From AI to Autonomous and Connected Vehicles: Advanced Driver-Assistance Systems (ADAS)

Description

The main topic of this book is the recent development of on-board advanced driver-assistance systems (ADAS), which we can already tell will eventually contribute to the autonomous and connected vehicles of tomorrow. With the development of automated mobility, it becomes necessary to design a series of modules which, from the data produced by on-board or remote information sources, will enable the construction of a completely automated driving system. These modules are perception, decision and action. State-of-the-art AI techniques and their potential applications in the field of autonomous vehicles are described. Perception systems, focusing on visual sensors, the decision module and the prototyping, testing and evaluation of ADAS systems are all presented for effective implementation on autonomous and connected vehicles. This book also addresses cooperative systems, such as pedestrian detection, as well as the legal issues in the use of autonomous vehicles in open environments. Cover Half-Title Page Title Page Copyright Page Contents Foreword 1 Foreword 2 Foreword 3 Preface 1 Artificial Intelligence for Vehicles 1.1. What is AI? 1.2. The main methods of AI 1.2.1. Deep Learning 1.2.2. Machine Learning 1.2.3. Clustering 1.2.4. Reinforcement learning 1.2.5. Case-based reasoning 1.2.6. Logical reasoning 1.2.7. Multi-agent systems 1.2.8. PAC learning 1.3. Modern AI challenges for the industry 1.3.1. Explainability: XAI (eXplainable Artificial Intelligence) 1.3.2. The design of so-called “hybrid” AI systems 1.4. What is an “intelligent” vehicle? 1.4.1. ADAS 1.4.2. The autonomous vehicle 1.4.2. The construction of the intelligent vehicle’s basic building blocks employing AI methods 1.5. References 2 Conventional Vision or Not: A Selection of Low-level Algorithms 2.1. Introduction 2.2. Vision sensors 2.2.1. Conventional cameras 2.2.2. Emerging sensors 2.3. Vision algorithms 2.3.1. Choosing the type of information to be retrieved from the images 2.3.2. Estimation of ego-movement and localization 2.3.3. Detection of the navigable space by a dense approach 2.3.4. From the detection of 3D plans to visual odometry 2.3.5. Detection of obstacles through the compensation of ego-movement 2.3.6. Visual odometry 2.4. Conclusion 2.5. References 3 Automated Driving, a Question of Trajectory Planning 3.1. Definition of planning 3.2. Trajectory planning: general characteristics 3.2.1. Variables 3.2.2. Constraints 3.2.3. Cost functions 3.2.4. Planning methodology 3.2.5. Co-pilot respecting legal traffic rules 3.2.6. Trajectory prediction for “ghost” objects and vehicles 3.2.7. Trajectory evaluation 3.2.8. Results on real vehicles and on simulators 3.3. Multi-objective trajectory planning 3.3.1. Linear scalarization 3.3.2. Nonlinear scalarization 3.3.3. Ideal methods 3.3.4. Summary of multi-objective planning methods 3.3.5. High level information 3.4. Conclusion on multi-agent planning for a fleet of vehicles: the future of planning 3.5. References 4 From Virtual to Real, How to Prototype, Test, Evaluate and Validate ADAS for the Automated and Connected Vehicle? 4.1. Context and goals 4.2. Generic dynamic and distributed architecture 4.2.1. Introduction 4.2.2. An interoperable platform 4.3. Environment and climatic conditions 4.3.1. Introduction 4.3.2. Environmental modeling: lights, shadows, materials and textures 4.3.3. Degraded, adverse and climatic conditions 4.3.4. Visibility layers and ground truths 4.4. Modeling of perception sensors 4.4.1. Typology of sensor technologies 4.4.2. From a functional model to a physical model 4.4.3. Optical sensors 4.4.4. LIght Detection And Ranging (LIDAR) 4.4.5. RAdio Detection And Ranging (RADAR) 4.4.6. Global Navigation Satellite System (GNSS) 4.5. Connectivity and means of communication 4.5.1. State of the art 4.5.2. Statistical model of the propagation channel 4.5.3. Multi-platform physico-realistic model 4.6. Some relevant use cases 4.6.1. Graphic resources 4.6.2. Communication and overall risk 4.6.3. Automated parking maneuver 4.6.4. Co-pilot and automated driving 4.6.5. Eco-mobility and eco-responsible driving profile 4.7. Conclusion and perspectives 4.8. References 5 Standards for Cooperative Intelligent Transport Systems (C-ITS) 5.1. Context and goals 5.1.1. Intelligent transport systems (ITS) 5.1.2. The connected and cooperative vehicle 5.1.3. Silos communication systems 5.1.4. Cooperative Intelligent Transport Systems (C-ITS) 5.1.5. Diversity of Cooperative ITS services 5.1.6. Standardization bodies 5.1.7. Genesis of the “Cooperative ITS” standards 5.2. “ITS station” architecture 5.2.1. General description 5.2.2. ITS station communication units 5.2.3. Types of ITS stations 5.3. Features of the ITS station architecture 5.3.1. Combination of communication technologies 5.3.2. Centralized communications 5.3.3. Localized communications (V2X) 5.3.4. Hybrid communications 5.3.5. Extensive communications 5.3.6. Communications management 5.3.7. Messaging 5.3.8. Data organization and identification 5.3.9. Secure communications and access to data 5.3.10. Evolution of standards 5.4. Features of the ITS station architecture 5.5. Deployment of Cooperative ITS services 5.6. References 6 The Integration of Pedestrian Orientation for the Benefit of ADAS: A Moroccan Case Study 6.1. Introduction 6.2. Advanced Driver Assistance System (ADAS) 6.3. Proposal for an applicable system to the Moroccan case 6.4. General conclusion 6.5. References 7 Autonomous Vehicle: What Legal Issues? 7.1. Introduction 7.2. The definition of the so-called “autonomous” vehicle 7.3. Legal framework and experiments 7.4. The notion of the “driver” 7.5. The notion of the “custodian” 7.6. What liability regime? 7.7. Self-driving vehicle insurance? 7.8. Personal data and the autonomous vehicle 7.9. The need for uniform regulation List of Authors Index Other titles from iSTE in Mechanical Engineering and Solid Mechanics EULA