Advanced Microsystems for Automotive Applications 2018

The AWARE (All Weather All Roads Enhanced vision) French public funded project is aiming at the development of a low cost sensor fitting to automotive and aviation requirements, and enabling a vision in all poor visibility conditions, such as night, fog, rain and snow.

In order to identify the technologies providing the best all-weather vision, we evaluated the relevance of four different spectral bands: Visible RGB, Near-Infrared (NIR), Short-Wave Infrared (SWIR) and Long-Wave Infrared (LWIR). Two test campaigns have been realized in outdoor natural conditions and in artificial fog tunnel, with four cameras recording simultaneously.

This paper presents the detailed results of this comparative study, focusing on pedestrians, vehicles, traffic signs and lanes detection.

Smart mobile devices can be easily transformed into driving assistance tools or traffic monitoring systems. These devices are placed behind the windshield such that the camera is facing forward to observe the traffic. For the visual information to be useful, the camera must be calibrated, and a proper calibration is laborious and difficult to perform for the average user. In this paper, we propose a calibration technique that requires no input from the user and is able to estimate the extrinsic parameters of the camera: yaw, pitch and roll angles and the height of the camera above the road. The calibration algorithm is based on detecting vehicles using CNN based classifiers, and using statistics about their size and position in the image to estimate the extrinsic parameters via Extended Kalman filters.

In the near future Automated Vehicles (AVs) will be part of the vehicular traffic on the roads. Normally, all automation levels will be granted on the road based on the different road situations, but challenging situations will still exist that AVs will not be able to handle safely and efficiently. AVs driving at a high automation level may step down to the lower automation level and handover the partial/full control to the driver when the automation system reaches its functional system limits or encounters unexpected situations. This paper briefly explains the H2020 TransAID project covering the transition phases between different levels of automation. It will review related work and introduce the concept to investigate automation level changes. Furthermore, the collective sensor data processing architecture using for demonstrators and the selected use cases are presented.

With the continuous development and improvement of advanced driver assistance systems up to highly automated driving functions, the driving task is changing. There is no need for the driver to permanently supervise automatic driving functions of SAE J3016 level 3 and 4. The driver is allowed to engage in non-driving related tasks temporarily. However, if the automated vehicle reaches its limitations, the driver needs to react appropriately to a take-over request. Driver state monitoring systems might enable adaptive take-over concepts to support the driver in such situations. In order to recognize the currently performed non-driving related task by a technical system it is necessary to fuse different features from several measurement signals to infer the currently executed task of the driver. Main features of non-driving related tasks include the driver’s visual orientation and position of his or her hands. In this paper, a methodology is presented to detect a non-driving related task using Hidden Markov Models to represent the temporal relationships of characteristic features. Measurement data was obtained from participants in a driving simulator and used to train and evaluate the presented system with various non-driving related tasks.

Autonomous Driving at level 5 requires high-performance vehicle computers (HPVC) to perform the multitude of complex functions, such as comprehensive vision processing, object recognition, intelligent traffic system, and task dispatch between different ECUs in the car. Today, HPVC systems are available as development platforms but not ready to be deployed under harsh operating conditions of real vehicles yet. The paper assesses the requirements, discusses the current state of the art, and introduces architectural and design solutions for a robust and safe automotive grade HPVC platform. The required high computational power and all the necessary communication interfaces will be provided at costs allowing the production of passenger cars for the broad public.

Road Vehicle Automation will revolutionise transport. Such revolution will effectively start when new transport services with significant added value with respect to today’s ones can be deployed.

This paper presents two transport services, one based on private vehicle ownership and one on public and share transport vehicles, which will become the first available disruptive “new modes of transport”.

Such modes will have different impacts on the society and the economy and depending on the favored one they will have long term influence on our society.

A political intervention is needed to evaluate the effects of this revolution beforehand and to shape policies to guide the future to avoid automation to backfire.

The introduction of automated vehicles to the market raises various questions and problems. One of those problems is the trustworthiness of the automated systems and in this connection the user’s perception and acceptance. The user’s perception is especially important during SAE level 3 automated driving (L3AD), where the driver has to be able to resume vehicle control, and during the initial deployment of automated systems, where mixed traffic situations occur, in which automated and human-driven vehicles share the same road space. The Horizon 2020 project TrustVehicle aims at investigating critical scenarios, especially in mixed traffic situations and under harsh weather conditions, and at improving the trustworthiness and availability of L3AD functionalities through a user-centric approach.

Connected vehicles are an essential part of Intelligent Transport Systems (ITS). A number of communication technologies exist that can complement each other or serve as an alternative. Keeping that in mind, to get the most benefit for a connected vehicle, a hybrid communication paradigm where multiple communication technologies are used in parallel is considered as the natural way forward.

To achieve this in practice, it is important to design vehicular communication architectures to be flexible but also reliable. Building upon an established theory of adaptation layer based architecture in literature, this paper discusses the specifics of a practical implementation of such architecture. This practical environment is provided within the European research project ADAS&ME.

The paper discusses the practical assumptions while using an adaptation layer based hybrid communication architecture and presents the benefits of it while also critically mentioning the shortcomings.

Riding a motorcycle requires both physical and mental effort. These requirements are amplified by factors like long riding hours, high or low temperatures, high relative humidity levels or rain. Besides exposing the rider to the external environment, the vehicle cannot offer full aerodynamic protection and limits him/her in a fixed position, which is less comfortable than that of a car. Furthermore, physical effort is required to steer and actively balance the motorcycle. Such factors may induce impairing states like physical fatigue, distraction and stress. The work carried out within the ADAS&ME project has the aim to create a system able to detect, and possibly in extreme conditions prevent, these states, and then to provide adequate assistance to the rider during long touring travels and, if the situation becomes safety critical, actively enable intervention functions with embedded ad-hoc safety strategy.

Vehicle data is a valuable source for digital services, especially with a rising degree of driving automatization. Despite regulation on data protection has become stricter due to Europe’s GDPR we argue that the exchange of vehicle and driving data will massively increase. We therefore raise the question on what would be a privacy-preserving way of vehicle data exploitation? Blockchain technology could be an enabler, as it is associated with privacy-friendly concepts including transparency, trust, and decentralization. Hence, we launch the discussion on unsolved technical and non-technical issues and provide a concept for an Open Vehicle Data Platform, respecting the privacy of both the vehicle owner and driver using Blockchain technology.

The advancement of automated driving (AD) depends on a multitude of influencing factors, however, achieving higher levels of automation fundamentally hinges on the capabilities of Artificial Intelligence (AI) to perform driving tasks. Improvements in AI hardware and the availability of large amounts of data (Big Data) have fueled the rapid increase in AD-related research and development activities over the past decade and are thus also the key indicators for future development. The shift from humans to AI in vehicle control unlocks many of the well-established potentials of AD, but is also the root for many non-technical issues that affect its introduction. Starting from the state of the art of AI for AD this chapter discusses key challenges and opportunities that mark the development path.

The SilverStream project has developed and demonstrated a new light and affordable vehicle concept (L-category) tailored to the needs of ageing population. The project has combined both ergonomic concepts conceived for elderly people and advanced automotive technologies for improved driveability and energy efficiency. It has been focused on the development of a comprehensive set of technologies covering the whole vehicle, driven by a team of experts in the fields of medical and cognitive science domains through a top/down approach. Hence those technologies have been integrated into a vehicle demonstrator running in realistic tests environment. This paper provides a description of the experimental activities carried out during the whole project to verify the elderly acceptance and satisfaction of the proposed vehicle and integrated technologies.

Impact Clean Power Technology S.A. (ICPT S.A.) has recently developed an innovative, universal, and scalable electronic control unit for electric (EV) and hybrid (HEV) vehicles which fulfils intelligent management functions. One of the main problems of modern EVs is energy management. Proposed ECU (Electronic Control Unit) addresses this issue by performing the optimisation of energy consumption, higher power performance, real time power distribution which results in vehicle range extension.

With shared mobility features, such as keyless entry and cloud stored user profiles, informing and guiding the vehicle design in many areas like the E/E architecture, new challenges on how to approach the early stages of a vehicle development process arise. Car connectivity as the enabler for many shared mobility features is in the focus of the presented approach, however also integration aspects into the whole system design are considered.

For an entrepreneurial project, where a vehicle is conceptualized from the idea through a prototype to a serial product, requirement specifications and function specification are not the right tools to start with. In this paper share2drive and FEV share their design approach of deriving a prioritized feature set for a new vehicle class of a Personal Public Vehicle (PPV), dedicated to the use for shared mobility concepts and with end user satisfaction and User Experience (UX) as guiding principles.

This article outlines market trends, customer needs and challenges that the automotive industry will face to achieve electric, autonomous and shared mobility: For the policy and automotive industry, the trend towards electrification seems to be agreed among stakeholders, however, there are still major challenges, for example, shortage of electricity, batteries and production equipment in some regions. The other topic is autonomous driving. According to a worldwide consumer survey conducted by NRI, the acceptance and needs of customers vary from society to society. The spread of shared mobility also depends on the maturity of the taxi industry. While the coming transformation will be significant and affect the global market, regional, cultural, social issues need to be considered.

This chapter is summarizing the findings of the EU-funded Coordination and Support Action “Safe and Connected Automation in Road Transport” (SCOUT) that has established a comprehensive and structured roadmap to describe innovation paths towards an accelerated development and deployment of high degree automated driving, i.e. particularly at SAE levels 4 and 5. With the involvement of a multitude of experts, the project assessed a number of use cases and development trends, identified societal goals and challenges, and formulated a future vision for connected and automated driving (CAD). It also analysed the state of play in technologies and business models, and it identified gaps and risks. Hurdles for achieving the vision have been recognized, actions to overcome those hurdles have been found at technical, societal, economical, human factors and legal layers, and interlinks between those actions have been described. Finally, opportunities to leapfrog hurdles for innovation in level 4/5 automated driving by a coordinated interplay of actions have been described for five specific use cases: automated on-demand shuttle, truck platooning, valet parking, delivery robot, and traffic-jam chauffeur.