Driving Safety through ADAS: An Indian Perspective

<div class="section abstract"><div class="htmlview paragraph">Advanced Driver Assistance Systems (ADAS) is a growing technology in automotive industry, intended to provide safety and comfort to the passengers with the help of variety of sensors like radar, camera, Light Detection and Ranging (LIDAR) etc. The camera sensors in ADAS used extensively for the purpose of object detection and classification which are used in functions like Traffic sign recognitions, Lane detections, Object detections and many more. The development and testing of camera-based sensors involves the greater technologies in automotive industry, especially the validation of camera hardware and software. The testing can be done by various processes and methods like real environment test, model-based testing, Hardware, and Software in loop testing. A fully matured ADAS camera system in the market comes after passing all these verification processes, yet there are lot of new failures popping up in the field with this ADAS system. Since ADAS is an evolving technology, many new field issues keep coming due to huge diversity of features in the real-world infrastructure. So, to bring up a more reliable ADAS system, validating every newly reported issue and including the fix in the software is the only way to bring the safe and reliable system in the Automobiles. If there is any issue reported in certain places, the current practice is to reproduce the issue in the same place, analyzing the issue & finding the solution with fix in the software and finally validating that issue in the same location. This process of reproducing the issue & validating the fix in the same location can become more complex and expensive since that hotspot locations can be found anywhere in the world. This paper proposes a technique for the camera-based testing includes maps-based testing by using real maps scenarios played in front of the camera in controlled simulation environment and evaluate the results to confirm the software maturity. Real world scenarios can be created using open-source maps data and using it after fine tuning in the Hardware in Loop (HiL) system can reduce the complexity and cost of development & validation of ADAS camera Sensors.</div></div>

Perception system plays an important role in Advanced driver assistance systems (ADAS) & Autonomous vehicles (AV) to understand the surrounding environment and further navigation. It is highly challenging to achieve the accurate perception of ego vehicle mimicking human vision. The available ADAS and AV solutions could able to perceive the environment to some extent using multiple sensors like Lidars, Radars and Cameras. National Highway Traffic Safety Administration Crash reports of ADAS and AV systems shows that the complete autonomy is challenging to achieve using the existing sensor suite. Particularly, in extreme weather, low light and night scenarios, there is a need for additional perception sensors. Infrared camera seems to be one of the potential sensors to address such extreme and corner cases. This chapter aimed to discuss the advantage of adding infrared sensors to perceive the environment accurately. The advancements in deep learning approaches further leverages to enhance ADAS features. Also, the limitations of current sensors, the need for infrared sensors and technology, artificial intelligence and current research focus using IR images are discussed in detail. Literature shows that by adding IR sensor to existing sensor suite may lead a way to achieve level 3 and above autonomous driving precisely.

Various Advanced Driver Assistance Systems (ADAS) become prevailing recently. In this paper, we argue the safety analysis of combined ADAS systems. The definition of ADAS is vague, so we obey the definition of Code of Practice for the Design and Evaluation of ADAS (CoP) (1). In this definition, the ADAS have to be active, that is, it “provide(s) active support for lateral and/or longitudinal control”. There is a technical report that provides the consolidation way of various warnings emitted by the several ADAS systems (ISO/TR 12204 (2)). However, the problem is not limited to the warning signals. We have to consider the controller of ADAS because it is actively controlled from its definition. We need the more integrated way, and we provide a way to handle this situation by using the idea: DESH-G model.

Analysis of advanced driver assistance systems in police vehicles: A survey study

In recent years, the automotive industry has shown increased interest in Advanced Driver Assistance Systems (ADAS), especially those based on bio-signals. Recent advances in RGB-D technologies have provided effective solutions for tracking human activity based on depth data. In this paper is presented an ADAS system based on Kinect RGB-D camera for the identification of the driver’s distraction. Using depth and colour information the proposed ADAS system is be able to identify the driver’s head orientation and eye position. Based on this data, the driver’s inattention is detected and the driver is warned by audio signals. The proposed ADAS system was evaluated using a Virtual Reality driver simulator for manual and visual distraction. The results show accurate recognition of driver’s distraction.

The study aims to improve the safety of the ADAS (Advanced Driver Assistance System) system under the challenging scenarios of single vehicle perception long tail or complex extreme driving conditions. In multiple vehicles following driving scenarios, when the remote target vehicle is blocked by the nearby target vehicle, the single-vehicle intelligence will be limited by its perception range and FOV (Field of View) and cannot respond in time, probably leading to collision accident or emergency braking thereby reducing the riding comfort. To solve these issues, we developed a V2X (Vehicle to Everything)-based ADAS system and designed a decision-making algorithm considering the interaction risk between multiple target vehicles by V2V (Vehicle to Vehicle) communication. Simulation and vehicle tests showed that compared with traditional single-vehicle intelligence schemes, the V2X-based ADAS system and the decision-making algorithm could provide about 1.75 s earlier time for braking, significantly improving driving safety. Reducing the braking force by about 30% can significantly improve ride comfort at the same time. This study can effectively improve vehicle driving safety under extreme conditions, which has theoretical value for the V2X application in mass-production vehicles.

Most of chassis systems and Advanced Driver Assistance Systems (ADAS) are developed independently. Car manufacturers have even separate departments to develop the two types of systems. Even though each system category is developed for a different objective, from a global vehicle motion control perspective, these systems may influence the same physical variable. If, from the design process, no supervisory strategy is ensured for both categories, the different systems may interact and generate unwanted behaviors. These interactions can be very unpredictable and may impact the global vehicle safety. Moreover, future automated vehicles will require additional innovative systems. This will make the vehicle over-actuated. The global vehicle motion control should take into account this aspect. New requirements for the longitudinal, transverse, and vertical dynamics should be addressed. Car manufacturers tend to develop tuned rule-based strategies for a specific set of integrated systems by studying different use-cases. On one hand, we cannot foresee all the possible conflicted scenarios. On the other hand, the more numerous the systems get, the more unpredictable the interactions become. The definition of use-cases will become harder or even non-scalable. Our research aims to develop an integrated control architecture where ADAS and chassis systems are optimally coordinated. This our work is based on rather a mathematical formalization of system interactions. This enables developing a multi-layered modular control architecture that starts with a high-level robust control to specify the motion of the car, and then distribute the control on the different implemented systems upstream the low-level controllers using an optimization-based control allocation strategy. This latter strategy is made flexible and extensible so if a new system should be implemented within the same car, the control designer does not have to redesign the overall architecture of the motion control. This remains valid for both ADAS and chassis systems control, and for both trajectory and speed control. To test this, we developed high fidelity vehicle models for different vehicles in Simcenter Amesim, and we implemented the overall control architecture in Matlab, then both softwares can be co-simulated. Through several scenarios, co-simulation results showed that the vehicle performance is improved when activating several systems at the same time with an optimal coordination. More severe situations can be handled at high velocities. In addition, the different systems can be made complementary so if one system fails, another completely different system can takeover the maneuver. The global vehicle is then safer without any redundancy of the advanced expensive systems.

Automated vehicles and Advanced Driver Assistance Systems (ADAS) face a variety of complex situations that are dealt with numerous sensors for the perception of the local driving area. Going forward, we see an increasing use of multiple, different sensors inputs with radar, camera and inertial measurement the most common sensor types. Each system has its own purpose and either displays information or performs an activity without consideration for any other ADAS systems, which does not make the best use of the systems. This paper presents an embedded real-time system to combine the attributes of obstacles, roadway and ego-vehicle features in order to build a collaborative local map. This embedded architecture is called PerSEE: a library of vision-based state-of-the-art algorithms was implemented and distributed in processors of a main fusion electronic board and on smart-cameras board. The embedded hardware architecture of the full PerSEE platform is detailed, with block diagrams to illustrate the partition of the algorithm on the different processors and electronic boards. The communications interfaces as well as the development environment are described.

Assisted driving is currently considered a key aspect for improving road safety, and automakers and OEMs are working to achieve higher levels of vehicle automation by introducing new technologies and Advanced Driver Assistance Systems (ADAS) in the circulating fleet. This trend requires test protocols for vehicle safety assessment to be frequently reviewed and updated, considering the latest advances in the state of the art regarding ADAS functions and systems. As of today, performance assessment programs (such as NCAP) mainly evaluate how an ADAS behaves in terms of crash avoidance in specific critical scenarios, which represent the most frequent crash constellations among real-world impacts. However, enhanced safety can be also obtained in case the impact is not avoided if a decrease in Injury Risk (IR) for the involved road users is achieved by ADAS intervention, compared to the case of no intervention.The purpose of this work is to propose an overall framework to draft or update test protocols for ADAS performance assessment based on real car-to-car impact observations, representative of impact scenarios in terms of both occurrence frequency and IR. First, the in-depth accident database IGLAD is analyzed to identify the most relevant car-to-car accident scenarios based on a relevance indicator, i.e., the risk level being the multiplication of the occurrence frequency and IR for a specific scenario. For each relevant scenario, a risk level-based strategy to identify one significant closing speed between vehicles for the tests is defined; the test collision speed for the two vehicles is determined analogously, and the risk level for each combination of speeds in a scenario represents the maximum achievable score by the ADAS if the collision is averted. Considering the well-established Euro NCAP framework as a relevant starting point for the definition of test protocols, two examples are highlighted regarding the proposal of a new test protocol and an update of an already existing one. Finally, a method is proposed for ADAS performance assessment if the impact is not avoided, scaling the maximum achievable score based on the IR reduction consequent to the ADAS intervention.

In-vehicle electronics is the fastest growing area of auto technology. A large part of this growth is in the area of Advanced Driver Assistance Systems (ADAS), which have become a very important part of the modern automobile. These ADAS systems usually run multiple applications simultaneously (e.g., Lane Departure Warning, Traffic Sign Detection, Pedestrian Detection, etc.). Each of these applications consists of multiple tasks and has hard real-time constrains that need to be satisfied. Finding new ways to reduce the cost, size, weight, complexity, and power consumption of the hardware used in these systems, while being able to offer more and more configurable features has always been a challenging problem for automotive suppliers and OEMs. The solution can be found in heterogeneous multicore embedded System on Chip (SoC), but the transition toward multi-core architectures has created more challenges at the software side, where fast deployment, integration and verification of the software is required. In addition to that, the temporal behavior of such safety critical applications must be predicted, with minimal processor reservation and memory usage. In this paper we will present a workflow to easily deploy and schedule multiple vision based ADAS applications on heterogeneous multi-core platform. This will be accomplished by employing Single Rate Data Flow (SRDF) graph as a base model of computation combined with hierarchical scheduling strategy that provides functional isolation and predictable timing between these applications. The results of this work could be used towards the design and implementation of partitioned, real-time operating systems that execute on heterogeneous multicore system on chip environment and a tool-chain to auto-generate such a system.

Comprehensive situational awareness is paramount to the effectiveness of advanced driver assistance systems (ADASs) used in daily urban traffic, particularly for the unmarked roads, which cannot fulfill the requirements of conventional ADAS systems. This paper proposed a stereovision-based multimodal ADAS system designed for expanding the usability of ADAS functions, including lane-keeping assist, adaptive cruise control, and precrash system, to normal urban scenarios with unmarked roads. At first, the physical road boundary and vehicle candidates are detected. Subsequently, the contextual information between the host vehicle, the road, and the other vehicles are correlated for both low-level object detection improvement and high-level road structure estimation. Finally, the required ADAS elements are generated based on the correlation results with respect to the system functionalities. Experimental results in various typical but challenging scenarios have substantiated the effectiveness of the proposed system, which could help increase the value of the existing ADAS system without major modifications or expense.

Modern cars use advanced electronic systems that help the driver with the driving process - so-called Advanced Driver-Assistance Systems (ADAS). ADAS systems are used to automate, customize and improve systems within a vehicle for greater safety and better driving experience. Since ADAS systems as such can have a significant impact on the driving process, the vehicle and the driver, they must be thoroughly tested and developed within many industry standards. The key factor in their work is communication between individual system components. This standardized communication is necessary to test, which is usually performed by developing AUTomotive Open System Architecture (AUTOSAR) communication tests. Since ADAS testing can be quite a complex and time-consuming process, automated testing is performed in an appropriate testing environment. In this paper, existing ADAS environment testing systems is presented, which generates a test environment for the simulation of communication in the middle layer (Middleware) of AUTOSAR architecture. Test Environment Generator (TEG) is a Python program for processing ARXML test files based on which it generates a test environment model in the form of separate components in the C programming language. The program consists of input data parsing, parsed data storing and components generation that build the test environment. Based on the detected disadvantages of the existing TEG, several modifications are proposed in order to accelerate its execution time and to introduce more robust and stable data storage methods in database form.

Immerse yourself in the evolving world of automotive technology with ADAS and Automated Driving - Systems Engineering. Explore advanced driver assistance systems (ADAS) and automated driving, revealing the automotive industry’s technological revolution. As technology becomes a driving force, this book serves as a guide to understanding cutting-edge technologies deployed by leading vehicle manufacturers. Discover how multiple systems synergize to provide ADAS and automated driving functions. Authored by an industry expert, this book explores systems engineering’s crucial role in designing, safety-critical cyber-physical systems. Gain practical insights into the processes and methods adapted for the current technological era of software-defined vehicles, influenced by AI, digitalization, and rapid technological advances. Whether you're a seasoned engineer navigating the shift to software-defined vehicles or a student eager to grasp systems engineering methods, this book is your key to unlocking the skills demanded in the exciting era of digitalization. Immerse yourself in real-world examples drawn from industry experiences, bridging the gap between theory and practical application. Gain the knowledge and expertise needed to embark on projects involving the intricate world of cyber-physical systems with ADAS and Automated Driving - Systems Engineering. “As this book demonstrates, systems engineering is needed more than ever to navigate the complexities of the type of projects where alternative delivery models are applied and to help ensure effective delivery even within the constraints of aggressive and adaptable schedules.” Dr David Ward Global Head of Vehicle Resilience—Functional Safety HORIBA MIRA Limited “This book holistically explains the lifecycle and the processes for ADAS and autonomous systems and their influence on the overall vehicle over its complete lifecycle.” Matthias Schulze Vice President, ADAS Product, ecarx

Existing automotive Hazard Analysis and Risk Assessment (HARA) process as discussed by the international standard ISO 26262 is static in nature. While the standard describes a systematic process to incorporate functional safety in the development process of Electrical & Electronic (E/E) systems, it fails to address the needs of Advanced Driver Assistance Systems (ADAS) and Automated Driving (AD) systems. In order to ensure the safety of ADAS and AD systems, it is important to incorporate the changing nature of interactions between the system and the environment, in the safety analysis process for ADAS and AD systems. In this paper, the authors argue the need for a dynamic approach for automotive safety analysis by adapting the tactical safety for ADAS and AD systems depending on the real-time operational capability and real-time ASIL (Automotive Safety Integrity Level) rating of a situation, and discuss a framework for this process. The novelty and therefore contribution of this paper lies in the proposed ASIL inspired dynamic tactical safety framework, which evaluates the severity, controllability and exposure ratings in real-time based on the real time values of the various vehicle and environment parameters. These ratings are used to assign a real-time ASIL value which is used to determine the tactical decisions in order to lower the ASIL value in real-time by altering the functional (operational) capability of the system. Furthermore, the framework is explained with the help of a case study based on a combined Adaptive Cruise Control (ACC) and Autonomous Emergency Braking (AEB) system.

A large number of researches show that various driver distractions considerably increase the probability of causing an accident. Advanced Driver Assistance Systems (ADAS) can be used to prevent dangerous driving conditions by monitoring the environment and warn the user in situations like collision, lane departure or speed infractions. In most cases of using the ADAS systems, the driver is warned by visual indicators or audio signals. This paper investigates the design of a device that can be integrated in the driver’s seat which allows the issue of dynamic vibrotactile warnings received from a smartphone based ADAS system.