Skip to main content

2024 | Book

Vehicle Computing

From Traditional Transportation to Computing on Wheels


About this book

Over the past century, vehicles have predominantly functioned as a means of transportation. However, as vehicular computation and communication capacities continue to expand, it is anticipated that upcoming connected vehicle (CVs) will not only serve their conventional transport functions but also act as versatile mobile computing platforms. This book presents the concept of Vehicle Computing, encompassing five primary functionalities of CVs: computation, communication, energy management, sensing, and data storage. It proposes a potential business model and explores the challenges and opportunities associated with these domains.

Vehicle Computing serves as an important resource for the research community and practitioners in the field of edge computing and cyber physical system, capturing the essence of a rapidly changing industry, addressing the challenges and opportunities associated with connected vehicles (including software-defined vehicles, autonomous vehicles, electric vehicles), machine learning, communication, sensing, data storage, energy management, and computer systems. It synthesizes the latest research and real-world applications, offering valuable insights to both academia and industry professionals.

Vehicle Computing covers topics such as:

The fundamentals of Vehicle Computing, including its historical context and key components. Advanced communication and networking technologies for connected vehicles. Sensing and data acquisition techniques, including edge and cloud computing integration. Energy management and storage, focusing on electric vehicle infrastructure and vehicle-to-grid. Data storage and processing strategies for vehicular environments. Business models, opportunities, and challenges associated with Vehicle Computing. Real-world applications and case studies, highlighting best practices and future trends.

Table of Contents

Introduction to Vehicle Computing
Over the past century, vehicles have predominantly served as a means of transportation. However, as vehicular computation and communication capacities continue to expand, connected vehicles (CVs) will not only fulfill their conventional transport functions but will also act as versatile mobile computing platforms. In this chapter, we introduce the evolving paradigm of vehicle computing and explore the essential functionalities of CVs that underpin this transformative shift—computation, communication, energy management, sensing, and data storage. We highlight the transition from traditional vehicular roles to advanced computational capacities and detail how these vehicles integrate with and interact with burgeoning communication technologies. The chapter further examines how CVs are poised to become pivotal nodes within energy networks through Vehicle-to-Grid (V2G) integration and how they leverage sophisticated sensing capabilities for enhanced data collection and storage. Besides, this chapter introduces an innovative business model for vehicle computing, addressing the economic and infrastructural challenges while capitalizing on opportunities in this emerging field. By discussing the technical challenges, we also present the opportunities associated with these domains in the era of vehicle computing.
Sidi Lu, Weisong Shi
Mobile Computation in Connected Vehicles
In this chapter, we delve into the transformative role of connected vehicles as dynamic computation platforms, transcending their conventional transportation functions. With the advent of diverse computing hardware such as Graphic Processor Units (GPUs), Digital Signal Processors (DSPs), Field Programmable Gate Arrays (FPGAs), and Application-Specific Integrated Circuits (ASICs), vehicles are now equipped to execute intricate computational tasks. This narrative begins with a historical overview of automotive software and computing systems, highlighting the evolution toward intelligent vehicle applications. Subsequently, it explores the concept of software-defined vehicles, outlining the application landscape and requirements. An in-depth examination of the reference architecture for vehicle computing systems is provided, including state-of-the-art computing systems, real-time operating systems, and middleware solutions like Robot Operating Systems and Autoware. The chapter also addresses the multifaceted challenges associated with vehicle computations, spanning artificial intelligence, vehicle operating systems, hardware costs, and experimental platforms. Through this comprehensive discourse, we illuminate the complex interplay between technology and mobility, charting the path for future innovations in vehicle computing.
Sidi Lu, Weisong Shi
Vehicular Communication and Networking Technologies
As vehicles evolve into sophisticated computing platforms, their ability to communicate effectively becomes critical for safety and efficiency. This chapter provides a comprehensive exploration of mainstream vehicular communication mechanisms, their reliability, bandwidth, scalability, and envisioned advancements. Through detailed discussions on communication architectures, including centralized, decentralized, and publish/subscribe frameworks, this chapter dissects the roles and implications of each in the context of vehicle computing. Besides, this chapter further introduces the innovative EdgeARC, an edge-based architecture for vehicle computing. Next, the implications of Vehicle-to-Everything (V2X) technology are thoroughly discussed, encompassing its pivotal role in establishing a fully interconnected traffic system. The chapter also discusses challenges and strategies for robust cybersecurity within vehicle networks. Later on, case studies and their implementations have been proposed. The chapter concludes by confronting the contemporary challenges in vehicular communication, such as cyberattack protection and the coexistence with human-driven vehicles, while contemplating the future where smart infrastructure becomes an asset rather than a liability.
Sidi Lu, Weisong Shi
Sensing and Data Acquisition Techniques
The advent of connected vehicles (CVs) and the progression toward full autonomy have positioned modern automobiles as complex mobile sensing platforms. Relying on a sophisticated array of sensors—including cameras, LiDARs, radars, IMUs, and GPS—these vehicles perceive and interact with their surroundings with remarkable accuracy. This chapter delves into the multifaceted sensing and data acquisition techniques pivotal to the operation of CVs, examining the roles and integration of various automotive sensors and the challenges they present. It is estimated that a single autonomous vehicle can generate between 20 to 40 terabytes of data each day, including data streams from cameras, sonars, radars, and LiDARs, highlighting the critical necessity for effective data management strategies. Addressing the consequent “data explosion,” this chapter provides insight into the state-of-the-art in data storage, compression, and logging systems tailored for vehicular contexts, which are imperative for enhancing the performance and security of the overall vehicle computing system. Moreover, it investigates the synchronization issues associated with multi-sensor data and proposes solutions for handling anomalous situations such as adverse weather conditions, emergency maneuvers, and challenging work zones. By offering a comprehensive overview of the current challenges and deliberating on future directions, this chapter lays the groundwork for researchers and practitioners to advance the domain of vehicle computing, ensuring secure and efficient management of sensor data.
Sidi Lu, Weisong Shi
Energy Management, Efficiency, and Delivery
This chapter delves into energy management and delivery in the vehicle computing era, specifically focusing on the sophisticated domain of electric vehicles (EVs). It discusses the criticality of real-time monitoring and predictive analysis for key parameters like voltage, temperature, and state of charge (SOC) that ensure the health and efficacy of EV batteries. This chapter also discusses advanced modeling techniques for fuel consumption in heavy-duty trucks, which are essential for optimizing energy usage and reducing environmental impact. Additionally, it highlights the innovative Vehicle-to-Grid (V2G) technologies that promise to revolutionize energy distribution by allowing EVs to interact and contribute to the power grid. The chapter further investigates the strategies for improving V2G integration and the associated challenges, setting the scene for future research. It offers a cohesive understanding of the current state and future directions in vehicle computing, balancing technical depth with practical insights for sustainable energy management in the automotive industry.
Sidi Lu, Weisong Shi
Programming Interfaces for Vehicle Computing
In this chapter, we embark on a comprehensive exploration of Vehicle Programming Interfaces (VPIs) within the transformative sphere of vehicle computing. It scrutinizes the eclectic array of Automotive Software Platforms, from the structured approaches of AUTOSAR and SOAFEE to the cutting-edge developments by Baidu Apollo, Autoware, NVIDIA DRIVE, BlackBerry IVY, and the robotics-focused ROS. We present a stratified analysis of VPIs, delineating their critical function in interfacing between the vehicular core and its animating software across multiple vectors: hardware, data, computation, service, and management. Through a detailed Case Study: VPI Implementation, the chapter concretizes the theoretical framework with practical instances. It examines the physical aspects of VPIs and showcases the implementation within a software ecosystem of real-world VPI applications. Addressing the challenges and opportunities that VPIs present, the chapter probes into the dynamic complexities of integrating these interfaces in VC and concludes with a forward-looking synthesis that highlights their pivotal role in driving the automotive industry toward an interconnected, intelligent future.
Sidi Lu, Weisong Shi
Teleoperation in Vehicle Computing
Throughout the last 100 years, the primary function of vehicles has been to provide transportation, enhance mobility, and establish unprecedented levels of connectivity. However, as we transition into a new age of vehicle computing, the advancement in onboard computing and communication technologies promises to revolutionize the traditional functions of vehicles. The advent of connected vehicles (CVs), especially connected and autonomous vehicles (CAVs), stands as a critical breakthrough, reconceptualizing vehicles as dynamic computing entities. This paradigm shift not only amplifies the operational capabilities of vehicles beyond basic transportation but also assimilates them into an expansive network of interconnected devices and infrastructures. This chapter illustrates how devices, even those with minimal computational power, can utilize the advanced computing resources of nearby CVs to carry out complex operations. Through comprehensive scrutiny of the various aspects of vehicle computing, inclusive of case studies, essential technologies, prospective business models, a foundational computing framework, and upcoming challenges, this narrative investigates the integral role of teleoperation in this evolutionary process. Teleoperation, or the remote maneuvering and operation of vehicles, emerges at the intersection of connectivity and computing, heralding a shift toward vehicles that are increasingly intelligent, autonomous, and multifaceted.
Sidi Lu, Weisong Shi
Testing for Vehicle Computing
This chapter serves as a pivotal testing reference for vehicle computing, providing thorough evaluation and testing approaches that are at the heart of connected and autonomous vehicle technologies. The chapter begins by detailing CAVBench, an innovative benchmark suite specifically conceived for vehicle computing systems, offering a closer look at its architecture and the imperative role of benchmarking in enhancing system performance. Subsequently, it examines crucial metrics for computing systems such as accuracy, timeliness, power, cost, reliability, privacy, and security, underlining their relevance in the assessment process. The narrative then transitions into the domain of simulation, contrasting various simulators and emphasizing their significance through case studies like BlueICE and D-STAR. Furthermore, the chapter explores testbeds for vehicle computing, spanning outdoor and indoor environments and delving into the nuances of single-vehicle and multi-vehicle testing, illustrated by the ICAT case study. Finally, the chapter engages in a thoughtful discussion on the challenges posed by experimental platforms and physical worlds coupling, providing a comprehensive overview that is instrumental for academics, industry professionals, and enthusiasts invested in advancing vehicle computing systems.
Sidi Lu, Weisong Shi
Vehicle Computing
Sidi Lu
Weisong Shi
Copyright Year
Electronic ISBN
Print ISBN

Premium Partner