash avoidance and braking systems for the area of Adhoc vehicle networks such as the intelligent transport System, which focuses on road safety and communication between on road vehicles.

Automatic collision notification availability and emergency response times following vehicle collision—an analysis of the 2017 crash investigation sampling system

Objective To determine whether occupants of collisions involving at least one vehicle with an available Automatic Collision Notification (ACN) system have quicker times from collision to 1) Emergency Medical Services (EMS) notification and 2) arrival to a medical center. Methods Using data from the 2017 Crash Investigation Sampling System, vehicles were categorized as whether ACN was available using data from the CISS's dataset of crash avoidance system availability (in which ACN is included though notably not a crash avoidance system). A Cox proportional hazards model—overall and stratified by urbanization—was used to compare the time from collision to both EMS notification and EMS arrival to a medical center. Results A total of 2,034 collisions (weight n: 2,775,512) involving 4235 occupants (weighted n: 4,987,669) were included. An estimated 259,021 (9.3%) and 546,223 occupants (11.0%) were in a collision in which one vehicle had ACN equipped. The median time to EMS notification was longer for collisions in which no involved vehicles had ACN available (median 4, IQR 2-9 minutes) than ACN-exposed collisions (median 2, IQR 1-5 minutes). There was a marginally significant higher hazard (i.e., instantaneous risk) of EMS notification for collisions with at least one vehicle having ACN available (HR 1.77, 95% CI 0.99-3.15). Likewise, there was a higher instantaneous risk of medical center arrival for occupants (HR 1.80, 95% CI 1.41-2.30) involved in collisions in which at least one vehicle had ACN available. ACN was associated with quicker EMS notification only in urban areas (HR 3.06, 95% CI 1.57-5.97) and associated with a greater reduction in time to medical facility in less urban areas (median 36 vs 45 minutes, HR 2.12, 95% CI 1.22-3.63). Conclusions This is the first study to directly compare EMS response-related times between collisions involving vehicles with and without ACN available. The current data corroborate prior literature reporting quicker EMS notification times among collisions involving ACN-equipped vehicles. This is the first study to find that ACN is also associated to quicker times to medical center arrival, particularly for collisions occurring in less urban areas. Future research examining whether these decreased times are associated with better clinical outcomes are needed in order to fully assess ACN's ability to prevent trauma-related mortality and morbidity.

NHTSA’s 2018 Heavy Vehicle Automatic Emergency Braking Test Track Research Results

<div class="section abstract"><div class="htmlview paragraph">This paper presents National Highway Traffic Safety Administration’s 2017 and 2018 test track research results with heavy vehicles equipped with forward collision warning and automatic emergency braking systems. Newly developed objective test procedures were used to perform and collect performance data with three single-unit trucks equipped with the crash avoidance systems. The results of this research show that the test procedures are applicable to many heavy vehicles and indicate that performance improvements in heavy vehicles equipped with these safety systems can be objectively measured.</div></div>

Review Paper on Vehicle to Vehicle Communication for Crash Avoidance System

The objective of this paper is to provide a brief description on the proposed technologies to predict the collision between vehicles before the collision. The spectacular increase in traffic increases the demand for innovative technologies that can improve the safety and efficiency of transport systems. Road safety can be significantly improved by the use of wireless communication technologies for vehicle networks, which allows new services such as collision detection traffic management and other communication devices between moving vehicles. This paper presents an implementation of the complete vehicle-vehicle communication based on Li-Fi technology and DSRC technology based on Wi-Fi. The proposed system solves many of the problems faced by existing systems by using a GPS module instead of the conventional speedometer and also uses sensors that are reliable in areas where human intervention is involuntary or life-threatening in danger of extinction. The problems of congestion in the urban arteries increase day by day, and it is very difficult to deal with them in emergencies. Therefore, within the system, a communication unit is developed that interacts with other vehicles to free the lanes. This system aims to communicate with the vehicle in its environment using its location (i.e., using latitude and longitude) to indicate proximity. If these vehicles are in the immediate vicinity, drivers are notified by a message. In this way, drivers can communicate with each other and act according to the situation.

OLDER ADULTS’ OPINIONS ON DIFFERENT VEHICLE TECHNOLOGIES

Vehicle technologies have the potential to greatly improve road safety. Given normative changes in cognitive, sensory and physical functioning, older drivers may particularly benefit from such technologies. However, little research has examined older adults’ opinions of vehicle technologies, descriptive differences of individuals more likely to have positive opinions of vehicle technologies, and how their opinions may differ depending on the type of vehicle technology. The current study examined older adults’ opinions on vehicle technology in a sample of 72 adults between 65 and 85 years (M = 72.3, SD = 5.36, 48% women). Participants were asked, “How important is [parking assistance, crash avoidance systems, early collision warnings, built-in GPS] in choosing a new vehicle?” on a scale from 1 (“not at all”) to 5 (“must have”). On average, participants rated built-in GPS as the most important (M = 3.81, SD=1.10) with parking assist as the least important (M=1.86, SD=1.13). We used correlational analyses to examine the association between demographic and personality and importance ratings. Women were more likely to rate greater importance for built-in GPS than men (r=.35, p<.05). Age, education, self-reported driving quality, and self-reported average weekly driving miles were not significantly associated with importance rating. In terms of personality, only higher levels of extraversion were associated with more positive ratings of early collision warning systems (r=.24, p<.05). Vehicle technology design and education should take older adults’ preferences into account and consider individual differences, and future work should examine other predictors of vehicle technology preferences such as functional performance.

Prediction of Near-Crashes from Observed Vehicle Kinematics using Machine Learning

This study introduces a machine learning model for near-crash prediction from observed vehicle kinematics data. The main hypothesis is that vehicles tend to experience discernible turbulence in their kinematics shortly before involvement in near-crashes. To test this hypothesis, the SHRP2 NDS vehicle kinematics data (speed, longitudinal acceleration, lateral acceleration, yaw rate, and pedal position) are utilized. Several machine learning algorithms are trained and comparatively analyzed including K nearest neighbor (KNN), random forest, support vector machine (SVM), decision trees, Gaussian naïve Bayes (Gaussian NB), and adaptive boost (AdaBoost). Sensitivity analysis is performed to determine the optimal prediction horizon length (the time period before the occurrence of a near-crash) and the turbulence horizon length (the time period during which near-crash related changes in vehicle kinematics take place). The results indicate that optimal prediction performance can be achieved at a 1 s prediction horizons and a 3 s turbulence horizon. At these values, the AdaBoost model outperforms all other models in relation to its recall (100%), precision (98%), and F1-score (99%). These values imply that the near-crash prediction model is highly efficient in predicting most instances of near-crashes with minimal false near-crash predictions. This promising prediction performance offers a viable tool for supporting crash avoidance systems in the emerging connected/autonomous vehicle technology.

Safety assessment of automated vehicles: how to determine whether we have collected enough field data?

Objective: The amount of collected field data from naturalistic driving studies is quickly increasing. The data are used for, among others, developing automated driving technologies (such as crash avoidance systems), studying driver interaction with such technologies, and gaining insights into the variety of scenarios in real-world traffic. Because data collection is time consuming and requires high investments and resources, questions like “Do we have enough data?,” “How much more information can we gain when obtaining more data?,” and “How far are we from obtaining completeness?” are highly relevant. In fact, deducing safety claims based on collected data—for example, through testing scenarios based on collected data—requires knowledge about the degree of completeness of the data used. We propose a method for quantifying the completeness of the so-called activities in a data set. This enables us to partly answer the aforementioned questions.Method: In this article, the (traffic) data are interpreted as a sequence of different so-called scenarios that can be grouped into a finite set of scenario classes. The building blocks of scenarios are the activities. For every activity, there exists a parameterization that encodes all information in the data of each recorded activity. For each type of activity, we estimate a probability density function (pdf) of the associated parameters. Our proposed method quantifies the degree of completeness of a data set using the estimated pdfs.Results: To illustrate the proposed method, 2 different case studies are presented. First, a case study with an artificial data set, of which the underlying pdfs are known, is carried out to illustrate that the proposed method correctly quantifies the completeness of the activities. Next, a case study with real-world data is performed to quantify the degree of completeness of the acquired data for which the true pdfs are unknown.Conclusion: The presented case studies illustrate that the proposed method is able to quantify the degree of completeness of a small set of field data and can be used to deduce whether sufficient data have been collected for the purpose of the field study. Future work will focus on applying the proposed method to larger data sets. The proposed method will be used to evaluate the level of completeness of the data collection on Singaporean roads, aimed at defining relevant test cases for the autonomous vehicle road approval procedure that is being developed in Singapore.

A motivational driver model for the design of a rear-end crash avoidance system

A motivational driver model is developed to design a rear-end crash avoidance system. Current driver assistance systems use engineering methods without considering psychological human aspects, which leads to false activation of assistance systems and complicated control algorithms. The presented driver model estimates driver’s psychological motivations using the combined longitudinal and lateral time to collision, the vehicle kinematics, and the vehicle dynamics. These motivations simplify both autonomous driving algorithms and human-machine interactions. The optimal point of a motivational multi-objective cost function defines the decision for the autonomous driving. Moreover, the motivations are used as risk assessment factors for driver–machine interaction in dangerous situations. The system is evaluated on 10 human subjects in a driving simulator. The assistance system had no false activation during the tests. It avoided collisions in all the rear-end crash avoidance scenarios, while 90% of human subjects did not.

Roadside Sensing Information Enabled Horizontal Curve Crash Avoidance System Based on Connected and Autonomous Vehicle Technology

Horizontal curves are a major cause of road departure crashes that lead to fatal and severe injuries. Existing curve crash avoidance systems are typically enabled by displaying safety messages via in-vehicle heads-up/down display. However, these systems just pass the information to drivers. The final decision to reduce or maintain speed in response to the safety message is still the human driver’s. Because of the involvement of the human factor, there is potential for road departure crashes to happen if human drivers do not respond to safety messages appropriately. Autonomous vehicle (AV) technology targets elimination of human error in driving through an automated driving system. In this context, this paper proposes a conceptual prototype of a connected and AV-based horizontal curve crash avoidance system (CAV-HCCAS), aiming at achieving a permanent solution to horizontal curve safety by excluding human error through automated driving. In CAV-HCCAS, a roadside sensor detects pavement wetness level at the horizontal curve and communicates it to the vehicle via dedicated short-range communication. By processing the pavement wetness information, the AV applies a safe curve travel speed that reflects the real-time pavement conditions. An automated driving simulation experiment was performed to prove the concept. Dry and wet pavement conditions were simulated for a horizontal curve. Lane deviation data and the resulting lane departure conflicts were measured as safety performance measures. Results indicate a significant reduction of lane departure conflicts when CAV-HCCAS is implemented under both dry and wet pavement conditions, which reflects a substantial safety benefit.

The COVCRAV project: Architecture and design of a cooperative V2V crash avoidance system

Systems capable of warning motorists against hazardous driving conditions are extremely useful for next-generation cooperative situational awareness and collision avoidance systems. In this paper, we present some preliminary results related to the COVCRAV project which aims to develop an on-board Road Hazard Signaling (RHS) system based on a crowd-apprising model. Unlike other approaches that rely on the automatic detection of dangerous situations via onboard sensors or warning messages received from roadside units, our approach enables drivers to interact directly with a touchscreen Driver Vehicle Interface (DVI) to notify nearby vehicles about the presence of a hazardous driving situation based on many high-value safety use-cases. We describe our RHS application and highlight the key functions provided by the originating and the receiving ITS applications. We also provide some details regarding the design aspects and system architecture of the proposed system.

A Comparative Analysis of Tree-Based Ensemble Methods for Detecting Imminent Lane Change Maneuvers in Connected Vehicle Environments

Lane changing is one of the main contributors to car crashes in the U.S. The complexity of the decision-making process associated with lane changing makes such maneuvers prone to driving errors, and hence, increases the possibility of car crashes. Thus, researchers have been investigating ways to model and predict lane changing maneuvers for optimally designed crash avoidance systems. Such systems rely on the accuracy of detecting the onset of lane-change maneuvers, which requires comprehensive vehicle trajectory data. Connected Vehicles (CV) data provide opportunities for accurate modeling of lane changing maneuvers, especially with the variety of advanced tools available nowadays. The review of the literature indicates that most of the implemented modeling tools do not achieve reliable accuracy for such critical safety application of lane-change prediction. Recently, eXtreme Gradient Boosting (XGB) became a well-recognized algorithm among the computer science community in solving classification problems due to its accuracy, scalability, and speed. This study implements the XGB in predicting the onset of lane changing maneuvers using CV trajectory data. The performance of XGB is compared to three other tree-based algorithms namely, decision trees, gradient boosting, and random forests. The Next Generation SIMulation trajectory data are used to represent the high-resolution CV data. The results indicate that XGB is superior to the other algorithms with a high accuracy value of 99.7%. This outstanding accuracy is achieved when considering vehicle trajectory data two seconds prior to a potential lane change maneuver. The findings of this study are promising for detection of lane change maneuvers in CV environments.

Motorcycle crashes potentially preventable by three crash avoidance technologies on passenger vehicles

ABSTRACTObjective: The objective of this study was to identify and quantify the motorcycle crash population that would be potential beneficiaries of 3 crash avoidance technologies recently available on passenger vehicles.Methods: Two-vehicle crashes between a motorcycle and a passenger vehicle that occurred in the United States during 2011–2015 were classified by type, with consideration of the functionality of 3 classes of passenger vehicle crash avoidance technologies: frontal crash prevention, lane maintenance, and blind spot detection. Results were expressed as the percentage of crashes potentially preventable by each type of technology, based on all known types of 2-vehicle crashes and based on all crashes involving motorcycles.Results: Frontal crash prevention had the largest potential to prevent 2-vehicle motorcycle crashes with passenger vehicles. The 3 technologies in sum had the potential to prevent 10% of fatal 2-vehicle crashes and 23% of police-reported crashes. However, because 2-vehicle crashes with a passenger vehicle represent fewer than half of all motorcycle crashes, these technologies represent a potential to avoid 4% of all fatal motorcycle crashes and 10% of all police-reported motorcycle crashes.Discussion: Refining the ability of passenger vehicle crash avoidance systems to detect motorcycles represents an opportunity to improve motorcycle safety. Expanding the capabilities of these technologies represents an even greater opportunity. However, even fully realizing these opportunities can affect only a minority of motorcycle crashes and does not change the need for other motorcycle safety countermeasures such as helmets, universal helmet laws, and antilock braking systems.

Vehicle deformation depth based injury risk function for safety benefit evaluation of crash avoidance and mitigation systems

As the delta-v-based injury models used to evaluate intelligent driving systems are always fitted with European or American crash database, they cannot achieve wide application in those countries where limited in-depth analysed crash data are recorded. An injury model which is based on easily accessible information, is urgently needed. In this study, a deformation depth based injury risk model is proposed to overcome the limitation of delta-v. First, a correlation between the vehicle deformation depth and occupant injury risk is verified from the aspects of retrospective safety assessment and stiffness cluster analysis using German in-depth accident study and national automotive sampling system-crashworthiness data system. Furthermore, injury risk-deformation functions are regressed for different stiffness clusters using the crash data. The fitting accuracy reaches 97%, higher than the existing literature. A novel safety benefit assessment simulation platform is built with the regressed injury risk model. Based on this platform, an autonomous emergency braking system is evaluated. Only 1% error of the safety benefit exists between the proposed model and the delta-v based one.

Development and Analysis of an Automated Bird Crash Avoidance System

Development and Analysis of an Automated Bird Crash Avoidance System

Crash Avoidance System by Sharing Drive Information

Crash Avoidance System by Sharing Drive Information