Handbook of Driver Assistance Systems

Human information processing systems, as well as the individual driver characteristics interacting reciprocally with them, are particularly significant for the task of vehicle guidance. This chapter will describe these connections between driver, vehicle and environment using a simple system model. The driver’s intake, processing and output of information will be delineated. The relevant driver characteristics, capacities and skills for vehicle guidance will be described. Based on this understanding, requirements for vehicle guidance with regards to the driver will be systematized by considering subtasks and evaluated with respect to the limits of human capacity.

The attractive power of driving motor vehicles results from the expansion of human mobility far beyond the natural physiological capabilities of people such as radius of action, power, speed, transport capacity, independence of timing and choosing routes, etc. Unfortunately, the enormous kinetic energy involved in the dynamic process of driving is coupled with an inherent danger of loss of control.Both human factors and technical features of the road traffic system combined with their interactive compatibility decisively influence primary safety, i.e., accident prevention potential.Science established a successful method of gaining and comprehensively representing knowledge by derivation of empirical models in terms of qualitative (descriptive) and particularly quantitative (mathematical) models. Such modeling approaches for human driver behavior in road traffic with scope on specific capabilities and limitations are reported on, aiming at their challenges for driver assistance systems.As focal points of the following discussion, the predictability principle (in control systems theory terminology, this could be named “anticipatory observability criterion”), the acquisition of driving skills, and the quantification of collective and individual human driving competence will be highlighted. The gaps between intrinsic human performance limitations and physico-technical constraints of vehicle, road, and traffic-environment characteristics open up the most promising realms for the development of driver assistance systems.

The term driver assistance systems in the chapter title shall be understood to include vehicle automation. This chapter starts with a homogeneous and consistent classification and nomenclature of all kinds of driver assistance systems known and under discussion today (including vehicle automation). It thereby builds upon familiar classification schemes by the German Federal Highway Research Institute (BASt) and the standardization body SAE international. Detailed evaluation of the German legal situation for driver assistance systems and vehicle automation is provided in the following Sect. 2.In Sect. 3, an overview is given on the legal system in the US to reveal aspects relevant for vehicle automation. This is intended as initial information for those not acquainted to the US legal system which has been the first to regulate automation in several federal states.Finally, in Sect. 4, the current rating scheme of the European New Car Assessment Programme (EuroNCAP) is presented in comparison to legal instruments. The model of a consumer protection based approach proves to be a flexible instrument with great advantages in promoting new technologies. Technical vehicle regulations on the other hand rule minimum requirements. Both approaches are needed to achieve maximum vehicle safety.

In order to make any statements about the effect of advanced driver assistance systems (ADASs) on road safety, it is important to understand the accidents that happen. In 1970, 21,332 people were killed on German roads (West Germany). In 2013, 3,339 people were killed on the roads. The number of motor vehicles in Germany increased during this time: from 16.8 to 53.8 million. In order to get a better understanding of accident statistics, a shift of focus is required from the general view obtained from a country’s accident statistics to detailed analysis of the accidents that happen. This field extends from the representative surveys of the German Federal Statistical Office (Destatis), based on road accident reports, to the in-depth analyses of different stakeholders on road safety. Accident analysis was carried out for cars, trucks, buses, and powered two-wheelers based on the German In-Depth Accident Study (GIDAS) and the German insurers’ accident database (UDB). The safety potential of advanced driver assistance systems (ADASs) can be ascertained in a variety of ways. For the results here, an alternative, “what if” method, was used in order to quantify the effect of different generic ADASs for cars, trucks, and buses.

Driving a car is a task that requires predominantly cognitive resources. Which resources are required exactly and to which amount they are required depends on the characteristics of the situation. The situation comprises the driver, the vehicle, and the environment. Advanced driver assistance systems (ADAS) change the situation and thus the task of driving a car in several aspects. These changes have an impact on the driver and mainly concern workload, situation awareness, and mental models. Changes therein can result in behavioral changes subsumed under the term behavioral adaptation. Behavioral adaptation can be negative or positive or even both depending on the perspective. However, when developing and designing ADAS, the nature of the aforementioned changes resulting in behavioral adaptation must be understood and must be taken into account. Behavioral changes must further be an integral part of evaluating the effect of such systems. Because of the constant technological progress, ADAS increasingly constitute a step toward full automation. Therefore, experiences in other domains in which automation has reached higher levels than in passenger cars must also be taken into account. This chapter provides the basis to understanding such ADAS-related effects.

This chapter gives a brief overview of the automotive standard ISO 26262 containing requirements for functional safety in order to avoid or control systematic failures and random HW failures. In this context the hazard analysis and risk assessment for a driver assistance function is shown, and further steps to prevent relevant hazards outgoing from the function are described. Since very important for the driver assistance functions, hazards resulting from functional insufficiencies, which are out of the scope of ISO 26262, are discussed in the last part of this chapter.

Software development for automotive applications has become the most sophisticated and critical activity during the vehicle development. AUTOSAR (AUTomotive Open System ARchitecture) develops a standardized open software architecture for automotive electronic control units (ECUs). AUTOSAR is a partnership of automotive manufacturers, suppliers, and tool and semiconductor vendors.The focus is on managing the growing complexity in the development of automotive electric/electronic (E/E) architecture, with the aim to enable new technologies and improve development efficiency – without making compromises on quality. The standardization is realized in the three technical areas:1.Software architecture2.Development methodology3.Application interfacesBesides this focus AUTOSAR’s key success factors are its development agreement that controls the legal part of the collaboration between the partners and its lean organization that distinguishes between the “Founding Fathers” (i.e., the core partners) and other partners (premium, development, and associate partners) and thus installs lean processes for fast decisions. As a result of its joint development activities, AUTOSAR has provided several releases since its foundation in 2002: The latest Release 4.2.1 has been delivered on October 31, 2014, and contains more than 218 concepts. By October 2014 more than 180 partner companies successfully share and live AUTOSAR’s fundamental principle:Cooperate on standardization, compete on implementation.

In spite of the complexity and large variety of cars, electronic stability programs can still be tested in elaborate real test drives. However, due to the high system complexity, the complexity of the test cases, and the required scope of tests, this is not economically feasible for advanced driver assistance systems with environment perception. The repeatability of the tests, even under the exact same testing conditions and procedure, in practice does not exist due to various potential and occasionally unknown or disregarded influences. Therefore, the test results are not reproducible – Reproducibilityfirstly, because functionally relevant characteristics can depend on the interaction between multiple road users, and secondly, because they can be subject to complex interactions between boundary conditions such as the blinding effect of a low sun and its reflection on a wet road at a certain angle. The features of currently used advanced driver assistance systems (ADAS) access environmental information that is collected by several different sensors and processed to obtain a representation of the environment. To serve their purpose, these functions utilize different actuators and components of the human-machine interface. This architectural distribution of assistance functions to different control units and vehicle components results in a strong interconnection that must be considered during testing and that drives up the costs of testing. This chapter will highlight the advantages resulting from virtual integration Virtual Integrationand describe its functionality and limitations.

Depending on the application, different concepts for driving simulators have been realized. A quite common dynamic driving simulator concept for professional applications, i.e., a motion platform consisting of a hexapod based on a linear rail, is explained in detail. Using Daimler’s dynamic simulator as an example, the essential technological components of driving simulators are explained and the potentials and limitations due to the sensitivity of the human vestibular organ are discussed. Reasons for simulator sickness and how to avoid it complete the part on simulator design.A second focus is placed on the design of simulator experiments with test persons. A clear goal of the simulation experiment, a good choice of technical and psychological test design, and knowledge about the behavior of test persons help set up effective driving simulator tests. Driver distraction is an essential feature to simulate the complete scope of real accident situations and to assess the behavior of a representative set of test persons.The factors affecting the validity of simulator experiments compared to real-world experiments are discussed, and some findings on the opportunities and limitations of simulator experiments are presented.

Modern driver assistance systems are designed to intervene actively during driving in order to avoid an imminent accident or to reduce potentially health-threatening consequences of an accident. Due to the severe risks that are associated with such interventions in critical situations, it is of paramount importance that these systems are evaluated thoroughly in the development stage, with methods that not only demonstrate technical functionality but also take into account the behavior of the driver as he/she interacts with the technology. With increasing complexity and criticality of the driving situation, in which an assistance system is supposed to intervene, it becomes increasingly difficult to test the interaction of system performance and driver behavior reliably and safely. The vehicle in the loop (VIL) combines a virtual visual simulation with the kinesthetic, vestibular, and auditory feedback of a real car. As such, the VIL offers a variety of new options for evaluating driver assistance systems. Thus, the VIL constitutes a viable alternative to established evaluation methods such as field studies and conventional simulators. The VIL was developed on the basis of empirical evaluations. The present article describes this development process and discusses its potential for future development.

The term test procedureTest procedure refers to a method that describes how a system has to be tested to identify and assess specific behavior or properties by experiments. This also includes the specification of required tools, equipment, boundary conditions, and evaluation methods.Test procedures are an essential tool to check whether desired product properties are present, which of course also applies to the development of driver assistance systems. In addition to development and release testing that mainly is performed by the vehicle or system manufacturer, there are tests with the purpose of an independent product testing that are conducted by external test organizations. These tests are needed for vehicle type approval (for admission to a specific market), in the context of applying the standard for functional safety (in both cases mainly executed by technical services (being accredited as certification laboratory)) or for customer information purposes (by a test institute for consumer protection).The focus of this chapter is these “external” test methods. After a taxonomy of test procedures, the differences between legislation (type approval) and consumer testing are highlighted. Typical tests and the associated test setup, tools, and assessment criteria are discussed, and an outlook toward testing in the near and mid-future is given.

The development of driver assistance systems must be accompanied by user-oriented evaluation procedures in order to achieve high effectiveness and acceptance in everyday use while minimizing unwanted “side effects.” In addition to design recommendations such as the Response Code of Practice, user-oriented tests with both expert and nonexpert drivers have to be conducted in various phases of the development process.This chapter explains the suitability, planning, execution, and analysis of these user-oriented tests in a variety of test environments. It covers the whole range from driving simulator experiments, tests on proving grounds and in real traffic environments, up to and including field validation tests before final sign-off.Recommendations are given for the experimental design, including the selection of test persons, sample size, test scenarios, and setups, as well as the choice of suitable assessment parameters and criteria. A special section is devoted to the execution and analysis of field validation tests.Practical examples for all test settings complete the chapter, including from the area of Functional Safety. The evaluation and validation of Mercedes-Benz safety systems for rear-end crash avoidance is a recurrent theme, supplemented by examples of other types of driver assistance system.

Within this article, the testing method EVITA (Experimental Vehicle for unexpected Target Approach) for the evaluation of anticollision systems is presented. Using this method, it is possible to generate scenarios in a real test drive which are typical for rear-end collisions without endangering the occupants and vehicles. Furthermore, the criterion of speed reduction is explained to evaluate the effectiveness of the system, and finally the latest results are described.

Many tests of assistance systems can be performed more precisely, much more safely, and more efficiently using coordinated automated vehicles. A testing method that has been developed at Daimler AG to cope with the challenges of testing new assistance systems is presented. The concept for safe operation of automated vehicles on a test track is detailed by describing the technical components and the control strategy of the system. Results from precision and repeatability tests are discussed, and methods of planning tests efficiently and safely are described. The concept of virtual guide rails, which allows a vehicle being tested to act autonomously within a deterministic testing environment, is presented.In a separate section, the design of automatically driving crash targets is discussed. Two different concepts – the self-driving soft crash target and the over-drivable target carrier – are described in detail. Advantages and limitations of these concepts are discussed.The chapter concludes with a presentation of several typical test applications of coordinated automated vehicles as single vehicles for better precision and repeatability, as coordinated vehicles to set up complex scenarios that are too difficult to coordinate with human drivers, or as a combination of human-driven vehicles with precisely coordinated crashable targets in challenging traffic situations.

Driver assistance systems require fundamental information from sensors. In order to meet the high standard of safety and availability of these systems, the product quality is essential. Therefore, the selection process plays an important role during the purchasing process in the automotive industry. The surrounding and specific application defines the sensor design and manufacturing process of the sensor.For advanced system functions, the requirements of sensor data content and precision are increasing continuously; however, there are still some values which have not changed since the first ABS was introduced into the market. Even though the function remains relatively unchanged, the technology itself is changing. This opens up the possibility for the introduction of new features.This chapter provides a general overview of the key figures related to sensors for safety systems with details to the design and with special considerations to the fitment in the vehicle.

Typical characteristics of ultrasonic sensors for parking assistance systems in automobiles are described. The chapter includes the principles of sound conversion into electrical energy and vice versa, material and production of piezoceramic transducer elements, acoustic design, as well as structure, setup, and installation of complete sensor elements into a vehicle. Simulation, measurement, and evaluation techniques for obstacle detection and distance calculation in the close range around the car are another major focus of this chapter. Performance characteristics and robustness factors together with a summary about current and future application in various configurations for advanced parking systems on the way to fully automated parking represent a roundup at the end.

RADAR sensors are used in many driver assistance systems. We could ask whether RADAR for automobiles is similar to RADAR used in aircraft or military applications. The answer would be yes and no: yes, because the basic physical principles are valid for all domains, and no, because the requirements are very different. Whereas sometimes the requirements are less ambitious, enabling new concepts to be implemented, in other aspects, the requirements are higher due to the more complex traffic environment. The fundamentals of RADAR technology laid out in this chapter give an understanding of how RADAR works in typical automotive applications and why principle limitations define the performance. At the end of the chapter, the current technology of automotive RADAR is demonstrated by examples from industry, including their specifications.

Light Detection And Ranging (LIDAR) is an optical measurement principle to localize and measure the distance of objects in space. Basically it is similar to a RADAR-system, but instead of using microwaves LIDAR uses ultraviolett, infrared or beams within the visible light spectrum. Besides distance measurements, which is the basic task, LIDAR sensors can be used for a limited visual detection of objects by analyzing the light intensity, visibility measurement by analyzing the shape of the reflected LIDAR pulse, day/night detection as background illumination is significantly different between day and night, pollution detection and speed estimation. As several research vehicles for autonomous driving vehicles like e.g. Google car use LIDAR as basis sensor technology for scanning the environment there is an increase in development activities for LIDAR sensors meeting automotive requirements (cost, performance, reliability).Parking Assistance are systems which support the driver during parking manoeuver. This is achieved either by providing distance information to relevant obstacles, camera images or additionally by steering assistance. For the different system configurations requirements regarding sensors, signal processing, HMI, interfaces to the vehicle network need to be met. While first parking systems only provided informations to the driver, recent systems provide lateral steering support and current plus next gerneration parking systems will take more and more both lateral and longitudinal controll of the vehicle during the parking manoeuver. In the near future Valet Parking systems will be available, where the system searches for a suitable parking slot and performs the entire parking process automatically.

Today’s traffic environment, such as traffic and information signs, road markings, and vehicles, is designed for human visual perception (even if first approaches for automatic evaluation by electronic sensor systems in the vehicle exist – see Chap. 50, “Intersection Assistance”). This is done by different shapes, colors, or a temporal change of the signals.It is therefore a good choice to use a system similar to the human eye for machine perception of the environment. CameraCamera systems are ideal candidates as they offer a comparable spectral, spatial, and temporal resolution. In addition to the “replica” of human vision, specific camera systems can provide other functions, including imaging in infrared spectral regions for night vision or a direct distance measurement.This chapter covers details on specific applications of camera-based driver assistance systems and the resulting technical needs for the camera system. Use cases covering the outside and inside of the vehicle are shown. The basis of every camera system is the camera module with its main parts – the lens system and the image sensor. The underlying technology is described, and the formation of the camera image is discussed. Moving to the system level, basic camera architectures including mono and stereo systems are analyzed. The chapter is completed with a discussion of the calibration of camera systems.

Automobiles may acquire a rich variety of relevant information from image data and its analysis using machine vision techniques. This chapter provides an overview on the principles underlying image formation and image analysis. The perspective projection model is formulated to describe the mapping of the 3D real world onto the 2D image plane with its intrinsic and extrinsic calibration parameters. Image analysis typically begins with the identification of features. These may describe locations of particular local intensity patterns in a single image, such as edges or corners, or may quantify the 2D displacement of corresponding pixels between two images acquired at different time instances or by a multicamera system. Such features can be used to reconstruct the 3D geometry of the real world using stereo vision, motion stereo, or multiview reconstruction. Temporal tracking using Bayesian filters and its variations not only improves accuracy but readily allows for information fusion with data of other sensors. The chapter closes with two application examples. The first addresses object detection and tracking using multiple image features. The second application focuses on intersection understanding illustrating the large potential of high-level scene interpretation through machine vision.

Camera-based driver assistance went from pure research level activities in the early 1990s to standard equipment products in vehicles nowadays. This change is due to both technological advances and algorithmic developments. Especially, stereo vision plays a vital role in advanced driver assistance systems. In this chapter, we lay the foundations of stereo vision, show the specific needs for driver assistance, and build up a processing chain combining motion estimation and stereo information. The combination is called 6D-Vision and allows velocity estimation on a pixel level. For efficiency reasons, an intermediate stereo representation called Stixels is introduced from which an object representation is derived. The final section describes future trends in stereo vision such as a combination with machine learning approaches.

Detecting pedestrians in street scenes is one of the most important but also one of the most difficult problems of computer vision. Ideally, all pedestrians should be robustly detected in order to provide optimal assistance to the driver regardless of visual conditions. Different environmental factors complicate this, however. Especially problematic are changing weather and visual conditions as well as difficult lighting situations and road conditions. Moreover, an individual’s clothing and partial occlusions of pedestrians, for example, by parked cars, further complicate the detection task. Also, in comparison to many other objects in street scenes, pedestrians are characterized by a high degree of articulation further complicating the task.

More and more driver assistance systems are based on a fusion of multiple environment perception sensors. This chapter gives an overview about the objectives of sensor data fusion approaches, explains the main components involved in the perception process, and explains the special topics that need to be taken into consideration in developing a multi-sensor fusion system for driver assistance systems. Focus is put on the topics of data association, tracking, classification, and the underlying architecture. The architecture strongly influences the costs, performance, and the development process of a multi-sensor fusion system. As there are no deterministic methods that guarantee an optimal solution for developing an architecture, the chapter gives an overview of established, general architecture patterns in the field of sensor data fusion and discusses their benefits and drawbacks.

The requirements for a vehicle environment representation increase with the complexity of advanced driver assistance systems and automatic driving. The ability of the current traffic situation to interpret and predict is essential for being able to automatically derive reasonable decisions. As a consequence, a state of the art vehicle environment representation has to incorporate all relevant dynamic objects as well as static obstacles and context information. While dynamic objects are typically described by an object-based representation using state variables, static obstacles as well as free space area are commonly modeled using grid-based methods. This chapter gives an introduction into both of these concepts.The chapter is organized as follows: First, the difference between function-oriented and modular fusion architectures is discussed. Afterwards, the joint integrated probabilistic data association (JIPDA) filter is introduced, which is one method to realize an object-based environment model incorporating both state and existence uncertainties. Further, the representation of static obstacles with occupancy grids is described in detail and the incorporation of measurements of different sensor types is illustrated. Finally, several hybrid environment representations are introduced and an example for a strictly modular architecture, the hierarchical modular environment perception, is presented.

In current vehicles, redundant sensors with heterogeneous measurement principles are applied in increasing numbers. Taking the advantage of these already existing redundancies, the concept of a central virtual sensor for the estimation of kinematic vehicle properties is created, based on a set of close-to-series sensors, consisting of a MEMS inertial measurement unit, a GPS receiver, and odometry sensors. Furthermore, a real-time capable implementation of this architecture is realized, using a linearized Error-State-Space Kalman filter. This fusion filter is enhanced by a correction algorithm for measurement latencies of multiple sensors and a two-step plausibilization of raw measurement data. In addition, an integrated assessment of the data quality is implemented. It describes data consistency using an integrity measure and data accuracy with a virtual datasheet.

Navigation software cannot work without a digitized map. The question is, what is a digital map exactly? What kind of data is part of a digital map? How is the data structured? This chapter gives an overview of the digital map in the format of NDS. The documentation is based on the NDS specification and looks first to the navigation database from feature perspective with a more and more deeper look into the building blocks of the database. A short outlook into the future of the Navigation Data Standard will finish this chapter.

Connectivity among vehicles and with infrastructure is becoming increasingly important. It is the technological basis for future “cooperative intelligent transport systems.” The ability of a vehicle to communicate with its immediate surroundings (other vehicles, the road transport infrastructure, or traffic control centers) – commonly referred to as vehicle-to-X communication – enables a great number of new or improved functions for driver information and assistance. Such functions can lead to increased road safety, improved traffic efficiency, and greater personal comfort and convenience for the driver. After a short introduction, the aspects of the underlying data communication are explained. This comprises especially the radio channel and transmission system, the frequency allocation, as well as the required standardization activities. Next, a system overview is presented explaining the different subsystems, their structure and functionality, as well as the interaction with one another. Then, the important issues of data security and privacy protection are addressed, explaining the protection objectives and challenges followed by the description of potential solutions and their mechanisms. After that, the vehicle-to-X applications are described. The explanation of the basic principle and the message types is then illustrated by two practical examples, followed by some results on performance and user acceptance from the German field trial simTD. Finally, an economic assessment and possible introduction scenarios are discussed.

Nowadays, a wide variety of in-vehicle services connect to a backend system via Internet. The key is to deliver information to the vehicle that is not locally available but accessible via Internet. For example, systems such as Google Traffic use fleet data to analyze the current traffic situation. This chapter gives an overview of available technologies for transmitting, storing, and analyzing data in a backend system. Based on simulation and measurement methods, we investigated the time required for transmitting data via cellular networks. The estimated transmission time is about 400 ms, whereby it can increase to 1 s, depending on the traffic situation and the condition of the cellular network. The transmitted data are then available in the backend system for further analysis. The technological background of the methods used for data storage and analysis is introduced by an example of a minimalistic programming for a local danger warning database system. The example of extracting parameters in intersections to support driver assistance systems illustrates how relevant information can be generated from fleet data. Hence, these data allow an enhancement of as yet prototypically developed driver assistance systems and enable the development of new systems.

Within the standard architecture, hydraulic brake systems of passenger vehicles must decelerate the vehicle according to the driver’s request and to legal requirements (i.e., ECE R13H). Wheel forces generated during braking are transferred via tires to the road surface in such a way that the vehicle remains stable and controllable and always follows the driver’s intention. The basis for this is optimized pedal feel and optimized distribution of brake forces left/right and front/rear.Architectures can be extended to influence fuel consumption and emissions. The combination of internal combustion engines and electric machines (“hybrid drive”) as well as electric drive is becoming more widespread in passenger vehicles. Coupling of electric machines and drivetrain generates electric power by brake energy recuperation. The impact on brake system design is to offer the same pedal feel, independent of whether the vehicle is braked by an electric machine and/or by friction brakes (brake blending).Electronically controlled hydraulic brake systems (e.g., ABS, TCS, ESC) optimize vehicle dynamics. Together with beam and image sensors, this opens various opportunities to utilize additional brake system functions, i.e., for advanced driver assistance systems (ADAS), to fulfill future vehicle safety requirements. The performance of these advanced assistance systems mainly depends on vehicle system and component layout, hardware, software, sensors, and HMI.

Electromechanical brake systems are already on the market as EPB (Electric Park Brake), in combination with conventional “wet” hydraulic service brake systems. In the future, so-called hybrid service brake systems will appear with the front axle still being hydraulically actuated and the rear axle having new “dry” electromechanical brake systems as a feasible “high-end” solution for advanced vehicles.

The steering converts the turning movement applied to the steering wheel by the driver into a change in the steering angle of the steered wheels. At the same time, its job is to inform the driver, by means of the haptic feedback, of the current driving situation and the road conditions.

Above all, a driver assistance system (DAS) should be transparent to the driver and perform predictably and in accordance with the driver’s expectations. A DAS should also be simple to use and learn and have limits which are clear and well communicated to the driver. Other requirements of a DAS include comfort, safety of use, and acceptance by drivers and the wider community. The development of a DAS requires the cooperation of experts from engineering, science, and humanities. During the development process, research is very important and effective measurement methods must be developed and applied, by a team with extensive knowledge and experience. The issue of driver responsibility is of crucial importance as DAS plays an even greater role in the control of the vehicles. There are many HMI factors associated with a DAS. Although these are well known, they are not yet fully described in standards and requirements documents. Also standardized measurement methods are not well developed.

Interaction between human and machine occurs via interfaces that provide the driver with information and are meant to assist the driver in the task of driving safely, effectively, and efficiently. The following is an explanation of how displays and controls must be designed in the course of product development and which aspects deserve the most attention from the standpoint of the interaction between human and machine. Firstly, a working model is presented in order to explain human information processing and the action process. This model can be regarded as the foundation for designing an HMI. This is followed by various methods of systematizing displays and controls best suited for approaching the issues involved in driving a vehicle. However, the human being should be at the center of the design process, which is the reason why design guidelines and principles are listed, in order to explain the underpinnings of the approach while focusing on user-oriented implementation.

This chapter gives an overview of the requirements for the input devices for driver assistance functions and the resulting design options: The reader is provided with a systematic procedure for designing input devices according to (Kircher JH, Baum E (Hrsg), Mensch-Maschine-Umwelt. Ergonomie für Konstrukteure, Designer, Planer und Arbeitsgestalter (Man–machine environment. Ergonomics for engineers, designers, planners and human factors engineers). Beuth Verlag GmbH, Berlin/Köln, 1986). This procedure will begin with identifying the requirements for driver assistance system (DAS) input devices, then follows an explanation of how which body part (ex. finger, hand, etc.), posture and grip type, for system interactions are determined. Additionally, it supports the selection of input devices and provides guidance of how to avoid accidental and unauthorized input. Finally it helps with the design and geometric integration of the arrangement, the definition of feedback and use direction, travel and resistance and the identification of controls. General recommendations are illustrated through specific examples of hardware, demonstrating how manifold input controls can be. In the last part of the chapter an overview of novel operation concepts is given, most of which are not currently implemented in vehicles, however, are estimated to gain importance in the future.

In modern vehicles, we are faced with a rapidly increasing flood of information to the driver coming from the own vehicle and neighboring vehicles, from the road, and from telecommunication equipment. In addition to established information systems, driver assistance, collision mitigation, and collision avoidance systems are being integrated more and more in vehicles. The information coming from all those systems must be presented to the driver with appropriate displays taking into consideration the ergonomic requirements of the human/machine interface.Keeping to the former standard practice, i.e., providing each new information component with its own display and an individual keypad, inevitably would have led to an overloaded cockpit, similar to that in aircraft, on which displays and indicators have to be relocated to unfavorable read-off positions and input elements have to be relocated to areas not easy to reach. Current and future vehicle information systems provide this huge amount of information mainly in three information centers: a more or less reconfigurable instrument cluster and a head-up display, both with driver-relevant information, and a center console display with driver and passenger relevant information. For these systems an appropriate bundling of the information, in conjunction with menu-prompted operating techniques, is essential both technically and ergonomically.

This chapter first describes a model of human information processing and introduces the interfaces between human and machine. Requirements for warning elements are presented and so are examples of warning elements for forward and sideways guidance. Finally, a method for pregrouping the warning elements and criteria for assessing them during testing are presented.

This following chapter deals with driver condition detection. After delineating the factors relevant to detecting a driver’s condition and discussing the reasons for addressing the subject in terms of accident risk and the corresponding potentials and challenges (Sect. 1), three potential uses of driver condition detection are examined: detection of inattentiveness (Sect. 2), detection of drowsiness (Sect. 3), and detection of medical emergencies (e.g., a heart attack; Sect. 4). The respective driver conditions are defined, relevant measuring variables and their corresponding measuring procedures present, and selected applications expanded upon. Section 5 addresses driver condition monitoring systems currently available on the market and names the measuring variables and procedures used by those systems, before giving a short overview of the problem of potential false alarms in Sect. 6.

Both for driver assistance systems and highly automated driving, the in-depth understanding of traffic situations becomes more and more important. From the viewpoint of a warning driver assistance system, the authors analyze the requirements and challenges of risk assessment and driver intent inference in complex urban scenarios and provide a systematic overview of existing approaches. Furthermore, the ability of each approach to deal with more than two alternative maneuvers, partially observable feature sets, and potential interaction between traffic participants is evaluated. It is found that generative approaches and Bayesian networks in particular show great potential for driver intent inference, but it is also argued that more effort should be put into modeling the driver’s situation awareness. Based on four concrete examples, the benefits of awareness-based situation analysis are demonstrated with respect to the avoidance of unnecessary warnings, the detection of occluded traffic participants, further improvement of the driver intent inference itself, as well as the prediction of the future trajectories of relevant traffic participants.

Many driver assistance systems (DAS) use the electronic stability control (ESC) system for their control tasks, while ESC itself uses the antilock brake system (ABS) and traction control system (ASR, TCS) for the control of the lateral dynamics of the vehicle. This chapter starts with the description of the systems ABS and ASR as they are used by ESC. Then the description of the system ESC as is used by DAS follows. At the end of the chapter, the brake-based assistance functions as used by DAS are described.

Motorcycling is a fascinating kind of transportation. While the riders’ direct exposure to the environment and the unique driving dynamics are essential to this fascination, they both cause a risk potential which is several times higher than when driving a car.This chapter gives a detailed introduction to the fundamentals of motorcycle dynamics and shows how its peculiarities and limitations place high demands on the layout of dynamics control systems, especially when cornering. The basic principles of dynamic stabilization and directional control are addressed along with four characteristic modes of instability (capsize, wobble, weave, and kickback). Special attention is given to the challenges of braking (brake force distribution, dynamic over-braking, kinematic instability, and brake steer torque induced righting behavior).It is explained how these challenges are addressed by state-of-the-art brake, traction, and suspension control systems in terms of system layout and principles of function. It is illustrated how the integration of additional sensors – essentially roll angle assessment – enhances the cornering performance in all three categories, fostering a trend to higher system integration levels.An outlook on potential future control systems shows exemplarily how the undesired righting behavior when braking in curves can be controlled, e.g., by means of a so-called brake steer torque avoidance mechanism (BSTAM), forming the basis for predictive brake assist (PBA) or even autonomous emergency braking (AEB). Finally, the very limited potential of brake and chassis control to stabilize yaw and roll motion during unbraked cornering accidents is regarded, closing with a promising glance at roll stabilization through a pair of gimbaled gyroscopes.

From a driver’s perspective, controlling a vehicle means controlling the speed and the path curvature. In exceptional circumstances, e.g., in emergency evading situations, also the orientation of the vehicle has to be controlled. In a narrower sense, vehicle handling refers to vehicle dynamics like cornering and swerving and includes the vehicle stability. The advances in global chassis control technology have been used to further improve the vehicle safety and handling qualities. The effects of active systems are well understood in the context of how they contribute to the overall vehicle performance.Altering the path curvature can easily be achieved by increasing the yaw gain such that the driver steering input is small. This strategy is only applicable up to a medium speed. The yaw rate’s normal driving range decreases significantly with vehicle speed, because the available tire–road friction is quickly saturated at high speed when the steering wheel angle input is too high. The strategy at high speed therefore must be to decrease steady-state yaw gain.At the limit of friction, where safety becomes relevant, the handling controller determines how the vehicle remains stable. All available actuators are incorporated and coordinated to reach this goal. The active chassis gives the driver optimal support for avoiding accidents. In the region beyond the limit of friction, the main task of the control system is to prevent the car from skidding heavily so that the car remains on track.During normal driving car drivers usually expect a linear yaw response of the vehicle with small phase lag. Most drivers have no experience of loss of linearity caused by saturation of tire forces. If saturation happens at the rear axle, the sideslip angle will increase quickly and therefore causes a hazardous driving problem for many drivers. The primary task of the control system should be to keep the vehicle sideslip angle small. An average driver feels uncomfortable when the magnitude of the sideslip angle exceeds a few degrees. State-of-the-art electronic stability control (ESC) systems limit the sideslip angle indirectly. ESC uses a reference yaw rate limited by the actual acceleration to account for the tire saturation. Additionally, the rate of change of sideslip angle is calculated and also limited.Global chassis control delivers significant benefits in normal driving and particularly in emergency situations. The configuration and coordinated interaction of the active systems are the key success factors for enhancing the vehicle performance. International standards like ISO 26262 ensure quality and safety of the overall control system at the highest level.

Vehicle stability functions like ABS, TCS, or ESP were firstly introduced on passenger vehicles. As the specific properties of heavy commercial vehicles lead to a very different behavior, the corresponding functions for commercial vehicles require at least significant modifications or in several cases completely new approaches to achieve the requested functionality.With the stabilizing functions for commercial vehicles described in this chapter, at least a similar improvement of the vehicle safety could be achieved as for passenger cars. Due to the significantly higher inertia of heavy vehicles and the related more severe consequences in accidents, the lawmaker in Europe (and successively also in other parts of the world) decided to mandate the antilock braking (ABS) and the vehicle dynamics control (ESP).This chapter focuses on the specifics of vehicle stability functions for commercial vehicles and their differences to similar functions for passenger vehicles.

Traffic accidents at night time have big economic consequences hence the characterization of accident events is very important. At night, the velocity of processing relevant visual information is low in the human subject and the risk of an accident is increased compared to daytime. For lighting design for night-time traffic, the visual process is not only influenced by the visual targets to be detected but also the observers (i.e., the drivers). For good object detection and recognition performance, a certain minimal luminance level must be provided on the road and its surrounding field by the vehicle’s lighting system. The low luminance on the road during dark hours, the small contrast between the objects and their surroundings and the low conspicuity of the objects in traffic space originate from the limited range of illuminated roadside with current low beam front lighting illumination systems. The improvement of visibility and a substantial reduction of traffic accidents are only possible by an increased usage of optimized high beam. To develop high-quality front lighting systems, advanced light source technologies, adaptive light distributions and so-called “light-based” lighting functions shall be used. The primary aim is the achievement of long visibility distances in all traffic situations.

For many people parking a car is more and more a chore task. Due to aerodynamic requirements, increasing the size of vehicles, the visibility to rear and front end of the vehicle decreases, and in parallel, it is more and more difficult to find a suitable parking space. While in the 1990s Parking Aid Systems were not seen as necessary in the meantime, systems supporting the parking process are either standard in some vehicles or have a high take rate. While Parking Aid Systems of the first generations were mainly informing systems, nowadays, these systems help in finding a suitable parking place and support steering during the parking maneuver, and future systems will be more and more autonomous, finally resulting in systems which find their parking place by themselves – valet parking.

Adaptive cruise control (ACC) has reached a new quality in driver assistance. For the first time, a large part of the driver’s tasks can be assigned to an automatic system and the driver relieved to a substantial degree. Based on cruise control, ACC adjusts the vehicle speed to the surrounding traffic. It accelerates and decelerates automatically when a preceding vehicle is traveling at less than the speed desired by the driver.ACC is a key functional innovation and represents a new system architecture with a high degree of function distribution. The different operating modes and system states are described along with function limits and transition conditions.From the many elements of this overall function, target selection and longitudinal control are addressed in detail because of the special challenges they present. Target selection is based on the actual road curvature being determined by the ESC sensor signals that describe the driving dynamics, of which several options are assessed. Predicting and selecting a suitably shaped corridor is explained using an example. Major sources of error for the individual steps, their severity, and possible countermeasures are described.The prerequisite for vehicle-following-distance control is the selection of a target. An example shows that the basic control principle is simple, but it conflicts with comfort and convoy stability. Details of additional control functions in curve situations and approaches are provided.The driver perspective is addressed in terms of control and display functions and in terms of satisfaction as ascertained by use and acceptance studies, also taking into account an extended driver familiarization phase.

For the high portion of forward collisions within the figure of accidents and related damages, basic counteracting strategies are derived. Accident prevention, reaction assistance, and emergency maneuver are the fundamental strategies for protection and are discussed here. With the given physical and empirical basis for control, strategies of countermeasures in different constellations enable the estimation of safety effect of different strategies and definitions of requirements for sensors and actuators.

Forward collisions represent a significant portion of all severe accidents. This is why appropriate warning and collision avoidance systems are of great importance to increase traffic safety. Different system specifications are subsumed under the so-called FVCX-systems; they differ in their way of affecting the overall system driver–vehicle–environment as forward collision conditioning, forward collision mitigation, forward collision warning, and forward collision avoidance systems. A more specific definition of FVCX-systems is derived by distinguishing them from other related systems such as adaptive cruise control and pedestrian safety systems which can also have an impact on forward collisions. The specifications of the actual systems already on the market can only be understood if the characteristics of machine perception are considered carefully. The progress in the field of machine perception enables the forward collision warning and avoidance systems. There are still limitations of state-of-the-art perception systems compared to attentive human drivers which must be considered when designing FVCX-functions. The state of the art in FVCX-systems is sketched out, highlighting realized examples of FVCX-systems of different car manufacturers. Another focus is on a systematic design process which is recommended for driver assistance systems. The motivation for driver assistance can always be derived from accident research. Already in the early conceptual phase functional safety, legal, ergonomic, and marketing aspects should be taken into consideration. Only if a consistent functional specification is found are further developments including package and architecture aspects justified. Concepts for testing and evaluation should be designed in an early development phase as well.

Unintentional lane departures are the root cause for more than 1/3 of all accidents with severely injured occupants on German roads. Therefore, in recent years, Lane Departure Warning (LDW) and Lane Keeping Assistance (LKA) systems have been introduced on the market, which support the driver in lane keeping. LDW informs the driver by means of tactile, visual, and/or audible feedback if the vehicle is about to leave the lane unintentionally. LKA supports the driver by intervening in lateral vehicle control to help keep to the lane.This chapter provides a clear classification of those lateral guidance assistance systems. General requirements are provided, referring to regulations and standards as ISO 17361, ISO DIS 11270, UN ECE R-79, and Euro NCAP. Key technologies and system components of current implementations are described, e.g., environment sensors, warning algorithms, HMI for driver information, and lateral controllers. Exemplary implementations of four OEMs are described in detail. A system evaluation from customer perspective is given referring to surveys published by ADAC and Auto-Bild. Finally, an outlook is given how to further improve the achieved performance for future systems.

More than 5 % of all accidents involving injury to people take place as the result of a lane change. Therefore, it is sensible to provide the driver with a lane change assistant in order to provide support in this driving maneuver.ISO standard 17387 “Lane Change Decision Aid System” differentiates between three different types of system: the “blind spot warning” which monitors the blind spot on the left and right adjacent to the driver’s own vehicle, the “closing vehicle warning” which monitors the adjacent lanes to the left and right behind the driver’s own vehicle in order to detect vehicles approaching from behind, and the “lane change warning” which combines the functions of “blind spot warning” and “closing vehicle warning.”Almost all major vehicle manufacturers are now offering systems that assist the driver to change lanes. Systems with “blind spot warning” are available from Citroën, Ford, GM, Jaguar, Jeep, Land Rover, Lexus, Mercedes, Nissan/Infiniti, Opel, and Volvo. Systems with “lane change warning” are available from Audi, BMW, Mazda, Porsche, Volvo, and VW. All vehicle manufacturers use an optical indicator in or near to the exterior mirrors in order to show information for the driver. The majority of vehicle manufacturers use RADAR sensors that are installed in the rear of the vehicle. Two-level, escalating driver information is only offered in some of the systems. The type of escalation (optical, acoustic, tactile, lateral guidance intervention) usually differs from one vehicle manufacturer to another.The performance capability of the lane change assistants described above is already quite considerable. However, all of these systems have their limits, and the vehicle manufacturers need to inform drivers of these in the owner’s manual, for example.

Junctions and intersections are relatively complex areas in today’s vehicle traffic. Due to this complexity, many traffic accidents occur between vehicles interacting in these areas. Each driver needs to assess parameters such as intersection geometry, right-of-way regulation, and the behavior of third-party vehicles, and a driver fault in any of these tasks can consequently lead to a collision. Thus, an intersection assistance system needs to consider different types of potential driver mistakes in these complex scenarios. This makes the avoidance of intersection collisions particularly challenging.This chapter summarizes major challenges for assistance systems that address the most relevant accident types in intersections, and it introduces different approaches to solve the resulting issues. These approaches vary from intersection-based driver information to cooperative active safety systems using communication technology and/or data from onboard sensors such as RADAR, camera, or LIDAR. Furthermore, the importance of the capabilities of different sensors as well as communication technology for onboard intersection assistance systems is discussed.The early recognition of driver mistakes and the design of a suitable intervention strategy require detailed analyses of common driver behavior in intersections. The results of respective driver behavior analysis are introduced. Different example prototype systems are described in detail, including criticality assessment and warning/intervention strategies. Validation tests with real test persons for some of the discussed systems prove that a positive driver acceptance for intersection assistance systems is feasible.To maximize the overall benefit of intersection assistants during the period of marked introduction, when fleet penetration rates are low, the possibilities and limitations of assistance for collision avoidance in the prioritized vehicle are discussed.

Traffic jams are situations where a high degree of automation could give a large benefit to customers. In addition, the relatively simple situation of a traffic jam means that a high degree of automation can be expected in the near future. This chapter explores in detail the motivation, the conditions, and the versions of assistance and automation systems designed to assist in traffic jams. Different levels of automation for traffic-jam assistance and automation systems will be discussed, such as the design of traffic-jam assistance systems and of automated following systems. Moreover, HMI concepts of state-of-the-art systems are presented, and their implications on controllability and take-over scenarios are discussed. Finally, the legal situation and therefore marketability aspects are regarded.

The chapter path guidance assistance for commercial vehicles looks at the differences between commercial vehicles and cars and highlights the specific requirements and solutions for commercial vehicles. The requirements concern both the driver and the technology. The requirements for commercial vehicles are considerably stronger than for cars. High mileages that significantly exceed 100,000 km per year and correspondingly high annual operating hours as well as heavy duty operation are the reason for this. The operating hours are recorded using tachographs which log the driver’s time at the wheel and rest periods to provide unbroken monitoring. Assistance and safety systems for commercial vehicles are also prescribed in addition to this device. The necessity of these systems is highlighted with the aid of accident scenarios. The chapter discusses lane departure warning (LDW) systems, automatic cruise control (ACC), and the advanced emergency braking system (AEBS). In addition to reliability and safety, fuel consumption is a key criterion for operating commercial vehicles. Consequently, efficient, anticipatory driving strategies have been developed whose function is explained in this chapter. The outlook highlights further developments, such as lane change assist systems, turning assist systems, and platooning.

Agricultural vehicles are complex machines which are used in a wide range of applications. To improve system performance and support operators a number of driver assistance systems have been developed and introduced in the recent past. This article describes a selection of driver assistance systems for agricultural tractors. The main focus is on handling assistance systems, process assistance systems, and automated steering systems which are state of the art in the agricultural industry today. The article closes with an outlook on highly automated vehicles, which is one focus area right now in the industry to further automate working processes.

This chapter provides an overview of vehicle navigation and traffic telematics. A brief history of navigation is followed by an introduction to the various technologies involved. Several aspects are considered, like position fixing and route calculation algorithms. On-board, off-board and hybrid navigation systems are compared with one another, and the interaction between navigation functions and traffic telematics is explained. The authors explore in particular the potential of these technologies in the development of future advanced driver assistance functions. In this context, they provide an overview of the radio broadcasting and mobile communications technologies available for supplying the vehicle with telematics data.

The automotive industry is facing the next major evolutionary step. New functions for highly automated driving are entering the vehicles. This is accompanied by increased E/E and mechatronic contents, leading to increased topological complexity. At the same time the system/component and development costs should remain stable, and product quality should be further improved.A promising strategy to master the complexity of the E/E architecture is the clustering of already intensively networked functional elements either by physical integration or by functional integration into a handful of functional domains. One of these functional domains is the motion domain, which is needed to execute the driving strategy. In recent times there has been a trend toward automation of selected elements of the driving strategy, like driving with a predefined speed or distance in a specific lane.The main purpose of motion control is to execute the driving strategy by generating and managing the forces at the wheels. Motion control structures and coordinates the access to the actuators. The command flow is hierarchically organized in a three-layer sequence. The standardization of the interfaces of each layer is an important task, which finally has to lead to an extension of the AUTOSAR application interface catalog. A new and challenging requirement for motion control is to provide a tracking control capability to follow a predefined trajectory autonomously.For a custom-specific realization of motion control, powerful and flexible integration platforms equipped with multi-core microcontrollers are available. The new architecture is highly scalable and fulfills all requirements from ISO26262 ASIL D. The design is fail operational due to additional on-chip diagnosis (1oo2D), i.e., in case of a permanent failure in one channel, a limp-home mode is entered. The AUTOSAR compliant software can be configured to satisfy different customer needs and requirements, e.g., most flexible hardware resource usage or maximum independency between OEM and supplier software (virtual ECU).

New active driver assistance systems that work at the road and navigation level as well as automated driving face a challenging task. They have to permanently calculate the vehicle input commands (such as those for the steering, brakes, and the engine/powertrain) in order to realize a desired future vehicle movement, a driving trajectory. This trajectory has to be optimal in terms of some optimization criterion (in general a trade-off between comfort, safety, energy effort, and traveling time), needs to take the vehicular dynamics into account, and must incorporate lane boundaries or the predicted free space amid (possibly moving) obstacles. This kind of optimization can be mathematically formulated as a so-called optimal control problem. In order to limit the calculation effort, the optimal control problem is usually solved only on a limited prediction interval (starting with the current time) leading to a receding horizon optimization.The chapter illustrates this practically proven approach in detail. Furthermore, the three general principles of dynamic optimization known from control theory and robotics are presented, namely, calculus of variations, direct optimization, and dynamic programming. Furthermore, their application to driver assistance systems and automated driving is exemplified and the high practical relevance supported by the given literature. Finally, the respective advantages and limitations of the optimization principles are discussed in detail proposing their combination for more involved system designs.

This contribution describes the basic concept and practical evaluation of a driver assistance system, which early detects dangerous overtaking maneuvers on two-lane rural roads and helps to prevent accidents. A fusion of video and RADAR data combines a high-precision detection of far objects with accurate lateral position and velocity estimates for nearer objects. The detection of nearer objects is performed by a video based vehicle classifier. The fused environment data is the basis to identify a hazardous situation by combining a signal based detection of the driver’s overtaking intention with a problematic constellation of the involved vehicles. When such a hazardous situation is detected, warnings are initiated, and an automatic brake intervention aborts the dangerous overtaking maneuver at the last possible moment, so that the driver can get behind the preceding vehicle by swerving to his/her own lane. The system was developed during the Proreta 2 research project by Technische Universität Darmstadt in cooperation with Continental AG.

Instead of a multitude of single assistance functions, the PRORETA 3 concept presents just two functional assistance modes: Firstly, the so-called Safety Corridor in the case, that the vehicle guidance is carried out by the human driver and secondly, Cooperative Automation, offering partial automation of driving in cooperation with the driver. In the Safety Corridor mode, the system has to permanently monitor driving situations and assess concerned potential hazards. As a result, the driver will be informed in the first instance, then in the next stage, a warning is given, and in the last instance, an autonomous collision avoidance trajectory is generated.Cooperative Automation is a concept of shared vehicle guidance. The execution of driving is automated; the driver interacts and supervises the execution, close to the concept of Conduct-by-Wire.The functional architecture of PRORETA 3 integrates concepts for human guidance as well as for (full) automation. A multimodal Human–Machine Interface provides information, warnings, and action recommendations, if necessary, in order to make the PRORETA 3 Safety Corridor clear and understandable. A maneuver interface makes it possible to delegate maneuvers in the Cooperative Automation Mode to the PRORETA system. The traffic environment is represented by a Parametric Free Space (PFS) map. The Trajectory Planning uses a predictive control model applied on a risk potential field.The research vehicle was demonstrated and tested on a test track in Griesheim, Germany. The system acceptance and driving experience were evaluated by questionnaires. The overall assessment of the Safety Corridor, the Cooperative Automation, and the entire system reflects a high acceptance of the PRORETA3 assistance concept.

The technological feasibility of more and more assistant systems and automation in vehicles leads to the necessity of a better integration and cooperation with the driver and with other traffic participants. This chapter describes an integrated cooperative guidance of vehicles including assisted, partially automated, and highly automated modes. Starting with the basic concepts and philosophy, the design space, parallel and serial aspects, the connections between abilities, authority, autonomy, control, and responsibility, vertical versus horizontal and centralized versus decentralized cooperation are discussed, before two follow-on chapters of H-Mode and Conduct-by-Wire describe instantiations of cooperative guidance and control.

In this article, the development of the maneuver-based vehicle guidance concept Conduct-by-Wire is described. After a brief introduction, the function allocation between driver and vehicle is presented in detail. A promising approach is the separation of decision making and execution. Therefore, while driving with Conduct-by-Wire, the driver passes maneuver commands to the vehicle which are then translated into driving functions. In this article, the development and verification of both, maneuvers and driving functions, are described. The article closes with the development and evaluation of an interaction concept for maneuver inputs and an outlook on future work.

With increasing technical possibilities in the area of assistance and automation, diverse challenges, risks, and chances arise in the design of assisted, partially and fully automated driving. One of the greatest challenges consists of integrating and offering a multitude of complex technical functions in such a way that the human driver intuitively understands them as a cohesive, cooperative system. A solution to this problem can be found in the H-Mode. It is inspired by the role model of horse and rider and offers an integrated haptic-multimodal user interface for all kinds of movement control. The H-Mode, as presented in this chapter, has been designed for ground vehicles and includes several comfort and security systems on three assistance and automation levels, which can be interchanged fluidly.

In this chapter, a survey of the current state of research on autonomous driving is given and is set in the context of the requirements of an autonomous vehicle following the vision of an automated taxi. The overview is based on (scientific) publications and self-reports of the developing teams. Aspects of interest for this summary are approaches on environmental perception, self-perception, mission accomplishment, localization, cooperation, map usage, and functional safety.Typically, emphasis is given to reliance on global satellite systems (e.g., GPS) and map data. Only a few approaches focus on environmental perception and scene understanding. Even though impressive demonstrations of autonomous driving have been presented in recent decades, this overview concludes that many aspects still remain only partially solved or even unsolved, especially when driving autonomously in public road traffic.

Gazing into the future of driver assistance systems means looking for stimuli for future developments and identifying specific challenges and effects DAS may be exposed to. One specific “problem area” is the validation of autonomous driving. Statistical considerations show how very difficult it will be to obtain proof of safety on a level comparable to human drivers and that a metric is needed to be able to certify autonomous driving in future. The evolution to autonomous driving is shown as a triangle with three different starting bases. The priorities for future research are given in the last section.