ADAS

Validation and certification enabling the operation of automated vehicles may perhaps be the biggest challenge for the developers of such systems. While there is a consensus about the outstanding problem and the related questions, there is, unfortunately, no widely accepted and feasible solution to this problem. The classical automotive testing and validation approaches for certifying automated vehicles would require several millions of km of on-road testing time and are unfeasible. Simulation techniques can potentially be utilized for this purpose, but the fidelity and modelling accuracy requirements are unknown. This issue is addressed by the two recent sister projects, 'testEPS' and 'Central System', co-funded via the EUREKA network and the Austrian and Hungarian Ministry of Transportation. The current paper aims to introduce both projects together with their respective goals, implementation plans and expected outcomes. They originate from an exploratory phase with initial cross-project cooperation. Due to the joint genesis and unique structure cross-projects synergies effects are expected to be realised to support future verification and validation of ADAS/AD systems, including standardization.

Snelheid en overdreven snelheid worden algemeen beschouwd als belangrijke oorzaken van verkeersongevallen. Snelheidsassisterende systemen geplaatst in het voertuig kunnen bijdragen om de veiligheid en de leefbaarheid op de weg te verhogen. Verschillende studies hebben aangetoond dat ISA een gunstig effect heeft op de verkeersleefbaarheid. Tot vandaag is implementatie uitgebleven. Een van de meest aangegeven reden is dat er geen draagvlak zou zijn bij de bestuurders. Deze bijdrage richt zich op de acceptatie van ISA bij autobestuurders. In Vlaanderen en Nederland werd einde 2009 een grootschalige survey gehouden waarbij 6370 personen reageerden in Belgie en 1158 in Nederland. De respondenten gaven aan dat hun eigen rijgedrag van grote invloed kan zijn op ongevallen en verkeersveiligheid en dat ondersteuning in hun rijgedrag door technologie niet wordt afgewezen. Bijna 95% van de respondenten is voorstander van ISA: zeven op tien chauffeurs wil een informatief of waarschuwend systeem....

The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a la...

Globally, pedestrians represent 23% of all road deaths. Many solutions to protect pedestrians are proposed; in this paper, we focus on technical solutions of the ADAS–Advanced Driver Assistance Systems–type. Concerning the interaction between drivers and pedestrians, we want to have a closer look at two aspects: how to protect pedestrians with the help of vehicle technology, and how pedestrians–but also car drivers–perceive and accept such technology. The aim of the present study was to analyze and describe the experiences, needs, and preferences of pedestrians–and drivers–in connection with ADAS, or in other words, how ADAS should work in such a way that it would protect pedestrians and make walking more relaxed. Moreover, we interviewed experts in the field in order to check if, in the near future, the needs and preferences of pedestrians and drivers can be met by new generations of ADAS. A combination of different methods, specifically, an original questionnaire, on-the-spot inte...

Antenna module is a vital component of automated driving systems, it should function as needed in dGPS, HD map correction services, and radio and navigation systems. The proposed antenna model for GPS only patch antenna operating at 1.57542 GHz and the GNSS patch antenna resonating at 1.5925 GHz are developed. This work presents the design, modelling, determining passive gain of the GPS patch vs. GNSS antenna with intended targeted applications within the automotive system. Simulation are undertaken to evaluate the performance of the proposed GNSS antenna. Simulation conducted in FEKO software rather than mathematical modelling. The two antennas are also compared from the size standpoint. The goal of this paper is to test, measure and evaluate the performance of GPS against GNSS antennas. Another emphasis of this paper is how to obtain the equivalent amount of total passive gain in a GPS vs. that of GNSS antenna.

This paper describes a novel Driver Assistant System based on real-time video to track lanes and road signs with minimal hardware and software requirements. The proposed system was designed to use low cost cameras and processing power of an on-board commodity laptop. The system model was developed using MATLAB®/Simulink blocksets. This was later converted into an optimized compiled code using the built-in code generation features for the Pentium and AMD processors. The lane tracking algorithm based on Hough Transform was implemented as embedded MATLAB® code. The signboards were detected by Blob Analysis Based Template Matching. Sum of Absolute Differences (SAD) as well as Scale Invariant Feature Transform (SIFT) followed by RANdom SAmple Consensus (RANSAC) based template matching methods. The above were implemented and compared for their performance. The developed system was tested on different drives varying from a high speed drive on a high way to a low speed drive on the city roa...

T his paper presents a HiL test bench specifically designed for closed-loop testing of the monocular-vision based ADAS sensors, whereby the animated pictures of the virtual scene is calibrated and projected onto a 120-degree circular screen, such that the camera sensor installed has the same vision as the observation of the real-world scene. A high-fidelity AEBs model is established and deployed in the real-time target of the HiL system, making intervention decisions based on the instance-level detection information transmitted from the physical sensor. By referring to the 2018 edition of the C-NCAP testing protocol, the HiL tests of the rear-end collision scenarios is performed to investigate the performance and characteristics of the longitudinal-motion sensing of the sensor sample under test. By comparing and analyzing the differences between the measured data and the ground truth, the sensor's visual-perceptual capabilities with respect to accuracy and delays are evaluated in the presence of emergency braking of the subject and the leading vehicles. Finally, the matching and optimization solution is offered for performance enhancement of the camera-only AEBs using this monocular vision sensor.

Globally, pedestrians represent 23% of all road deaths. Many solutions to protect pedestrians are proposed; in this paper, we focus on technical solutions of the ADAS–Advanced Driver Assistance Systems–type. Concerning the interaction between drivers and pedestrians, we want to have a closer look at two aspects: how to protect pedestrians with the help of vehicle technology, and how pedestrians–but also car drivers–perceive and accept such technology. The aim of the present study was to analyze and describe the experiences, needs, and preferences of pedestrians–and drivers–in connection with ADAS, or in other words, how ADAS should work in such a way that it would protect pedestrians and make walking more relaxed. Moreover, we interviewed experts in the field in order to check if, in the near future, the needs and preferences of pedestrians and drivers can be met by new generations of ADAS. A combination of different methods, specifically, an original questionnaire, on-the-spot inte...

Development of Advanced Driver Assistance (ADAS) Systems and Automated Driving (AD) technologies require extensive calibration, testing and validation before such systems can be rolled out into the production line. It is in the interest of the OEMs to speed up these development cycles to ensure compliance with the expected performance requirements. In this paper, a novel steerable chassis dynamometer test bench with a corresponding methodology is introduced to develop and test ADAS/AD technologies. A use case example of tuning the camera-based implementations of the lane keeping assistant (LKA) and adaptive cruise control (ACC) functions on an AD demonstrator vehicle utilizing this test bench is described with preliminary performance results.

Current full-and semi-Autonomous car prototypes increasingly feature complex algorithms for lateral and longitudinal control of the vehicle. Unfortunately, in some cases, they might cause fussy and unwanted effects on the human body, such as motion sickness, ultimately harnessing passengers' comfort, and driving experience. Motion sickness is due to conflict between visual and vestibular inputs, and in the worst case might causes loss of control over one's movements, and reduced ability to anticipate the direction of movement. In this paper, we focus on the five main physical characteristics that affect motion sickness, including them in the function cost, to provide quality passengers' experience to vehicle passengers. We implemented our approach in a state-of-the-art Model Predictive Controller, to be used in a real Autonomous Vehicle. Preliminary tests using the Unreal Engine simulator have already shown that our approach is viable and effective, and we implemented an...

In this paper, an advanced-and-reliable road-lanes detection and tracking solution is proposed and implemented. The proposed solution is well suited for use in Advanced Driving Assistance Systems (ADAS) or Self-Driving Cars (SDC). The main emphasis of the proposed solution is the precision and the predictability in identifying the driving-lane boundaries (linear or curved) and tracking it throughout the drive. Moreover, the solution provides fast enough computation to be embedded in affordable CPUs that are employed by ADAS systems. The proposed solution is mainly a pipeline of reliable computer-vision algorithms that augment each other and take in raw RGB images to produce the required lane boundaries that represent the front driving space for the car. The main contribution of this paper is the precise fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a sophisticated real-time output. Each used algorithm is described in detail, implemented and its performance is evaluated using actual road images and videos captured by the front-mounted camera of the car. The whole pipeline performance is also tested and evaluated on real videos. The evaluation of the proposed solution shows that it reliably detects and tracks road boundaries under various conditions.

In this paper, an advanced-and-reliable vehicle detection-and-tracking technique is proposed and implemented. The Real-Time Vehicle Detection-and-Tracking (RT VDT) technique is well suited for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC). The RT VDT is mainly a pipeline of reliable computer vision and machine learning algorithms that augment each other and take in raw RGB images to produce the required boundary boxes of the vehicles that appear in the front driving space of the car. The main contribution of this paper is the careful fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a precise and sophisticated real-time output. In addition, the RT VDT provides fast enough computation to be embedded in CPUs that are currently employed by ADAS systems. The particulars of the employed algorithms together with their implementation are described in detail. Additionally, these algorithms and their various integration combinations are tested and their performance is evaluated using actual road images, and videos captured by the front-mounted camera of the car as well as on the KITTI benchmark with 87% average precision achieved. The evaluation of the RT VDT shows that it reliably detects and tracks vehicle boundaries under various conditions. 7 8 9 10 11 12 13 14 15 16 17 18

This paper describes a novel Driver Assistant System based on real-time video to track lanes and road signs with minimal hardware and software requirements. The proposed system was designed to use low cost cameras and processing power of an on-board commodity laptop. The system model was developed using MATLAB®/Simulink blocksets. This was later converted into an optimized compiled code using the built-in code generation features for the Pentium and AMD processors. The lane tracking algorithm based on Hough Transform was implemented as embedded MATLAB® code. The signboards were detected by Blob Analysis Based Template Matching. Sum of Absolute Differences (SAD) as well as Scale Invariant Feature Transform (SIFT) followed by RANdom SAmple Consensus (RANSAC) based template matching methods. The above were implemented and compared for their performance. The developed system was tested on different drives varying from a high speed drive on a high way to a low speed drive on the city roads. The system was able to detect the lane markings under various lighting conditions and on many types of roads ranging from unmarked roads to multi-lane national highways. The road sign detection system was able to detect signboards as long as the background was not very cluttered. The implemented system has an overall success rate of over 97% for lane detection and more than 70% for the road sign detection.

Advanced driver assistance systems (ADASs), and particularly pedestrian protection systems (PPSs), have become an active research area aimed at improving traffic safety. The major challenge of PPSs is the development of reliable on-board pedestrian detection systems. Due to the varying appearance of pedestrians (eg, different clothes, changing size, aspect ratio, and dynamic shape) and the unstructured environment, it is very difficult to cope with the demanded robustness of this kind of system.

Advanced Driver Assistance Systems (ADAS) proved a potential to save lives and reduce serious injury in traffic accidents. But if they are not known and accepted by the drivers, they will not deliver the benefits intended by their designers. The aim of the current research was to assess the awareness and acceptance of selected advanced driver assistance systems among a sample of Czech drivers, as well as the factors that might influence it. Together, 526 drivers participated in the questionnaire study. About a half of them was not aware of any further information besides the existence of various ADAS and more than 70 % did not drive with such systems yet. As for the acceptance, most of the systems were desired by at least 50 % of the respondents, but the majority was not willing to pay any extra money for the systems. A perceived safety benefit might increase the acceptance, but in the end, a thorough driver education about the systems' function and limitations is needed.

Advanced Driver Assistance Systems/Autonomous Driving (ADAS/AD) functions require extensive validation and testing before they can be released to the market. During both the functional development and the production phase, ADAS/AD functions need to undergo calibration, as well as robustness, integrity and integration checks. This paper presents a novel method for calibration, functional testing and diagnosis of specific ADAS/AD related failures of camera-based ADAS/AD systems utilizing a vehicle-in-the-loop test simulation setup with real time stimulation of the camera sensor on a novel steerable chassis dynamometer testbed. In this setup, the driving scenario and the functional testing environment is simulated whereas the real vehicle, equipped with SAE level 3 class ADAS functions, is tested with realistic rolling conditions on the testbench. Using this method, various error conditions can be emulated and any potential problems can be diagnosed during testing with or without access to the vehicle's ECUs. The presented setup represents a consistent testing methodology and a corresponding toolchain for this purpose, which can be utilized from functional development phase till the end-of-line testing stage. Furthermore, we propose the idea of a standardized ADAS/AD diagnostic interface, to support diagnosis in time-critical conditions (e.g. end-of-line or workshop use cases) with respect to the expected performance limits. This diagnostic interface is crucial to perform testing in a consistent and reproducible manner and also to re-use and compare results between different testing environments. Kurzfassung Fahrerassistenzsysteme (FAS) und autonome Fahrfunktionen benötigen auf-wändige Validierung und Testing, bevor diese für Produktion und Verkauf freige-geben werden können. Sowohl während der Entwicklungs-als auch Produktions-phase müssen Fahrerassistenzfunktionen hinsichtlich ihrer Robustheit, Integrität und Integration überprüft werden. Dieses Paper präsentiert eine neuartige Me-thode zur Kalibrierung, Funktionsprüfung und Diagnose von Kamera-basierten FAS, welche auf der Verwendung einer vehicle-in-the-loop Simulation mit Over-the-Air Stimulation der Kamera basiert. Die vehicle-in-the-loop Simulation wird dabei auf einem neuartigen lenkbaren Rollenprüfstand implementiert. In diesem

This paper describes a novel Driver Assistant System based on real-time video to track lanes and road signs with minimal hardware and software requirements. The proposed system was designed to use low cost cameras and processing power of an on-board commodity laptop. The system model was developed using MATLAB®/Simulink blocksets. This was later converted into an optimized compiled code using the built-in code generation features for the Pentium and AMD processors. The lane tracking algorithm based on Hough Transform was implemented as embedded MATLAB® code. The signboards were detected by Blob Analysis Based Template Matching. Sum of Absolute Differences (SAD) as well as Scale Invariant Feature Transform (SIFT) followed by RANdom SAmple Consensus (RANSAC) based template matching methods. The above were implemented and compared for their performance. The developed system was tested on different drives varying from a high speed drive on a high way to a low speed drive on the city roa...

ABSTRACT In the paper, a new multi-sensor platform for adaptive driving assistance system is introduced. The platform is composed of multi-radar, multi-camera, combined positioning and navigation equipment, and some information can also be obtained from vehicle CAN bus. With the platform and the technique such as multicast network, the information such as road edges, lane marking, traffic marking, obstacles, other vehicles and pedestrians, position and velocity, acceleration and so on has be obtained during the vehicle is moving. The vehicle's moving state can be control with decision strategy module of ADAS based on the information. The experiments results show that the platform can complete the mission of information perception module of ADAS efficiently and accurately.

In this paper, an advanced-and-reliable vehicle detection-and-tracking technique is proposed and implemented. The Real-Time Vehicle Detection-and-Tracking (RT_VDT) technique is well suited for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC). The RT_VDT is mainly a pipeline of reliable computer vision and machine learning algorithms that augment each other and take in raw RGB images to produce the required boundary boxes of the vehicles that appear in the front driving space of the car. The main contribution of this paper is the careful fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a precise and sophisticated real-time output. In addition, the RT_VDT provides fast enough computation to be embedded in CPUs that are currently employed by ADAS systems. The particulars of the employed algorithms together with their implementation are described in detail. Additionally, these algorithms ...

In this paper, an advanced-and-reliable vehicle detection-and-tracking technique is proposed and implemented. The Real-Time Vehicle Detection-and-Tracking (RT_VDT) technique is well suited for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC). The RT_VDT is mainly a pipeline of reliable computer vision and machine learning algorithms that augment each other and take in raw RGB images to produce the required boundary boxes of the vehicles that appear in the front driving space of the car. The main contribution of this paper is the precise fusion of the employed algorithms where some of them work in parallel to strengthen each other in order to produce a precise and sophisticated real-time output. In addition, the RT_VDT provides fast enough computation to be embedded in CPUs that are currently employed by ADAS systems. Each used algorithm is described in detail, implemented, its performance is evaluated using actual road images, and videos captured by the front-mounted camera of the car. The evaluation of the RT_VDT shows that it reliably detects and tracks vehicle boundaries under various conditions.

In recent times, many innocent people are suffering from sudden death for the sake of unwanted road accidents, which also riveting a lot of financial properties. The researchers have deployed advanced driver assistance systems (ADAS) in which a large number of automated features have been incorporated in the modern vehicles to overcome human mortality as well as financial loss, and lane markings detection is one of them. Many computer vision techniques and intricate image processing approaches have been used for detecting the lane markings by utilizing the handcrafted with highly specialized features. However, the systems have become more challenging due to the computational complexity, overfitting, less accuracy, and incapability to cope up with the intricate environmental conditions. Therefore, this research paper proposed a simple encode-decode deep learning model to detect lane markings under the distinct environmental condition with lower computational complexity. The model is based on SegNet architecture for improving the performance of the existing researches, which is trained by the lane marking dataset containing different complex environment conditions like rain, cloud, low light, curve roads. The model has successfully achieved 96.38% accuracy, 0.0311 false positive, 0.0201 false negative, 0.960 F1 score with a loss of only 1.45%, less overfitting and 428 ms per step that outstripped some of the existing researches. It is expected that this research will bring a significant contribution to the field lane marking detection.

This paper introduces a novel vehicle-in-the-loop testing methodology called “Hybrid Testing”, which enables the evaluation of a real vehicle in a virtual traffic scenario in an enclosed proving ground with simulated traffic components and sensor signals. Among the other benefits, the introduced methodology is particularly suited to test and verify ADAS functions in virtual scenarios, which would otherwise be very difficult to create in real world. Development of ADAS functions require extensive testing and validation prior to deployment and generally, exhaustive real-life scenario evaluation of such systems is not feasible, let alone possible. With Hybrid Testing we can combine the benefits of simulation and real-life testing. We show how this methodology, as was developed in the EU-funded project INFRAMIX, can be used to evaluate ADAS functions on an example of a trajectory planning algorithm to demonstrate its working principles and benefits.

Automated vehicles are expected to cause a paradigm shift in mobility and the way we travel. Particularly, the increasing penetration rates of vehicles with automated driving functions will introduce new challenges such as excessive rutting. Lack of wheel wander and keeping to the lane center perfectly is expected to lead to excessive road surface depression induced by automated vehicle platoons. Inspired by this, the EU project ESRIUM investigates infrastructure assisted routing recommendations. In this respect, specially designed ADAS functions are being developed with capabilities to adapt their behavior according to specific routing recommendations, which will help to reduce rutting as well as to improve safety. The current paper presents three rule-based trajectory planner design alternatives for a representative use case and, their performance comparisons based on a simulation framework.

Traffic accidents due to human errors cause many deaths and injuries around the world. To help in reducing this fatality, in this research, a new module for Advanced Driver Assistance System (ADAS) for automatic driver drowsiness detection based on visual information and Artificial Intelligence is presented. The aim of this system is to locate, to track and to analyze the face and the eyes to compute a drowsiness index, working under varying light conditions and in real time. Examples of different images of drivers taken in a real vehicle are shown to validate the algorithm.

... information and will redirect the data coming from vehicle once again towards them. ... tests showed that the driving agent was able to simulate a human-like driving behaviour ... developing a new generation of infrastructure-based sensing techniques and for testing scenario-based ...

Traffic sign detection and recognition (TSDR) is an essential component of advanced driver assistance systems (ADAS). It is mainly designed to enhance driver safety through the fast acquisition and interpretation of traffic signs. However, such systems still suffer from the inability to accurately recognize signs. Moreover, the sharing of wirelessly recognized signs among vehicles is not yet supported by current systems. In some safety scenarios, vehicle-to-vehicle communication of traffic sign information is required. In this article, we first address challenges and undesirable factors facing TSDR systems. After that, we show how to design a TSDR system by addressing some useful techniques used in each stage of the system. For each stage, these techniques are regrouped into different categories. Then, for each category, a short description is given followed by some concluding remarks. Finally, the transmission of the recognized signs is briefly investigated.

The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a large measurement campaign on a Hungarian highway to support the development and experimental validation of the new approach. The quality of the model was tested and compared to reference measurements, leading to a pointwise position error of 9.60% in the lateral and 1.57% in the longitudinal direction. Additionally, the modeling of the natural scattering of the sensor model output was satisfying. In particular, the deviations of the position measurements were well modeled with this approach.

ABSTRACT Traffic sign detection and recognition (TSDR) is an essential component of advanced driver assistance systems (ADAS). It is mainly designed to enhance driver safety through the fast acquisition and interpretation of traffic signs. However, such systems still suffer from the inability to accurately recognize signs. Moreover, the sharing of wirelessly recognized signs among vehicles is not yet supported by current systems. In some safety scenarios, vehicle-to-vehicle communication of traffic sign information is required. In this article, we first address challenges and undesirable factors facing TSDR systems. After that, we show how to design a TSDR system by addressing some useful techniques used in each stage of the system. For each stage, these techniques are regrouped into different categories. Then, for each category, a short description is given followed by some concluding remarks. Finally, the transmission of the recognized signs is briefly investigated.