Internet of Vehicles and its Applications in Autonomous Driving

Mobility and transportation are the critical means of economic growth in any nation. Transportation is to the movement of people and goods across geographical distances. Transportation systems are an indispensable part of human activities. They remain the life blood of the economy of any nation, interconnecting cities, ports, and airports. They are essentials for everyday living, working, commuting, shopping, traveling, leisure, trading, and distribution of goods. Moving people and products demands smart freeways, bridges, marine ports, mass transit routes, rail lines, tunnels, etc. However, transportation has some notable problems, especially in metropolitan areas, which include traffic congestion, accidents and safety, energy consumption, and negative environmental impacts. To meet these and other related problems, intelligent transportation systems (ITS) offer a host of technologies.

This chapter provides an overview on ITS. It begins by giving a brief overview of the history of ITS. Then it discusses the concept and ITS enabling technologies. Then it covers ITS components, technologies, and examples and how to implement ITS. It addresses the benefits and challenges of ITS. It mentions some of recent developments in ITS. The final section concludes with comments.

Wireless technologies have witnessed an enormous development over the past few years. This technology allows communication even between mobile devices, which are called as mobile ad hoc networks (MANETs). Intelligent traffic control systems employ that part of MANET which allows communication between vehicles, called vehicular ad hoc networks (VANETs). This chapter proposes the use of VANET to ensure efficient traffic management and safe driving of vehicles in India. Two topology-based protocols are taken into consideration for simulation. It also analyzes the way in which communication takes place while using different protocols and proposes a suitable protocol and frequency for the corresponding application.

This study is an overview of autonomous cars and also the challenges faced in the field of autonomous cars. Recent advances are being made in the field of planning, perception, and decision-making for autonomous vehicles. This has led to great improvements in functional capabilities; several prototypes are already on roads. The challenge is to obtain the safe execution of vehicles in all driving situations. In this study, we will see recent methodologies for vehicle control using kinematic and dynamic model, collaborative autonomy, decision-making system for autonomous vehicles using convolutional neural network, path planning for autonomous vehicles using model predictive control, real-time decision-making for autonomous city vehicle using world model and driving maneuver system, and intention-aware autonomous driving decision-making using hidden Markov model and partially observable Markov decision process.

In recent years, the Internet of Things (IoT) has received significant attention globally by interconnecting every device from a small household object to large industrial equipment through the Internet. Among diverse applications, the Internet of Vehicles (IoV) is that interconnects numerous vehicles to communicate significant information through the IoT enabled network. The revolution in IoV made every vehicle as a smart object that captures, processes, and communicates information among the connected vehicles. Due to modernization, technological advancements have facilitated an explosive growth in the usage of the number of vehicles. Consequently, it leads to severe traffic congestion, increased number of accidents, the rise in pollution, etc. Hence, the IoV plays a prominent role to effectively administer and manage the traffic conditions. Among several IoT communication technologies, Wireless Personal Area Networks (WPAN) is limited to short transmission ranges, whereas Low Power Wide Area Networks (LPWAN) although it has extended coverage but suffers from lower throughput. Despite the popularity of Wireless Local Area Networks (WLAN), it suffers from severe contention in the dense networks. Hence, IEEE 802.11ah is introduced by the IEEE 802 task group to support IoT applications. IEEE 802.11ah operates at sub-1 GHz International Scientific Medicine (ISM) frequency bands. The standard provides an extended coverage up to 1 km, the data rate of 78 Mbps and connectivity to 8192 devices. It provides several enhancements to the Physical (PHY) and Medium Access Control (MAC) layer. The standard reduces the control overhead by implementing Null Data Packet (NDP) MAC frames, short MAC headers, etc. Hierarchical Association Identifiers (AID) is implemented to enhance the scalability. Above all, Restricted Access Window (RAW) mechanism is introduced to reduce the channel contention among the devices. Analyst forecast that there will be two billion number of vehicles by 2035. To support such dense IoV networks, IEEE 802.11ah is a perfect candidate. However, there exist several design issues and challenges when we propose IEEE 802.11ah for IoV. In this chapter, we discuss the various design issues and challenges in detail.

Connected vehicles are to be a reality in the near future. Vehicles can avoid accidents by communicating with each other. However, there are some problems related to connected vehicles which are not similar to other networks. They are frequent disconnections, highly varying topology, and limited bandwidth. For this reason, medium access protocols used for other networks such as mobile ad hoc networks are not suitable for vehicular communications. Hence, a new set of medium access protocols are developed for vehicular communications. This chapter describes in detail the major advances made in the area of medium access control for vehicular communications.

Consistently, car fabrication burn through millions in financing advancement of bleeding edge advances to keep drivers safe and mishap free while working their vehicles. These advances are referred to as Advanced Driver Assistance Systems (ADAS) and everyone is constrained by complex ongoing installed frameworks. This chapter introduces the basics of ADAS and provides a descriptive insight about Internet of Vehicles and ADAS. It gives an itemized review of past, present, and future plans of every variation. A diversified list of components, hardware, security issues, etc. have been discussed.

The accident rate in Saudi Arabia is quite high due to several factors such as speeding, lousy weather, pedestrian unawareness, etc. For the past year, Kingdom of Saudi Arabia suffered from a significant loss of human life and economical due to a traffic accident. Ministry of Interior Riyadh Traffic department reporting that traffic accident has made financial loss about 21 billion riyals a year. The traffic accident has increased rapidly, six injuries per eight incidents are caused by a traffic accident, whereas the global ratio is one injury for every eight accidents. This paper proposed unique solution by using two primary cameras for tracking the driver and pedestrian. The recognition rate of facial tracking have been evaluated through several machine learning algorithm and Tree has achieved the highest recognition rate with 87% followed by KNN with 77%. The result is quite promising with this double tracking: facial tracking to track the drowsiness and awareness while pedestrian tracking brake analysis for the object in front of or behind the vehicle. The future work with advanced sensor such as sonar and high speed camera might improve the accuracy and efficiency of the system.

Automatic Driver Assistance System (ADAS) is a concept to have an innovative automatic driver which is growing rapidly now-a-days. Even though an ADAS system is functioning automatically without the necessity of driver in presence, it is not considered as completely autonomous car. In some of the practical situations, it is more typical to handle few complications in driving. So, the latest technologies have not grown to the level of creating fully autonomous driving system. The ADAS is developed to avoid the road accidents due to human errors. There are various ADAS technologies developed so-far to provide driver safety and comfort.

Different control units are embedded in to the entire system for full control of the driving system. One of the control unit is Pedestrian Crash Avoidance Mitigation (PCAM). And one of the most difficult parts to assist the PCAM control unit is during the winter season when there is huge fog or haziness on the roads. So, an additional processing unit should be developed to get proper assistance to the ADAS system to avoid the crash during pedestrian crossing the road. For this purpose, a special imaging system should be introduced for better visualization of roads, nearby vehicles and people crossing the roads. Infrared imaging camera is additionally used with the normal camera system. So that the two images were processed with a concept of fusion, which combines the best properties of two images, and produce a clear vision of scene. This may improve the effective improvement in the PCAM control unit and enabling the autonomous cars to be driven successfully even in the heavy hazed areas without any crashes or accidents.

The evolution of Internet-of-Vehicles (IoV) has promised improvement in traffic management and road safety. However, with continuously increasing number of vehicles on road, there are numerous challenges associated with IoV. Communication among vehicles is needed to be secure and bandwidth efficient. Messages exchanged between vehicles must be authentic so as to maintain trust among the network. On the other hand, blockchain is a rapidly emerging technology for various IoT related applications. It ensures security by maintaining transaction history in the form of an encrypted and immutable ledger. Therefore, blockchain-based communications can potentially solve various challenges of IoV. However, there are certain constraints which make the practical implementation of blockchain in IoV difficult. For example, one of the most common consensus algorithms of blockchain, Proof-of-Work, is energy inefficient and time consuming. Various other consensus algorithms have been developed but they compromise security. This chapter conceptualises the implementation of blockchain in IoV, particularly useful in emergency situations, such as accident. We discuss some consensus algorithms of blockchains and their suitability in IoV, ultimately leading to a formation of voting based consensus integrated with a relay selection mechanism. Furthermore, we present an economic model to incentivise vehicles for safe driving and cooperation through blockchain-enabled transaction of rewards. The security capacity of proposed blockchain against collusion of relay nodes is analysed by game theory. Simulation results of the proposed approach demonstrate its efficiency in terms of latency and success rate in message transmission as compared to other blockchain-based solutions for IoV.

Nowadays vehicles have been used at a large scale in the modern society. But in many countries the current traffic-safety statistics is very terrifying. Many people are killed and injured in road accident. To reduce this problem government and manufacturers of countries have launched different initiatives like use of safety belt, airbags, antiblocking brake system, and smart vehicular transportation system. Upcoming traffic safety initiatives in smart transportation system depend on information technology and this technology also helps to authenticate and traceable the vehicles in the system. Recently, the smart vehicular system uses different types of networks like VANETs, AI based applications, etc. that aims to provide a safer, coordinated, smooth, and smart mode of transportation. This article focuses on the communication security issues in smart vehicular applications or IoV. Transmitting messages efficiently and honestly among vehicles is the key issues in this system. At present, the communication in smart transportation system is vulnerable to various types of security attacks because it uses an open wireless connection. The different types of attacks are secrecy attack, routing attack, data authenticity attack, attack on authentication besides this in the dense environment, the vehicle may receive multiple messages at the same time. Therefore, how to complete the authentication of multiple messages in a short time is an urgent problem. To address these problems, here we have introduced some technique using the concept of approximation algorithm and linear congruence. The different types of experiments on our technique and their results conform that our scheme is very secure, robust, and efficient for data transmission in smart vehicular or IoV.

This chapter describes application of AI tool to detect error for electric vehicle gearbox and design algorithm. Sequentially logged data demonstrate the condition monitoring approach and detects going to damage in the gear transmission that being done in advance. AI Autocorrect drive experience great service system and assists to driver.

Artificial intelligence (AI) technique gives solution to error coming failure in transmission system of electric power-train that triggers Engine Controller Unit (ECU) to work on error detection for a coming inadequacy. Chapter describes AI application usage of AI algorithm design and predict coming error. Due to increased expectation in range extend and reliability using electric car is that it should run in case of minor failure or major failure of any component by using trained knowledge. Decision support system uses knowledge of past failure and must adjust to a error coming. For example, Adaptive Fault Tolerant (AFT) (Liu and Peng, Veh Syst Dyn 48(11):1395–1412, 2010; Wallenberg, Feasibility study for an energy management system intelligent alarm process. In IEEE conference proceedings on power industry computer applications, pp 249–254, 1985) knows history and deals to overcome the error.