Train here, drive there: ROS based end-to-end autonomous-driving pipeline validation in CARLA simulator using the NHTSA typology

Urban complex scenarios are the most challenging situations in the field of Autonomous Driving (AD). In that sense, an AD pipeline should be tested in countless environments and scenarios, escalating the cost and development time exponentially with a physical approach. In this paper we present a validation of our fully-autonomous driving architecture using the NHTSA (National Highway Traffic Safety Administration) protocol in the CARLA simulator, focusing on the analysis of our decision-making module, based on Hierarchical Interpreted Binary Petri Nets (HIBPN). First, the paper states the importance of using hyper-realistic simulators, as a preliminary help to real test, as well as an appropriate design of the traffic scenarios as the two current keys to build safe and robust AD technology. Second, our pipeline is introduced, which exploits the concepts of standard communication in robotics using the Robot Operating System (ROS) and the Docker approach to provide the system with isolation, flexibility and portability, describing the main modules and approaches to perform the navigation. Third, the CARLA simulator is described, outlining the steps carried out to merge our architecture with the simulator and the advantages to create ad-hoc driving scenarios for use cases validation instead of just modular evaluation. Finally, the architecture is validated using some challenging driving scenarios such as Pedestrian Crossing, Stop, Adaptive Cruise Control (ACC) and Unexpected Pedestrian. Some qualitative (video files: Simulation Use Cases) and quantitative (linear velocity and trajectory splitted in the corresponding HIBPN states) results are presented for each use case, as well as an analysis of the temporal graphs associated to the Vulnerable Road Users (VRU) cases, validating our architecture in simulation as a preliminary stage before implementing it in our real autonomous electric car.

Detecting Driver Drowsiness with Multi-Sensor Data Fusion Combined with Machine Learning

In this research work, we develop a drowsy driver detection system through the application of visual and radar sensors combined with machine learning. The system concept was derived from the desire to achieve a high level of driver safety through the prevention of potentially fatal accidents involving drowsy drivers. According to the National Highway Traffic Safety Administration, drowsy driving resulted in 50,000 injuries across 91,000 police-reported accidents, and a death toll of nearly 800 in 2017. The objective of this research work is to provide a working prototype of Advanced Driver Assistance Systems that can be installed in present-day vehicles. By integrating two modes of visual surveillance to examine a biometric expression of drowsiness, a camera and a micro-Doppler radar sensor, our system offers high reliability over 95% in the accuracy of its drowsy driver detection capabilities. The camera is used to monitor the driver’s eyes, mouth and head movement and recognize when a discrepancy occurs in the driver's blinking pattern, yawning incidence, and/or head drop, thereby signaling that the driver may be experiencing fatigue or drowsiness. The micro-Doppler sensor allows the driver's head movement to be captured both during the day and at night. Through data fusion and deep learning, the ability to quickly analyze and classify a driver's behavior under various conditions such as lighting, pose-variation, and facial expression in a real-time monitoring system is achieved.

Numerical Simulation of Airbag and Study on the Effect of Airbag Parameters on Head Injury Criteria

In the case of an accident, inflatable restraints system plays a critical role in ensuring the safety of vehicle occupants. Frontal airbags have saved 44,869 lives, according to research conducted by the National Highway Traffic Safety Administration (NHTSA).Finite element analysis is extremely important in the research and development of airbags in order to ensure optimum protection for occupant. In this work, we simulate a head impact test with a deploying airbag and investigate the airbag's parameters. The airbag's performance is directly influenced by the parameters of the cushion such as vent area and fabric elasticity. The FEM model is analysed to investigate the influence of airbag parameter, and the findings are utilised to determine an optimal value that may be employed in the construction of better occupant safety systems. Keywords: airbag, finite element method, occupant safety, frontal airbag, vent size, fabric elasticity, head injury criteria

Motor Vehicle Crash Testing Regulations for More Inclusive Populations

There is a stark disparity in motor vehicle crash deaths and injuries between male and female drivers. Female drivers are 13% more likely to be killed than their male counterparts in similar motor accidents. However, vehicle safety test practices do not account for diverse body proportions when assessing safety outcomes. Vehicle crash testing standards only require testing of two variations of adult-sized crash test dummies: a 50th percentile male and a 5th percentile female. Automotive companies are not required to test safety outcomes in crash test model’s representative of average female proportions or of non-average body sizes and physiological compositions. Current crash test standards are regulated by the National Highway Traffic Safety Administration (NHTSA) under the US Department of Transportation. This memo proposes three actions for the NHTSA and the Department of Transportation to address disparities in vehicle safety outcomes: 1) update safety standard requirements to include a 50th percentile female crash test dummy, 2) implement a federal tax incentive program for companies to include a greater diversity of vehicle occupant models, and 3) allocate funds for research and development of virtual crash testing models. These proposed initiatives seek to raise the minimum safety requirements and prioritize wider representation of vehicle occupants to improve parity in vehicle safety outcomes.

Multiple Correspondence Analysis of Wrong-Way Driving Fatal Crashes on Freeways

The objective of this study is to identify clusters of contributing factors associated with the occurrence of wrong-way driving (WWD) fatal crashes on freeways using the multiple correspondence analysis (MCA) method based on the Burt matrix with an adjustment of inertias. A total of 14 years (2004–2017) of WWD fatal crash data were extracted from the National Highway Traffic Safety Administration (NHTSA) Fatality Analysis Reporting System (FARS) database. A standard procedure was developed to extract the WWD crash information (including a total of 3,817 crashes) on freeways from the FARS. Each crash contains various characteristics of crashes, vehicles, and drivers, for example, crash time, crash location, vehicle type, driver age, and so forth. The MCA analysis used a total of 19 key variables with 67 defined categories. The results of this study indicate that four clusters of factors which, when combined, might contribute to the occurrence of some WWD fatal crashes. These four clusters were: (1) younger drivers, driving under the influence (DUI), midnight/early morning, lower speed limit (45–50 mph), urban areas, and street lighting; (2) older drivers, non-DUI drivers, and daylight; (3) dark/no light, 18:00 to 23:59 p.m., higher speed limits (65 mph or more), and rural areas; and (4) rain/snow/sleet/hail/fog, and wet road surface.

PP29 Improving buckle up in EMS study (iBEST)

BackgroundAccording to NHTSA (National Highway Traffic Safety Administration), data collected from 1992-2011 showed that 84 percent of EMS provider was not restrained while working; increasing the severity of injury when an ambulance crashes or abruptly stop.ObjectivesTo increase the awareness of EMS providers focusing on safety belt usage during their work.MethodThe study design is a prospective study including fifteen of physicians, nurses, paramedics, ambulance driver, and nurse aid from King Chulalongkorn Memorial Hospital, whom went on duty from April to October 2020. The collected data includes demographic data, occupation and its safety, reasons for not using seat belt. The data related to seat belt usage collected were then described and analysed by Mixed-effects Poisson Regression method and interpreted as Incident Rate Ratio (IRR) with 95% confidence interval (95% CI) and p-value.Result3 out of 15 (20%) did not use seat belt in the period before warning stickers were posted in the ambulance. When compared to 1 month after warning stickers were posted, the number of sample using seatbelt while working/travelling in the ambulance elevated to 11 out of 15 (73.33%) [IRR (95%CI) =3.66 (95% CI: 1.02, 13.13), p = 0.046].While at 3 months and 6 months, 10 out of 15 (66.77%) and 6 out of 15 (40%) still adhere to seat belt use, respectively. There is no statistical significance with the rate of seatbelt usage comparing between one, three, and six months after the warning stickers were posted. The most common reason for not using seatbelt is 1) seat cover covering the seatbelt 2) obstructing work 3) cannot reach equipment.ConclusionWarning stickers posted in the ambulance can increase awareness for seatbelt use of King Chulalongkorn Hospital’s EMS personnel while working.

Predicción temporal del número de fatalidades por accidentes de tránsito en Texas en el contexto de una caminata al azar probabilista

Introducción: Las lesiones causadas por los accidentes de tránsito son consideradas en la actualidad una epidemia debido a la importante morbimortalidad que se reporta a nivel mundial por esta causa, por lo cual es necesario predecir su comportamiento. Considerando lo anterior, se busca confirmar la capacidad predictiva de una metodología que predice la cifra de fatalidades por lesiones causadas por los accidentes de tránsito aplicada en el contexto del estado de Texas, E.E.U.U, para el año 2015 mediante la caminata al azar probabilista. Métodos: se analizaron las cifras de los reportes anuales entre 1994 a 2014 emitidos por la National Highway Traffic Safety Administration (NHTSA) sobre las fatalidades por lesiones causadas por los accidentes de tránsito en Texas enanalogía con la caminata al azar probabilista para obtener una predicción para el 2015. Resultados: se observó que el comportamiento de esta variable es compatible al analizado con la caminata al azar, lo cual permitió aplicar esta metodología y obtener una predicción para el 2015 con un acierto del 96,3 % con respecto al valor oficial reportado. Conclusiones: la caminata al azar probabilista predice el comportamiento de variables aparentemente aleatorias en el tiempo con precisiones elevadas, lo cual permite su aplicación como herramienta de vigilancia en salud pública al evaluarcomplementariamente la efectividad de las intervenciones para reducir la mortalidad por las lesiones causadas por los accidentes de tránsito.

40 Years and More of Tire Science and Technology: A History of The Tire Society

ABSTRACT In the late 1960s in the United States, public interest in motor vehicle safety was at an all-time high, resulting in the National Traffic and Motor Vehicle Safety Act, the Highway Safety Act, and the creation of the National Highway Traffic Safety Administration. Around 1970, a group of industry scientists saw a need for a forum for creation of useful tire standards and dissemination of scientific knowledge about tires. This led to the formation of the American Society for Testing and Materials (ASTM) Committee F-09 on tires in 1971. In 1972, the committee began publication of the journal Tire Science & Technology (TSTCA), the first peer-reviewed journal dedicated exclusively to scientific articles on tires. In 1979, ASTM ceased publication of the journal, and in 1980, members of F-09 incorporated The Tire Society to continue publication. In 1982, The Tire Society held its first annual Conference on Tire Science and Technology. Nearly 40 years later, the society has been through many changes, but the journal, the annual conference, and the core mission of encouraging and disseminating knowledge about tire science and technology remain. Through a review of documents and interviews with members of the society, this article seeks to comprehensively document the history of The Tire Society.

Hybrid Machine Learning Algorithm for Identifying Feature Levels Associated with Safety Critical Events

According to the National Highway Traffic Safety Administration (NHTSA), about seven million traffic accidents claimed more than 36,560 human lives in the U.S. in 2018 . These statistics have prompted researchers to investigate the driver characteristics associated with safety-critical events (SCE). This paper presents a hybrid CatBoost algorithm for identifying the feature levels associated with SCE. The model accounts for numerous difficulties and drawbacks reported in the literature. The model was trained and validated using the entire set of the Second Strategic Highway Research Program Naturalistic Driving Study (SHRP2-NDS) events (crash/near-crash and normal/baseline). Results indicate that secondary tasks (interacting with object in-vehicle, reaching for objects in the vehicle, pet interaction, cellphone/tablet use, and writing/texting), intersection influence (parking lots/driveway/entrance/exit, uncontrolled intersections, traffic signals, interchanges, and stop signs), income (under $29,000 and $100,000–$149,000), age (16–19 and 20–24), traffic density (level of service C, D, and E/F), high sensation-seeking tendency (scoring 18–35 on a scale of 35), low driving knowledge (scoring 0–8.9 on a 19-point scoring system questionnaire), and gender = female are the feature levels having an association with SCE with a probability varying between 51% and 87%. Results also revealed that passenger interactions, eating/drinking, driving away from intersections or interchanges, being age 70—79, or driving in traffic density = A are more related to safe driving. Consideration of these results can contribute to reducing roadway crashes and improve traffic safety.

Smart Policy for Smart Vehicles: Regulatory revisions to incentivize efficient autonomous automobiles

Transportation accounts for nearly 30% of the United States’ annual greenhouse gas emissions and is currently the fastest growing source of emissions by economic sector. National policies are therefore needed to mitigate the climatic impact of vehicular travel. Autonomous vehicle technologies, such as adaptive cruise control and real-time route optimization, can potentially improve fuel efficiency. However, many emerging technologies remain too inefficient to meet federal fuel economy standards set by the U.S. Environmental Protection Agency and the National Highway Traffic Safety Administration. The current regulatory framework therefore hinders vehicle manufacturers from researching and developing greener autonomous technologies. In this analysis, we argue that these federal agencies should adopt policies like technology waivers, regulatory credits, environmentally preferable purchasing, and educational programs to stimulate the development of more efficient autonomous vehicle technologies. These policies would incentivize manufacturers to widely develop and deploy fuel-saving technologies that could potentially realize substantial reductions in greenhouse gas emissions.