Search Results

Data fusion plays a central role in more and more automotive applications, especially for driver assistance systems. On the one hand the process of data fusion combines data and information to estimate or predict states of observed objects. On the other hand data fusion introduces abstraction layers for data description and allows building more flexible and modular systems. The data fusion process can be divided into a low-level processing (tracking and object discrimination) and a high level processing (situation assessment). High level processing becomes more and more the focus of current research as different assistance applications will be combined into one comprehensive assistance system. Different levels/strategies for data fusion can be distinguished: Fusion on raw data level, fusion on feature level and fusion on decision level. All fusion strategies can be found in current driver assistance implementations.

Advanced driver assistance systems like cooperative adaptive cruise control (CACC) are designed to exploit information provided by vehicle-to-vehicle (V2V) and/or infrastructure-to-vehicle (I2V) communication systems to achieve desired objectives such as safety, traffic fluidity or fuel economy. In a day to day traffic scenario, the presence of unknown disturbances complicates achieving these objectives. In particular, CACC benefits in terms of fuel economy require the prediction of the behavior of a preceding vehicle during a finite time horizon. This paper suggests an estimation method based on actual and past inter-vehicle distance data as well as on traffic and upcoming traffic lights. This information is used to train a set of nonlinear, autoregressive (NARX) models. Two scenarios are investigated, one of them assumes a V2V communication with the predecessor, the other uses only data acquired by on-board vehicle sensors.

A Brake By Wire (BBW) system is generally composed of electro-mechanical calipers at each wheel, a pedal simulator and a central controller. The brake demand is processed by the pedal and the central controller commands the brake distribution for each brake actuator. The highly responsive and independent brake actuators lead to enhanced controllability which should result in not only better basic braking performance, but also improvements in various active braking functions such as integrated chassis control, driver assistance systems, or cooperative regenerative braking. Although the BBW system has the potential for numerous advantages and innovations in braking, it has yet to be successfully introduced in series production mainly due to safety and cost concerns. Recent studies have been made to investigate the functional safety aspects and additional mechanical backup measures in this regard.

We present a method for the estimation of vehicle mass and road gradient for a light passenger vehicle. The estimation method uses information normally available on the vehicle CAN bus without the addition of extra sensors. A composite parameter estimation algorithm incorporating a nonlinear adaptive observer structure uses vehicle speed over ground and driving torque to estimate mass and road gradient. A system of filters is used to avoid deriving acceleration directly from wheel speed. In addition, a novel data fusion method makes use of the regressor structure to introduce information from other sensors in the vehicle. The dynamics of the additional sensors must be able to be parameterised using the same parameterisation as the complete vehicle system dynamics. In this case we make use of an Inertial Measurement Unit (IMU) which is part of the vehicle safety and Advanced Driver Assist Systems (ADAS).

In-vehicle communication faces increasing bandwidth demands, which can no longer be met by today's MOST150, FlexRay or CAN networks. In recent years, Fast Ethernet has gained a lot of momentum in the automotive world, because it promises to bridge the bandwidth gap. A first step in this direction is the introduction of Ethernet as an On Board Diagnostic (OBD) interface for production vehicles. The next potential use cases include the use of Ethernet in Driver Assistance Systems and in the infotainment domain. However, for many of these use cases, the Fast Ethernet solution is too slow to move the huge amount of data between the Domain Controllers, ADAS Systems, Safety Computer and Chassis Controller in an adequate way. The result is the urgent need for a network technology beyond the Fast Ethernet solution. The question is: which innovation will provide enough bandwidth for domain controllers, fast flashing routines, video data, MOST-replacement and internal ECU buses?

Driving inattention caused by drowsiness has been a significant reason for vehicle crash accidents, and there is a critical need to augment driving safety by monitoring driver drowsiness behaviors. For real-time drowsy driving awareness, we propose a vision-based driver drowsiness monitoring system (DDMS) for driver drowsiness behavior recognition and analysis. First, an infrared camera is deployed in-vehicle to capture the driver’s facial and head information in naturalistic driving scenarios, in which the driver may or may not wear glasses or sunglasses. Second, we propose and design a multi-modal features representation approach based on facial landmarks, and head pose which is retrieved in a convolutional neural network (CNN) regression model. Finally, an extreme learning machine (ELM) model is proposed to fuse the facial landmark, recognition model and pose orientation for drowsiness detection. The DDMS gives promptly warning to the driver once a drowsiness event is detected.

Efficiency testing of hybrid-electric vehicles is challenging, because small run-to-run differences in pedal application can change when the engine fires or the when the friction brakes supplement regenerative braking, dramatically affecting fuel use or energy regeneration. Electronic accelerator control has existed for years, thanks to the popularity of throttle-by-wire (TBW). Electronic braking control is less mature, since most vehicles don’t use brake-by-wire (BBW). Computer braking control on a chassis dynamometer typically uses a mechanical actuator (which may suffer backlash or misalignment) or braking the dynamometer rather than the vehicle (which doesn’t yield regeneration). The growth of electrification and autonomy provides the means to implement electronic brake control. Electrified vehicles use BBW to control the split between friction and regenerative braking. Automated features, e.g. adaptive cruise control, require BBW to actuate the brakes without pedal input.

In previous work, AC Compressor Cycling (ACC) was modeled by incorporating evaporator thermal inertia in Mobile Air Conditioning (MAC) performance simulation. Prediction accuracy of >95% in average cabin air temperature has been achieved at moderate ambient condition, however the number of ACC events in 1D CAE simulation were higher as compared to physical test [1]. This paper documents the systematic approach followed to address the challenges in simulation model in order to bridge the gap between physical and digital. In physical phenomenon, during cabin cooldown, after meeting the set/ target cooling of a cabin, the ACC takes place. During ACC, gradual heat transfer takes place between cold evaporator surface and air flowing over it because of evaporator thermal inertia.

Typically, when one thinks of advanced driver assistance systems (ADAS), systems such as Forward Collision Warning (FCW) and Collision Imminent Braking (CIB) come to mind. In these systems driver assistance is provided based on knowledge about the subject vehicle and surrounding objects. A new class of these systems is being implemented. These systems not only use information on the surrounding objects but also use information on the driver's response to an event, to determine if intervention is necessary. As a result of this trend, an advanced level of understanding of driver braking behavior is necessary. This paper presents an alternate method of analyzing driver braking behavior. This method uses a frequency content based approach to study driver braking and allows for the extraction of significantly more data from driver profiles than traditionally would have been done.

Advanced driver assistance systems (ADAS) are becoming increasingly important for today's commercial vehicles. It is therefore crucial that different ADAS functionalities interact seamlessly with existing electronic control unit (ECU) networks. For example, autonomous emergency braking (AEB) systems directly influence the brake ECU and engine control. It has already become impossible to reliably validate this growing interconnectedness of control interventions in vehicle behavior with prototype vehicles alone. The relevant tests must be brought into the lab at an earlier development stage to evaluate ECU interaction automatically. This paper presents an approach for using hardware-in-the-loop (HIL) simulation to validate ECU networks for extremely diverse ADAS scenarios, while taking into account real sensor data. In a laboratory environment, the sensor systems based on radars, cameras, and maps are stimulated realistically with a combination of simulation and animation.

Intersection crashes are a frequent and dangerous crash mode in the U.S. Emerging Intersection Advanced Driver Assistance Systems (I-ADAS) aim to assist the driver to mitigate the consequences of vehicle-to-vehicle crashes at intersections. In support of the design and evaluation of such intersection assistance systems, characterization of the road, environment, and drivers associated with intersection crashes is necessary. The objective of this study was to characterize intersection crashes using nationally representative crash databases that contained all severity, serious injury, and fatal crashes. This study utilized four national crash databases: the National Automotive Sampling System, General Estimates System (NASS/GES); the NASS Crashworthiness Data System (CDS); and the Fatality Analysis Reporting System (EARS) and the National Motor Vehicle Crash Causation Survey (NMVCCS).

Starting from the USA and followed by the European Union, legal requirements concerning “Tire Pressure Monitoring Systems” (TPMS) for passenger cars and light trucks will be introduced in China as well and therefore in the third of the three largest automobile markets worldwide. Changes of pressure dependent physical tire properties such as dynamic roll radius and a certain tire eigenfrequency, which are included in the ESC-wheel speed signals, indicates pressure loss in an indirect manner. Systems with corresponding working principles are called “indirect Tire Pressure Monitoring System” (iTPMS). Since the tire is a structural element with varying characteristics according to the design parameters, the roll radius and frequency behavior due to pressure loss is variable as well. As a consequence, tires have to be evaluated regarding there compatibility to iTPMS during the vehicle development process.

The number of advanced driver assistance systems is constantly increasing. Many of the systems require visual attention, and a way to reduce risks associated with inattention could be to use multisensory signals. A driver's main attention is in front of the car, but inattention to surrounding areas beside and behind the car can be a risk. Therefore, there is a need for driver assistance systems capable of directing attention to the sides. In a simulator study, combined visual, auditory and vibrotactile signals for directional attention capture were designed for use in driver assistance systems, such as blind spot information, parking assistance, collision warnings, navigation, lane departure warning etc. An experiment was conducted in order to measure the effects of the use of different sensory modalities on directional attention (left/right) in driver assistance systems.

Complex systems, such as modern advanced driver assistance systems (ADAS), consist of many interacting components. The number of options promises considerable flexibility for configuring systems with many cost-performance-value tradeoffs; however the potential unique configurations are exponentially many prohibiting a build-test-fix approach. Instead, engineering analysis tools for rapid design-space navigation and analysis can be applied to find feasible options and evaluate their potential for correct system behavior and performance subject to functional requirements. The OpenMETA toolchain is a component-based, design space creation and analysis tool for rapidly defining and analyzing systems with large variability and cross-domain requirements. The tool supports the creation of compositional, multi-domain components, based on a user-defined ontology, which captures the behavior and structure of components and the allowable interfaces.

Virtual testing of advanced driver assistance systems (ADAS) using a simulation environment provides great potential in reducing real world testing and therefore currently much effort is spent on the development of such tools. This work proposes a simulation and hardware-in-the-loop (HIL) framework, which helps to create a virtual test environment for ADAS based on real world test drive. The idea is to reproduce environmental conditions obtained on a test drive within a simulation environment. For this purpose, a production standard BMW 320d is equipped with a radar sensor to capture surrounding traffic objects and used as vehicle for test drives. Post processing of recorded GPS raw data from the navigation system using an open source map service and the radar data allows an exact reproduction of the driven road including other traffic participants.

New challenges and complexities are continuously increasing in advanced driver assistance systems (ADAS) development (e.g. active safety, driver assistant and autonomous vehicle systems). Therefore, the health management of ADAS’ components needs special improvements. Since software contribution in ADAS’ development is increasing significantly, remote diagnosis and maintenance for ADAS become more important. Furthermore, it is highly recommended to predict the remaining useful life (RUL) for the prognosis of ADAS’ safety critical components; e.g. (Ultrasonic, Cameras, Radar, LIDAR). This paper presents a remote diagnosis, maintenance and prognosis (RDMP) framework for ADAS, which can be used during development phase and mainly after production. An overview of RDMP framework’s elements is explained to demonstrate how/when this framework is connected to database servers and remote analysis servers.

The automotive industry is swiftly moving toward Ethernet as the high-speed communication network for in-vehicle communication. There is nonetheless a need for protocols that go beyond what standard Ethernet has to offer in order to provide additional quality of service (QoS) to demanding applications such as advanced driver-assistance systems (ADAS) or audio/video streaming. The main protocols currently considered for that purpose are IEEE802.1Q, audio video bridging (AVB) with the credit-based shaper (CBS) mechanism (IEEE802.1Qav), and time-sensitive networking (TSN) with its time-aware shaper (TAS) (IEEE802.1Qbv). AVB/CBS and TSN/TAS both provide efficient QoS mechanisms, and they can be used in a combined manner, which offers many possibilities to the designer. Their use however requires dedicated hardware and software components and clock synchronization in the case of TAS.

Published information on studies of something so critical to safety as passenger vehicle tire pressures can be found [1, 2]; however, they only account for rolling tires. Studies related to spare tire pressures are lacking. This paper is the result of measurements on 150+ vehicles and the most surprising results are presented regarding the influence of Tire Pressure Monitoring Systems (TPMS) and the new spare tire locations and use. A statistical study was performed on the collected data to determine the correlation between tire pressures, vehicle age and TPMS. One particular topic of investigation was the relationship between various factors that influence spare tire pressure. Some newer models, particularly some mini-vans, have placed the spare tire in an unusual and inconvenient place for regular maintenance. Based on the data collected, TPMS has a positive influence on rolling tires but not on spare tires. The results support the need for TPMS to also monitor spare tire pressures.

The conventional radar modeling methods for automotive applications were either function-based or physics-based. The former approach was mainly abstracted as a solution of the intersection between geometric representations of radar beam and targets, while the latter one took radar detection mechanism into consideration by means of “ray tracing”. Although they each has its unique advantages, they were often unrealistic or time-consuming to meet actual simulation requirements. This paper presents a combined geometric and physical modeling method on millimeter-wave radar systems for Frequency Modulated Continuous Wave (FMCW) modulation format under a 3D simulation environment. With the geometric approach, a link between the virtual radar and 3D environment is established. With the physical approach, on the other hand, the ideal target detection and measurement are contaminated with noise and clutters aimed to produce the signals as close to the real ones as possible.

The way to autonomous driving is closely connected to the capability of verifying and validating Advanced Driver Assistance Systems (ADAS), as it is one of the main challenges to achieve secure, reliable and thereby socially accepted self-driving cars. Hardware-in-the-Loop (HiL) based testing methods offer the great advantage of validating components and systems in an early stage of the development cycle, and they are established in automotive industry. When validating ADAS using HiL test benches, engineers face different barriers and conceptual difficulties: How to pipe simulated signals into multiple sensors including radar, ultrasonic, video, or lidar? How to combine classical physical simulations, e.g. vehicle dynamics, with sophisticated three-dimensional, GPU-based environmental simulations? In this article, we present current approaches of how to master these challenges and provide guidance by showing the advantages and drawbacks of each approach.