Search Results

This paper presents an evaluation of two different Vehicle to Infrastructure (V2I) applications, namely Red Light Violation Warning (RLVW) and Green Light Optimized Speed Advisory (GLOSA). The evaluation method is to first develop and use Hardware-in-the-Loop (HIL) simulator testing, followed by extension of the HIL testing to road testing using an experimental connected vehicle. The HIL simulator used in the testing is a state-of-the-art simulator that consists of the same hardware like the road side unit and traffic cabinet as is used in real intersections and allows testing of numerous different traffic and intersection geometry and timing scenarios realistically. First, the RLVW V2I algorithm is tested in the HIL simulator and then implemented in an On-Board-Unit (OBU) in our experimental vehicle and tested at real world intersections.

The falling cost of lithium ion batteries combined with an ongoing need to reduce greenhouse gas emissions is driving the proliferation of affordable long-range battery electric vehicles (BEVs). However, an inherent challenge with longer-range BEVs is the increased time required to fully charge the battery using standard 120/240 V AC power outlets. One approach to address this issue involves moving to higher power onboard AC chargers; however, household and utility wiring may not allow for the full capability of these higher power chargers. This study explores the typical time available for vehicle charging during an overnight stop based on real-world customer “MyFord Mobile” (MFM) data collected from Ford electrified vehicles. Through this approach, the available overnight time for recharging and required energy to be added to the battery are evaluated under the influence of typical daily driving distances, extreme ambient temperatures, and value charging time windows.

The advancement towards development of autonomy follows either the bottom-up approach of gradually improving and expanding existing Advanced Driver Assist Systems (ADAS) technology where the driver is present in the control loop or the top-down approach of directly developing Autonomous Vehicles (AV) hardware and software using alternative approaches without the driver present in the control loop. Most ADAS systems today fall under the classification of SAE Level 1 which is also referred to as the driver assistance level. The progression from SAE Level 1 to SAE Level 2 or partial automation involves the critical task of merging autonomous lateral control and autonomous longitudinal control such that the tasks of steering and acceleration/deceleration are not required to be handled by the driver under certain conditions [1].

Level 2 (L2) partially automated vehicle systems require the driver to continuously monitor the driving environment and be prepared to take control immediately if necessary. One of the main challenges facing developers of these systems is how to ensure that drivers understand their role and stay alert as the systems require. With little real world data, it has been difficult to understand user attitudes and behaviors toward the implementation and use of partially automated vehicles. At the time of this study, Tesla was one of the few OEMs with a partially automated vehicle feature available on the market; Autopilot. In order to understand how customers interact with a partially automated vehicle, a study was conducted to observe people driving their own Tesla vehicles while autopilot was engaged. Sixteen Tesla owners (14 males and 2 females) between ages 25 to 60 had their vehicles instrumented with video/audio data collection systems for three consecutive days.

The construction of the Ford ELTEC (Electronic Technology) vehicle has offered a unique opportunity to demonstrate the practical advantages of using modern electronics in a family car. Included in the specification is the integrated control of a lean burn engine and a continuously variable transmission from a single microprocessor. A number of novel features are controlled such as ionisation feedback, intake port, variable geometry induction and an electronic throttle.

With the recent advancements in sensing and processing capabilities of consumer mobile devices (e.g., smartphone, tablet, etc.), they are becoming attractive choices for pervasive computing applications. Always-on monitoring of human movement patterns is one of those applications that has gained a lot of importance in the field of mobility and transportation research. Automatic detection of the current transportation mode (e.g., walking, biking, riding a shuttle, etc.) of a consumer using data from their smartphone sensors enables delivering of a number of customized services for multi-modal journey planning. Most accurate models for automatic mode detection are trained with supervised learning algorithms. In order to achieve high accuracy, the training datasets need to be sufficiently large, diverse, and correctly labeled.

Road Load Data is an important source of information for quality improvements. Vehicle and component load information, such as driver behaviour and other characteristics of vehicle use in real world conditions, are the basis for many engineering tasks, including fuel economy and life-time optimization. This new approach in road load data acquisition is based on the increasing existence of data bus networks in modern vehicles, as well as further improvements in data acquisition technologies. The applications of which alllow smart, inobtrusive solutions and, increasingly, the collection of real world customer data. This methodology of data collection leads to a significant alteration of the company-wide data base, relevant for future engineering efforts. The growing share of real world customer data will result in a more optimized and customer-orientated range of solutions, for all areas of vehicle engineering.

Accurate road friction coefficient is crucial for the proper functioning of active chassis control systems. However, road friction coefficient is difficult to be measured directly. Using the available onboard sensors, a model-based Extended Kalman filter (EKF) algorithm is proposed in this paper to estimate road friction coefficient. In the development of estimation algorithm, vehicle motion states such as sideslip angle, yaw rate and vehicle speed are first estimated. Then, road friction coefficient estimator is designed using nonlinear vehicle model together with the pre-estimated vehicle motion states. The proposed estimation algorithm is validated by both simulations and tests on a scaled model vehicle.

Autonomous vehicles and advanced driver assistance systems have functionality realized across numerous distributed systems that interact with a dynamic cyber-physical environment. This complexity raises the potential for emergent behaviours which are not intended for the system’s operational use. The need to analyze the intended functionality of these emergent behaviours for potential hazards, which may occur in absence of faults, are aspects of the ISO PAS 21448, Safety of the Intended Functionality (SOTIF) [1]. The Safety of the Intended Functionality or SOTIF is a framework for developing systems which are free from unreasonable risk due to the intended functionality or performance limitations of a system which is free from faults. This is meant to complement Functional Safety which is covered in ISO 26262 [2]. The major focus of SOTIF is to aid in the functional development of a system.

One of the ways to reduce city congestion is to balance the traffic flow on the road network and maximally utilize all road capacities. There are examples showing that, if the drivers are not competitive but cooperative, the road network usage efficiency and the traffic conditions can be improved. This motivates the idea of designing a cooperative routing algorithm to benefit most vehicles on the road. This paper presents a semi-cooperative social routing algorithm for large transportation network with predictive traffic density information. The goal is to integrate a cooperative scheme into the individual routing and achieve short traveling time not only for the traveler itself, but also for all vehicles in the road network. The most important concept of this algorithm is that the route is generated with the awareness of the total travel time added to all other vehicles on the road due to the increased congestion.

As automakers begin to design the autonomous vehicle (AV) for the first time, they must reconsider customer interaction with the Automatic Speech Recognition (ASR) system carried over from the traditional vehicle. Within an AV, the voice-to-ASR system needs to be capable of serving a customer located in any seat of the car. These shifts in focus require changes to the microphone selection and placement to serve the entire vehicle. Further complicating the scenario are new sources of noise that are specific to the AV that enable autonomous operation. Hardware mounted on the roof that are used to support cameras and LIDAR sensors, and mechanisms meant to keep that hardware clean and functioning, add even further noise contamination that can pollute the voice interaction. In this paper, we discuss the ramifications of picking up the intended customer’s voice when they are no longer bound to the traditional front left “driver’s” seat.

This paper demonstrates a solution to the security problem for automotive wireless powertrain networking. That is, the security for wireless automotive networking requires a localization function before we allow a node to join the network. We explain why for powertrain wireless networking, this ability of identifying the precise location of a communicating wireless node is critical. In this paper, we explore existing methods that others have used to implement localization for wireless networking. Then, we apply machine-learning techniques to a dataset that has localization information associated with received signal strength indication. We reveal insights provided by our dataset though an exploration with statistics and visualization. We then present our problem in terms of pattern recognition via multiple techniques, including Naïve Bayes Classifier and Artificial Neural Networks.

Electrified powertrains respond to driver demand for vehicle acceleration by producing power through either the electric drive system or an on-board combustion engine or both. In Plug-In Hybrid Vehicles (PHEVs), the powertrain provides the purest form of transportation when responding to driver demand through the electric drive system. We develop a method to size the electric drive system in PHEVs to provide zero emission driving in densely populated urban regions. We use real world data from Europe and calculate instantaneous wheel power during trips. Ray tracing is used to identify the regions where trips occur and the population density of these regions is obtained from an open source dataset published by Eurostat. Regions are categorized by their population density into urban and extra-urban regions. Real world data from these regions is analyzed to determine the wheel power required in urban and extra-urban settings.

Recommender systems guide a user to useful objects in a large space of possible options in a personalized way. In this paper, we study recommender systems for vehicles. Compared to previous research on recommender systems in other domains (e.g., movies or music), there are two major challenges associated with recommending vehicles. First, typical customers purchase fewer cars than movies or pieces of music. Thus, it is difficult to obtain rich information about a customer’s vehicle purchase history. Second, content information obtained about a customer (e.g., demographics, vehicle preferences, etc.) is also difficult to acquire during a relatively short stay in a dealership. To address these two challenges, we propose an interactive vehicle recommender system based a novel machine learning method that integrates decision trees and multi-armed bandits. Decision tree learning effectively selects important questions to ask the customer and encodes the customer's key preferences.

Adaptive Cruise Control (ACC) is becoming a common feature in modern day vehicles with the advancement of Advanced Driver Assist Systems (ADAS). Simultaneously, Hardware-in-the-Loop (HIL) simulation has emerged as a major component of the automotive product development cycle as it can accelerate product development and validation by supplementing in-vehicle testing. Specifically, HIL simulation has become an integral part of the controls development and validation V-cycles by enabling rapid prototyping of control software for Electronic Control Units (ECUs). Traditionally, ACC algorithms have been validated on a system or subsystem HIL bench with the ACC ECU in the loop such that the HIL bench acts as the host or trailing vehicle with the target or preceding vehicle usually simulated using as an object that follows a pre-defined motion profile.

There has been a great effort expended in identifying causes of Hydro-Carbon (HC) and Particulate Matter (PM) emissions resulting from poor spray preparation, leading to characterization of fueling behavior near nozzle. It has been observed that large droplet size is a primary contributor to HC and PM emission. Imaging technologies have been developed to understand the break-up and consistency of fuel spray. However, there appears to be a lack of studies of the spray characteristics at the End of Injection (EOI), near nozzle, in particular, the effect that tip deposits have on the EOI characteristics. Injector tip deposits are of interest due to their effect on not only fuel spray characteristics, but also their unintended effect on engine out emissions. Using a novel imaging technique to extract near nozzle fuel characteristics at EOI, the impact of tip deposits on Gasoline Direct Injection (GDI) fuel injectors at the EOI is being examined in this work.

The rapid development of connected and automated vehicle technologies together with cloud-based mobility services are revolutionizing the transportation industry. As a result, huge amounts of data are being generated, collected, and utilized, hence providing tremendous business opportunities. However, this big data poses serious challenges mainly in terms of data privacy. The risks of privacy leakage are amplified by the information sharing nature of emerging mobility services and the recent advances in data analytics. In this paper, we provide an overview of the connected vehicle landscape and point out potential privacy threats. We demonstrate two of the risks, namely additional individual information inference and user de-anonymization, through concrete attack designs. We also propose corresponding countermeasures to defend against such privacy attacks. We evaluate the feasibility of such attacks and our defense strategies using real world vehicular data.

During development of complex automotive technologies, a significant engineering effort is often dedicated to ensuring the safe performance of these systems. An important aspect to consider when assessing the viability of different safety designs or strategies is the time period from the occurrence of a fault to the violation of a Safety Goal (SG). This time period is commonly referred to as the Fault Tolerant Time Interval (FTTI). In Automotive Safety, ISO 26262 [1] calls for the identification and appropriate partitioning of the FTTI, however very little guidance is provided on how to do this. This paper presents a process, covering the entire safety development lifecycle, for the identification of timing constraints and the development of associated requirements necessary to prevent Safety Goal violations.