Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references.

1. Introduction to autonomous driving -- 1.1 Autonomous driving technologies overview -- 1.2 Autonomous driving algorithms -- 1.2.1 Sensing -- 1.2.2 Perception -- 1.2.3 Object recognition and tracking -- 1.2.4 Action -- 1.3 Autonomous driving client system -- 1.3.1 Robot operating system (ROS) -- 1.3.2 Hardware platform -- 1.4 Autonomous driving cloud platform -- 1.4.1 Simulation -- 1.4.2 HD map production -- 1.4.3 Deep learning model training -- 1.5 It is just the beginning --

2. Autonomous vehicle localization -- 2.1 Localization with GNSS -- 2.1.1 GNSS overview -- 2.1.2 GNSS error analysis -- 2.1.3 Satellite-based augmentation systems -- 2.1.4 Real-time kinematic and differential GPS -- 2.1.5 Precise point positioning -- 2.1.6 GNSS INS integration -- 2.2 Localization with LiDAR and high-definition maps -- 2.2.1 LiDAR overview -- 2.2.2 High-definition maps overview -- 2.2.3 Localization with LiDAR and HD map -- 2.3 Visual odometry -- 2.3.1 Stereo visual odometry -- 2.3.2 Monocular visual odometry -- 2.3.3 Visual inertial odometry -- 2.4 Dead reckoning and wheel odometry -- 2.4.1 Wheel encoders -- 2.4.2 Wheel odometry errors -- 2.4.3 Reduction of wheel odometry errors -- 2.5 Sensor fusion -- 2.5.1 CMU Boss for urban challenge -- 2.5.2 Stanford Junior for urban challenge -- 2.5.3 Bertha from Mercedes Benz -- 2.6 References --

3. Perception in autonomous driving -- 3.1 Introduction -- 3.2 Datasets -- 3.3 Detection -- 3.4 Segmentation -- 3.5 Stereo, optical flow, and scene flow -- 3.5.1 Stereo and depth -- 3.5.2 Optical flow -- 3.5.3 Scene flow -- 3.6 Tracking -- 3.7 Conclusions -- 3.8 References --

4. Deep learning in autonomous driving perception -- 4.1 Convolutional neural networks -- 4.2 Detection -- 4.3 Semantic segmentation -- 4.4 Stereo and optical flow -- 4.4.1 Stereo -- 4.4.2 Optical flow -- 4.5 Conclusion -- 4.6 References --

5. Prediction and routing -- 5.1 Planning and control overview -- 5.1.1 Architecture: planning and control in a broader sense -- 5.1.2 Scope of each module: solve the problem with modules -- 5.2 Traffic prediction -- 5.2.1 Behavior prediction as classification -- 5.2.2 Vehicle trajectory generation -- 5.3 Lane level routing -- 5.3.1 Constructing a weighted directed graph for routing -- 5.3.2 Typical routing algorithms -- 5.3.3 Routing graph cost: weak or strong routing -- 5.4 Conclusions -- 5.5 References --

6. Decision, planning, and control -- 6.1 Behavioral decisions -- 6.1.1 Markov decision process approach -- 6.1.2 Scenario-based divide and conquer approach -- 6.2 Motion planning -- 6.2.1 Vehicle model, road model, and SL-coordination system -- 6.2.2 Motion planning with path planning and speed planning -- 6.2.3 Motion planning with longitudinal planning and lateral planning -- 6.3 Feedback control -- 6.3.1 Bicycle model -- 6.3.2 PID control -- 6.4 Conclusions -- 6.5 References --

7. Reinforcement learning-based planning and control -- 7.1 Introduction -- 7.2 Reinforcement learning -- 7.2.1 Q-learning -- 7.2.2 Actor-critic methods -- 7.3 Learning-based planning and control in autonomous driving -- 7.3.1 Reinforcement learning on behavioral decision -- 7.3.2 Reinforcement learning on planning and control -- 7.4 Conclusions -- 7.5 References --

8. Client systems for autonomous driving -- 8.1 Autonomous driving: a complex system -- 8.2 Operating system for autonomous driving -- 8.2.1 ROS overview -- 8.2.2 System reliability -- 8.2.3 Performance improvement -- 8.2.4 Resource management and security -- 8.3 Computing platform -- 8.3.1 Computing platform implementation -- 8.3.2 Existing computing solutions -- 8.3.3 Computer architecture design exploration -- 8.4 References --

9. Cloud platform for autonomous driving -- 9.1 Introduction -- 9.2 Infrastructure -- 9.2.1 Distributed computing framework -- 9.2.2 Distributed storage -- 9.2.3 Heterogeneous computing -- 9.3 Simulation -- 9.3.1 BinPipeRDD -- 9.3.2 Connecting Spark and ROS -- 9.3.3 Performance -- 9.4 Model training -- 9.4.1 Why use Spark? -- 9.4.2 Training platform architecture -- 9.4.3 Heterogeneous computing -- 9.5 HD map generation -- 9.5.1 HD map -- 9.5.2 Map generation in the cloud -- 9.6 Conclusions -- 9.7 References -- Author biographies.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

This book is the first technical overview of autonomous vehicles written for a general computing and engineering audience. The authors share their practical experiences of creating autonomous vehicle systems. These systems are complex, consisting of three major subsystems: (1) algorithms for localization, perception, and planning and control; (2) client systems, such as the robotics operating system and hardware platform; and (3) the cloud platform, which includes data storage, simulation, high-definition (HD) mapping, and deep learning model training. The algorithm subsystem extracts meaningful information from sensor raw data to understand its environment and make decisions about its actions. The client subsystem integrates these algorithms to meet real-time and reliability requirements. The cloud platform provides offline computing and storage capabilities for autonomous vehicles. Using the cloud platform, we are able to test new algorithms and update the HD map--plus, train better recognition, tracking, and decision models. This book consists of nine chapters. Chapter 1 provides an overview of autonomous vehicle systems; Chapter 2 focuses on localization technologies; Chapter 3 discusses traditional techniques used for perception; Chapter 4 discusses deep learning based techniques for perception; Chapter 5 introduces the planning and control sub-system, especially prediction and routing technologies; Chapter 6 focuses on motion planning and feedback control of the planning and control subsystem; Chapter 7 introduces reinforcement learning-based planning and control; Chapter 8 delves into the details of client systems design; and Chapter 9 provides the details of cloud platforms for autonomous driving. This book should be useful to students, researchers, and practitioners alike. Whether you are an undergraduate or a graduate student interested in autonomous driving, you will find herein a comprehensive overview of the whole autonomous vehicle technology stack. If you are an autonomous driving practitioner, the many practical techniques introduced in this book will be of interest to you. Researchers will also find plenty of references for an effective, deeper exploration of the various technologies.

Also available in print.

Title from PDF title page (viewed on October 25, 2017).