Search Results

Abstract In the automotive domain, the overall complexity of technical components has increased enormously. Formerly isolated, purely mechanical cars are now a multitude of cyber-physical systems that are continuously interacting with other IT systems, for example, with the smartphone of their driver or the backend servers of the car manufacturer. This has huge security implications as demonstrated by several recent research papers that document attacks endangering the safety of the car. However, there is, to the best of our knowledge, no holistic overview or structured description of the complex automotive domain. Without such a big picture, distinct security research remains isolated and is lacking interconnections between the different subsystems. Hence, it is difficult to draw conclusions about the overall security of a car or to identify aspects that have not been sufficiently covered by security analyses.

Abstract To evaluate that automated vehicle is as safe as a human driver, a following question is studied: how does an automated vehicle react under extreme conditions close to collision? In order to understand the collision avoidance capability of an automated vehicle, we should analyze not only such post-extreme condition behavior but also pre-extreme condition behavior. We present a theory to analyze the collision avoidance capability of automated driving technologies. We also formulate a collision avoidance equation on the theory. The equation has two types of solutions: response driving plans and preparation driving plans. The response driving plans are supported by response strategy on which the vehicle reacts after detection of a hazard and they are highly efficient in terms of travel time.

Abstract Modern vehicles have incorporated numerous safety-focused advanced driver-assistance systems (ADAS) in the last decade including smart cruise control and object avoidance. In this article, we aim to go beyond using ADAS for safety and propose to use ADAS technology to enable predictive optimal energy management and improve vehicle fuel economy (FE). We combine ADAS sensor data with a previously developed prediction model, dynamic programming (DP) optimal energy management control, and a validated model of a 2010 Toyota Prius to explore FE. First, a unique ADAS detection scope is defined based on optimal vehicle control prediction aspects demonstrated to be relevant from the literature. Next, during real-world city and highway drive cycles in Denver, Colorado, a camera is used to record video footage of the vehicle environment and define ADAS detection ground truth. Then, various ADAS algorithms are combined, modified, and compared to the ground truth results.

Abstract Management of expressway networks has been mainly focused on defect management without looking at the correlations with accidental risks. This causes unsustainability in expressway infrastructure maintenance since such defects may not be a contributing factor toward public safety. Thus it is necessary to incorporate accidental events for decision-making in infrastructure management. This study has developed a novel approach to machine learning (ML) that incorporates actual primary data from the last 10 years of single-vehicle accidents (SVA) by collisions with motorway facilities, or so-called single-vehicle collisions with fixed objects. The ML is firstly aimed at identifying the influential factors of SVA in relation to finding effective countermeasures for accidents by integrating the correlation analysis, multiple regression analysis, and ML techniques. The study reveals that wet pavement conditions have a significant effect on SVA.

Abstract Under contract to the EPA, Eastern Research Group analyzed light-duty vehicle OBD monitor readiness and diagnostic trouble codes (DTCs) using inspection and maintenance (I/M) data from four states. Results from roadside pullover emissions and OBD tests were also compared with same-vehicle I/M OBD results from one of the states. Analysis focused on the evaporative emissions control (evap) system, the catalytic converter (catalyst), the exhaust gas recirculation (EGR) system and the oxygen sensor and oxygen sensor heater (O2 system). Evap and catalyst monitors had similar overall readiness rates (90% to 95%), while the EGR and O2 systems had higher readiness rates (95% to 98%). Approximately 0.7% to 2.5% of inspection cycles with a “ready” evap monitor had at least one stored evap DTC, but DTC rates were under 1% for the catalyst and EGR systems, and under 1.1% for the O2 system, in the states with enforced OBD programs.

Abstract A critical component of vehicle dynamic control systems is the accurate and real-time knowledge of the vehicle’s key states and parameters when running on the road. Such knowledge is also essential for vehicle closed-loop feedback control. Vehicle state and parameter estimation has gradually become an important way to soft-sense some variables that are difficult to measure directly using general sensors. In this work, a seven degrees-of-freedom (7-DOF) nonlinear vehicle dynamics model is established, where consideration of the Magic formula tire model allows us to estimate several vehicle key states using a hybrid algorithm containing an unscented Kalman filter (UKF) and a genetic algorithm (GA). An estimator based on the hybrid algorithm is compared with an estimator based on just a UKF. The results show that the proposed estimator has higher accuracy and fewer computation requirements than the UKF estimator.

Abstract The development of automated driving systems (ADS) necessitates procedures to validate system safety. The reliability of an ADS’s environment perception provided by lidar, radar, and camera sensors is of special interest in this context, because perception errors can be safety-critical. In this article, we formalize the reliability-based validation of environment perception for safe automated driving and discuss associated challenges. We describe a potential solution to a perception reliability validation by deriving performance requirements at the sensor level. We then summarize statistical methods to learn sensor perception reliabilities in field tests, on proving grounds, and through virtual simulations. With the developed safety validation framework, we show that, potentially, one can validate the safety of an ADS with feasible test effort.

Abstract In recent years, to avoid the failure of the onboard perception system, intelligent vehicle infrastructure cooperative systems have been attracting attention in the field of autonomous vehicles. Using the perception technology of roadside sensors to provide supplementary traffic information for autonomous vehicles has become an increasing trend. Several roadside perception solutions select deep learning for three-dimensional (3D) object detection. However, deep learning methods have several issues and lack reliability in practical engineering applications. To tackle this challenge, this study proposes a pedestrian detection algorithm based on roadside Light Detection And Ranging (LiDAR) by combining traditional and deep learning algorithms. To meet real-time demand, Octree with region-of-interest (ROI) selection is introduced and improved to filter the background in each frame, which improves the clustering speed.

Abstract Weather conditions such as rain, fog, snow, and dust can adversely impact sensing and perception, limit operational envelopes, and compromise the safety and reliability of advanced driver-assistance systems and autonomous vehicles. Physical testing of an autonomous system in a weather laboratory and on-road is costly and slow and exposes the system to only a limited set of weather conditions. To overcome the limitations of physical testing, a physics-based simulation workflow was developed by coupling computational fluid dynamics (CFD) with optical simulations of camera and lidar sensors. The computational data of various weather conditions can be rapidly generated by CFD and used to assess the impact of weather conditions on the sensors and perception algorithms.

Abstract Autonomous vehicles require precise knowledge of their position and orientation in all weather and traffic conditions for path planning, perception, control, and general safe operation. Here we derive these requirements for autonomous vehicles based on first principles. We begin with the safety integrity level, defining the allowable probability of failure per hour of operation based on desired improvements on road safety today. This draws comparisons with the localization integrity levels required in aviation and rail where similar numbers are derived at 10−8 probability of failure per hour of operation. We then define the geometry of the problem where the aim is to maintain knowledge that the vehicle is within its lane and to determine what road level it is on.

Abstract This work was supported jointly by the National Science Foundation of China under Grant No. 51875184 and the National key R&D programs, China New energy vehicles focus on special projects under Grant No. 2016YFB0100903-2.

Abstract The development of the technology of automated highways promises the opportunity for the vehicles to travel safely at a closer distance concerning each other. As such, vehicles moving in the wake of others experience a reduction in fuel consumption. This article investigates the effect of longitudinal distance between two passenger cars on drag coefficients numerically and experimentally. For the numerical analysis, the fluid flow at car speeds of 70, 90 and 110 km/h were examined. The Artificial Intelligence coding was applied to train an Artificial Neural Network to extend the calculated data. The optimum values for the inter-vehicle distance and the vehicle speed to assure the least drag coefficient are obtained. To support the numerical results an instrument designed and built particularly to accurately measure the fuel consumption was installed on a midsize sedan car and some field tests were carried out.

Abstract Road surface characteristics directly influence vehicle safety and performance, and its knowledge can be instrumental to road transportation system safety. This work focuses on the development of a test setup, which was utilized for real-time implementation of a road surface identification algorithm based on the acceleration response of an intelligent tire. Analysis of frequency domain data was used to leverage the tire-road contact information being relayed through the acceleration data. A signal processing algorithm was developed to separate each tire revolution, analyze it in real time, and convert it to the frequency domain in real time. In the end, the performance of the setup was validated with results from the literature, and the distinguishing signature possessed by each surface was used to categorize different terrains into the respective surface categories (Dry Asphalt, Wet Asphalt, Concrete) in real time.

Abstract This article presents data mining methodologies designed to support data-driven, long-term, and large-scale research in the areas of in-vehicle monitoring, learning, and assessment of older adults’ driving behavior and physiological signatures under a set of well-defined driving scenarios. The major components presented in the article include the instrumentation of an easily transportable vehicle data acquisition system (VDAS) designed to collect multimodal sensor data during naturalistic driving, an ontology that enables the study of driver behaviors at different levels of integration of semantic heterogeneity into the driving context, and a driving trip segmentation algorithm for automatically partitioning a recorded real-world driving trip into segments representing different types of roadways and traffic conditions.

Abstract Safety is always a crucial aspect of developing autonomous systems, and the motivation behind this project comes from the need to address the traffic crashes occurring globally on a daily basis. The present work studies the coexistence of the novel rule-based behavioral planning framework with the five key advanced driver assistance system (ADAS) features as proposed in this article to fulfill the safety requirements and enhance the comfort of the driver/passengers to achieve a receding-horizon autopilot. This architecture utilizes data from the sensor fusion and the prediction module for the prediction time horizon of 2 s iteratively, which is continuously moving forward (hence, the receding horizon), and helps the behavior planner understand the intent of other vehicles on the road in advance.

Abstract In the past years, the automotive industry has been integrating multiple hardware in the vehicle to enable new features and applications. In particular automotive applications, it is important to monitor the actions and behaviors of drivers and passengers to promote their safety and track abnormal situations such as social disorders or crimes. These applications rely on multiple sensors that generate real-time data to be processed, and thus, they require adequate data acquisition and analysis systems. This article proposes a prototype to enable in-vehicle data acquisition and analysis based on the middleware framework Robot Operating System (ROS). The proposed prototype features two processing devices and enables synchronized audio and video acquisition, storage, and processing. It was assessed through the implementation of a live inference system consisting of a face detection algorithm from the data gathered from the cameras and the microphone.

Abstract For safe and comfortable automated driving in the urban domain, especially in complex geometries as intersections, the prediction of surrounding traffic participants is fundamental. Several works in this field focus on predicting the behavior of vulnerable road users (VRU) at crossings. However, no approaches were found dealing with predicting the interaction between turning vehicles giving right of way or cooperating with VRU, which is substantial for the trajectory planning of following vehicles. Infrastructural sensor data from an intersection in Germany enables the development of a prediction concept for vehicles interacting with VRU. Our studies show that the original criteria for classifying an interaction between vehicles and VRU—the post-encroachment time (PET)—is not suitable as ground truth criteria for the aimed prediction. Instead, a clustering-based labelling approach with k-means shows promising results in trajectory pattern distinction.

Abstract As of today, multiple studies suggest a perceptible influence of the vehicle body stiffness on the drivability and steering feel. Most of them use subjective methods to score changes in stiffness but do not conduct further measurements to explain the underlying physical chain. This interaction between the body stiffness and vehicle dynamics is not fully understood and requires further research, especially in the on-center behavior and maneuvers of low-lateral dynamics. This research focuses on these two areas by measuring the steering inputs, the resulting vehicle response and the vibrational behavior of the body on a freeway and a comfort test track. Afterward, the main effects of different stiffening measures are analyzed and discussed. Regarding the influence on the steering feel, differences can be measured but seem too small to be perceptible for a normal driver.

Abstract A classical antiskid brake system (ABS) is typically used to control the brake fluid pressure by creating repeated cycles of decreasing and increasing brake force to avoid wheel locking, causing the fluctuation of the brake hydraulic pressure and resulting in vibration during wheel rotation. This article proposes a new approach of skid control for ABS by controlling the disk pad position. This new approach involves using a modest control method to determine the optimal skid that allows the wheel to exert maximum friction force for decelerating the vehicle by shifting the brake pad position instead of modulating the brake fluid pressure. This pad position control (PPC) method works in a continuous manner. Therefore, no rapid changes are required in the brake pressure and wheel rotation speed. To identify the PPC braking performance, braking test simulations and experiments have been carried out.

Abstract Public discussions on the wide-scale implementation of connected and autonomous vehicles (CAVs) mostly rely on the media. As such, what is usually understood about “autonomous vehicle technology” by the general society is not necessarily equal to the current stage of the industrial production of “autonomous vehicles” in a similar timeline. To elaborate, society tends to have a misunderstanding about the technology where the autonomous vehicle (AV) is commonly perceived as a “vehicle with the highest level of automation” [1]. In reality, to enable a feasible, market-wide deployment of the technology, CAV technology, as a product, should be released to the market incrementally in a technologically realistic timeline. This unrealistic expectation and misunderstanding by the public, due to the aforementioned misapprehensions, subsequently puts impractical business expectations on engineering and development teams.