Connected and Automated Vehicles: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Memoona Sadaf
,
Zafar Iqbal
,
Abdul Rehman Javed
,
Irum Saba
,
Moez Krichen
,
Sajid Majeed
,
Arooj Raza

Autonomous vehicles (AV) are game-changing innovations that promise a safer, more convenient, and environmentally friendly mode of transportation than traditional vehicles. 

  • autonomous vehicles
  • vehicular technology
  • artificial intelligence
  • federated learning
  • deep learning
  • machine learning
  • cloud computing

1. Introduction

The development and deployment of autonomous vehicles (AVs) have captured the attention of researchers, policymakers, and the public alike. AVs promise to transform how we travel and interact with the world. Their advanced sensors, machine-learning algorithms, and sophisticated control systems offer a safer, more efficient, and more convenient mode of transportation than traditional vehicles. AVs are expected to profoundly impact society, with potential benefits including enhanced safety, increased efficiency, reduced traffic congestion, and improved mobility. Driver automation provides only one automatic feature. For instance, with the help of cruise control, speed is monitored. In partial automation, the vehicle has the feature of steering and acceleration. Conditional automation can detect the environment, and all tasks are performed automatically, but still, human efforts are required. In high automation, human efforts are optional but are preferable. In high automation, zero human intervention is required [1][2].
Since the 1920s, when the radio-based vehicle-to-vehicle (V2V) communication system was developed, researchers have been interested in automated cars. Later, in the 1930s and 1940s, electromagnetic vehicle guidance was developed, and in the 1950s and 1960s, magnets were added to vehicles to test smart motorways [3]. Autonomous vehicles can view the world in a 360° range, thanks to high-precision technology, which is twice as much as humans, who can only see 180° horizontally [4]. Vehicle-to-Everything (V2X) communication is an essential technology for enabling the full potential of autonomous vehicles. It enables communication between vehicles and other road users, including pedestrians, bicyclists, and infrastructure, such as traffic signals and road signs. V2X technology allows AVs to exchange data with other vehicles and infrastructure in real-time, improving safety, efficiency, and environmental impact, as shown in Figure 1.
Figure 1. AVs Communication Scenarios.
Due to the autonomous nature of the vehicle and the fact that it would function with little to no human input, even those with visual or hearing impairments can own one, making them inclusive. The first issue is because of constant connectivity with the outside world; data protection might develop into a cyber issue. Autonomous driving has advanced gradually and is becoming more sophisticated in perceiving environments in everyday life properly and quickly analyzing sensor information; thanks to the growth of the Internet of Things and artificial intelligence technologies, it can now make complex decisions by itself.

2. Infrastructure and Ad Hoc Autonomous Vehicle

Autonomous vehicles can be classified into two categories based on the usage of infrastructure they use infrastructure-based autonomous vehicles and Ad hoc (infrastructure-less) autonomous vehicles. Infrastructure-based autonomous vehicles rely on physical infrastructure such as roads, traffic signals, and mapping systems. They use Global Positioning System (GPS), LiDAR, RADAR, cameras, and other sensors to navigate, but also require a well-maintained network of roads, signs, and signals to ensure safe and efficient operation [5]. Infrastructure-based autonomous vehicles are autonomous vehicles that rely on physical infrastructure such as roads, traffic signals, and mapping systems to operate. These vehicles use GPS, LiDAR, RADAR, cameras, and other sensors to navigate and make decisions. Still, they also require a well-maintained network of roads, signs, and signals to ensure safe and efficient operation. Some key features and benefits of infrastructure-based autonomous vehicles include [6]:

1.
Improved Safety: By relying on physical infrastructure, infrastructure-based autonomous vehicles can use safety features such as traffic signals, road markings, and signs to make driving decisions and reduce the risk of accidents.
2.
Increased Efficiency: Infrastructure-based autonomous vehicles can optimize their routes based on real-time traffic data and use dedicated autonomous vehicle lanes to reduce congestion and improve overall traffic flow.
3.
Improved User Experience: Infrastructure-based autonomous vehicles can provide a more comfortable and convenient riding experience, using amenities such as rest stops, charging stations, and service facilities along the way. However, there are also some limitations to infrastructure-based autonomous vehicles [7], such as:
•
Cost: Implementing the necessary physical infrastructure can be expensive, and maintaining it can also be a high ongoing cost.
•
Limited Operating Environments: Infrastructure-based autonomous vehicles are limited to operating in areas with well-defined roads and traffic signals and may not be suitable for rural or off-road environments.
•
Dependence on Human Intervention: While infrastructure-based autonomous vehicles can use physical infrastructure to make driving decisions, they may still require human intervention in certain scenarios, such as system failure or road closure.
On the other hand, infrastructure-less autonomous vehicles do not rely on any physical infrastructure to operate. Instead, they use advanced sensors and algorithms to perceive their environment, make decisions, and navigate [8]. This allows them to operate in environments without well-defined roads or traffic signals. However, the lack of physical infrastructure can also pose challenges regarding safety, reliability, and scalability [9].

2.1. Technologies

Autonomous vehicles utilize several important technologies that are as follows:
  • Sensors: To observe and comprehend their environment, autonomous cars use a range of sensors, including cameras, LiDAR, radar, and ultrasonic sensors. These sensors give the vehicle information about its surroundings, such as the location, mobility of other cars, pedestrians, and obstacles [10].
  • Computer Vision: Computer vision algorithms are used to process and analyze the data collected by the vehicle’s sensors. These algorithms help the vehicle to identify and track objects in its environment, as well as to understand their movement and behavior.
  • Artificial Intelligence (AI) and Machine Learning: Algorithms based on machine learning and artificial intelligence are utilized to make choices and direct the vehicle’s activities. For example, they can be used to determine the vehicle’s best path to follow, predict the behavior of other road users, and react to unexpected events.
  • GPS and Maps: GPS and high-definition maps are used to provide the vehicle with information about its location and help it navigate and avoid obstacles [11].
  • Communication Systems: Autonomous vehicles use a variety of communication systems, such as cellular networks, dedicated short-range communication (DSRC), and Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication, to exchange information with other vehicles, road infrastructure, and the cloud.
  • Actuation Systems: Autonomous vehicles use actuation systems, such as electric motors, hydraulic actuators, and pneumatic systems, to control the vehicle’s movement and perform tasks such as steering, accelerating, and braking.
  • Power and Energy Management Systems: Autonomous vehicles use power and energy management systems, such as batteries, fuel cells, and regenerative braking, to provide the vehicle with the energy needed to operate and optimize its energy efficiency.

2.2. Routing

Routing in autonomous vehicles refers to determining the best path for the vehicle from its starting point to its destination. This is an important aspect of autonomous vehicle technology, enabling it to navigate safely and efficiently through its environment [12]. Several key factors are considered when determining the best route for an autonomous vehicle, including:
  • Traffic Conditions: The vehicle uses real-time traffic data to avoid congested areas and to select the fastest and most efficient route.
  • Road Infrastructure: The vehicle considers the physical layout of the road network, including the presence of intersections, toll booths, and other road features when selecting a route.
  • Obstacles: The vehicle uses its sensors to detect and avoid obstacles, such as other vehicles, pedestrians, and road work that may be present along the route.
  • Safety: The vehicle considers the safety of its passengers and other road users when selecting a route. For example, it may avoid routes with a high incidence of accidents or with poor road conditions.
  • Energy Efficiency: The vehicle considers the energy consumption of different routes and selects the route that minimizes energy usage.

2.3. Data Dissemination

There are several ways in which data can be disseminated in autonomous vehicles; autonomous vehicles use onboard networks, such as Ethernet and Controller Area Network (CAN) Bus, to share data within the vehicle. This enables different systems and components to exchange information and collaborate to make informed decisions. It uses V2V communication to share data with other vehicles. This enables the vehicles to share information about their surroundings, such as the location of other vehicles and obstacles, and to coordinate their movements to improve safety and efficiency. V2I communication shares data with road infrastructure, such as traffic signals and signs. This enables the vehicle to receive information about traffic conditions, road closures, and other relevant information that can be used to make informed decisions. Autonomous vehicles can also use cloud services to access real-time data and cloud-based resources. This includes data from remote sensors, traffic information, and weather data, which can be used to make informed decisions and improve the vehicle’s performance [13].

3. Autonomous Vehicles in Smart Cities in a Nutshell

3.1. Public Adoption

Autonomous vehicle (AV) public acceptance is a complicated subject reliant on several variables, including technology improvements, laws, infrastructure, and customer trust, as seen in Figure 2. AV technology is still under development and not yet completely prepared for wide-scale implementation [14]. Numerous businesses and governments fund research and testing to enhance the technology and sell AVs. Many areas still develop AV regulations, which differ by nation and region [15]. Additionally, it is necessary to construct and enhance the AV infrastructure, which consists of dedicated lanes, charging stations, and communication networks. Another crucial aspect of AV adoption is consumer faith in them. According to studies, many individuals are reluctant to ride in AVs or permit them to operate on public roads because they are concerned about their reliability and safety [16].
Technologies 11 00117 g003
Figure 2. Public Adoption of Autonomous Vehicles.

3.1.1. Technological Adoption

The complicated technology underlying AVs includes many systems and elements, including sensors, perception algorithms, decision-making systems, etc. In concert, the seamless and reliable operation of any of these systems poses a significant challenge. It is expensive to develop and incorporate AV technology into automobiles [17]. As a result, AVs might become more expensive, reducing their accessibility for the typical user. People can have inflated expectations of what AVs are capable of, which could lead to disappointment and mistrust when the technology falls short.

3.1.2. Consumer Trust

As it is essential for successfully adopting the technology, consumer trust is a significant issue with autonomous vehicles (AVs). If consumers believe AVs to be risky, they might be reluctant to trust them. This can result from previous AV-related mishaps, a lack of knowledge about the technology, or doubts regarding the dependability of the systems. Suppose customers are unsure of how AVs operate or believe that the businesses creating and marketing the technology need to be more honest about its capabilities and restrictions. In that case, customers can be reluctant to trust AVs [18].

3.1.3. Infrastructure Adoption

The minimal AV infrastructure now available is one of the key issues. This includes the absence of the AVs’ necessary communication networks, charging stations, and dedicated lanes. Standardization and interoperability are necessary for AV infrastructure to interact with the vehicles smoothly and communicate with them to assure flawless operation [19]. As AVs have the potential to alter how we move across space and utilize it, new urban design methods will be necessary. When creating new infrastructure, this will need to be considered. The required infrastructure must be created and integrated in a way that is economical, interoperable, and responsive to the changing requirements of the transportation system to support the safe and effective operation of AVs.
Autonomous vehicle (AV) deployment has been modest in developed nations thus far but is anticipated to pick up. Several businesses, like Waymo and Tesla, have started to deploy AVs in small numbers, primarily for research and development. For instance, Tesla has been utilizing its Autopilot technology on its electric cars, while Waymo has been testing its autonomous vehicles on public highways in California and Arizona [20].

3.2. Planning the Driverless City

The process of preparing cities for integrating autonomous cars and its effects on urban life is called “Planning the Driverless City”. This considers variables including transportation networks, urban planning, and public policy [21]. The goal is to minimize negative effects while ensuring that cities are fully prepared to benefit from driverless technology. Governmental organizations, transportation businesses, IT firms, and other stakeholders might work together during the planning phase. Designing a driverless city necessitates considering several considerations, such as infrastructure, communication and coordination, Data and Privacy, regulations, integration with public transportation, and social and cultural impacts, as shown in Figure 3.
Technologies 11 00117 g004
Figure 3. Key Pillars of a Sustainable and Resilient Smart City Ecosystem.

3.2.1. Infrastructure

Infrastructure plays a crucial role in deploying and operating autonomous cars since it impacts how well they can function. To understand their surroundings and abide by traffic laws, autonomous cars need delineated roads and traffic lights [22]. The car needs accurate GPS and mapping data to locate and decide its course. To ensure they can run continually and effectively, they also need facilities for charging and maintenance. A lot of data is produced and needed by AVs, and this data needs to be processed and stored in secure data centers.

3.2.2. Communication and Coordination

The deployment and operation of autonomous vehicles depend heavily on collaboration and communication. To coordinate their movements, exchange data about their location, speed, and trajectory, and prevent crashes while maximizing traffic flow, autonomous vehicles must be able to communicate with one another [23]. Being able to interface with the infrastructure, such as traffic lights and road signs, to receive real-time updates on the state of the roads and traffic patterns.

3.2.3. Data and Privacy

Autonomous vehicles must have access to real-time data and traffic information while maintaining individual privacy to assure safety and effectiveness. The creation and use of autonomous cars depend heavily on data and privacy. Safety, public trust, legal compliance, and maintaining a competitive edge depend on safeguarding data gathered by AVs [24]. For decision-making and safe operation, AVs rely on enormous volumes of data. For the safety of passengers and other road users, it is essential to ensure that these data are accurate and secure.

3.2.4. Regulation

Regulations aid in making sure that AVs are built, tested, and used in a way that protects passengers and other road users and that they comply with safety requirements. It can ensure that AVs are created and used consistently across numerous areas and legal systems. This can make deploying AVs on a large scale easier and ensure system compatibility. By defining standards for AV design, operation, and maintenance, as well as specific rules for protecting the personal data gathered by AVs, regulations can aid in the protection of consumers. Governments must establish rules to guarantee autonomous vehicles’ security and moral use in urban settings [25].

3.2.5. Integration with Public Transportation

Autonomous vehicles can enhance the current public transit networks, giving passengers more options and easing congestion. Integrating AVs with public transportation can increase accessibility for those who cannot drive, such as the elderly, disabled, and children.

3.2.6. Social and Cultural Impact

It is necessary to consider how these changes will be handled and disseminated to the general public because the advent of autonomous vehicles will have a big social and cultural influence. Many occupations in the transportation industry, including those of truck and taxi drivers, could be replaced by AVs, which could substantially affect the labor market. It affects various groups of people differently, such as low-income neighborhoods; thus, it is crucial to consider these consequences and deal with any inequalities that may emerge [26].

3.3. Traffic Management

The coordination of self-driving automobiles is referred to as traffic management in autonomous vehicles, and it aims to improve traffic flow, lessen congestion, and boost road safety. Numerous methods can accomplish this, including real-time traffic monitoring, vehicle communication, traffic prediction, and routing algorithms. The infrastructure of smart cities can also be combined with traffic management systems to create a connected network that can react to shifting road conditions. The objective is to develop a transportation system that is safer, more effective, and more sustainable. The subject of traffic management and control in a transportation system with autonomous cars is the focus of ref. [27]. The author analyzes the difficulties and constraints that must be solved to fully exploit autonomous vehicle advantages, including increased safety, effectiveness, and sustainability. The essay also highlights the necessity for a fresh strategy for managing and controlling traffic in an environment with autonomous vehicles, including the application of cutting-edge tools like real-time traffic monitoring and vehicle communication. Even if there is still much to be accomplished in this area, the author concludes that incorporating autonomous vehicles into the transportation system has great potential.

3.4. Environmental Impact and Public Health

The design and use of the vehicles, the charging and power infrastructure for electric vehicles, and the broader transportation system in which they are incorporated are just a few of the variables that affect how environmentally friendly autonomous vehicles are [28][29]. Autonomous cars can potentially increase overall sustainability in the transportation industry by lowering emissions and energy use. The design of the vehicles, the charging and power systems for electric vehicles, and the overall transportation system in which they are integrated are just a few of the variables that will determine whether or not autonomous vehicles can reduce emissions and energy consumption in the transportation sector, according to research [27].
Several variables, such as the decline in traffic accidents, noise pollution, and changes in physical activity, will affect how autonomous vehicles affect public health. Policy choices, technological developments, and changes in transportation behavior and habits likely influence these variables. To ensure that the development of autonomous vehicles benefits society, it will be crucial to monitor and evaluate their influence on public health closely. Increased sedentary behavior and decreased physical activity could result from autonomous vehicles, exacerbating obesity and other health issues. The need for travel may rise due to autonomous vehicles, resulting in more clogged roads and less physical exercise [30][31].
An analysis of how autonomous vehicles affect public health can be found in article [32]. The authors examine self-driving cars’ potential advantages and disadvantages, such as increased safety, physical activity, lower pollution, and screen time. To make sure that the development of autonomous vehicles has a good impact on public health, there is a need for technological advancements as well as regulatory interventions. The authors conclude that interdisciplinary research, stakeholder involvement, and evidence-based policymaking are necessary to address the health effects of autonomous vehicles.

4. Emerging Technologies

4.1. Artificial Intelligence Techniques

The development of autonomous cars depends heavily on artificial intelligence (AI). It allows the vehicle to perceive, comprehend, and act in its environment. To enhance different areas such as communication, safety, and traffic efficiency in vehicle ad hoc networks (VANETs), artificial intelligence approaches have been extensively investigated [33]. The following are some typical AI methods applied in Autonomous Vehicles:
  • Machine learning (ML) is utilized for anomaly detection, route optimization, and traffic prediction [34].
  • Reinforcement learning (RL) is a technique for dynamic route planning and adaptive traffic control.
  • Artificial neural networks (ANN) are used to identify, classify, and communicate about vehicles.
  • Fuzzy logic is used to make safety-critical decisions like emergency braking.
  • The use of genetic algorithms (GA) to improve network communication and energy efficiency.
  • Swarm intelligence—utilized in platooning of vehicles for cooperative communication.
  • Natural language processing (NLP)—utilized for hands-free operation and other human-vehicle interactions. Figure 4 shows the graphical representation of AI techniques.
Technologies 11 00117 g005
Figure 4. The Evolving Landscape of Artificial Intelligence Techniques.

4.2. Cloud Computing

The technology behind autonomous cars aims to lessen our reliance on fossil fuels, reduce traffic jams, and make it easier for the disabled and the elderly to travel. The employment of technology in autonomous vehicles allows for a 60% reduction in pollutants and a 90% reduction in road accidents. Automobiles employ AI methods for data management and analysis to make sense of the vast volumes of information generated by sensors and other onboard equipment. Voice recognition, picture identification, and decision-making are just some of the many uses for machine learning algorithms, deep learning, reinforcement learning, and simultaneous localization and mapping (SLAM) in autonomous vehicles. Edge computing, vehicular cloud computing (VCC), software-defined networking (SDN), network function virtualization (NFV), and named data networking are all promising new developments in the field of autonomous vehicles (NDN). While NFV emphasizes computational power, NDN facilitates efficient data transfer, edge computing enables real-time data processing, SDN enables interoperability between different data sources, virtualized compute infrastructure improves traffic management and road safety, and VCC focuses on data center consolidation. These advancements in technology are crucial to ensuring that autonomous vehicles can be used safely and effectively [35].
The hardest part of securing autonomous automobiles is designing an edge computing infrastructure. Autonomous automobiles need enough computing power, redundancy, and security to prevent accidents. Dealing with massive amounts of real-time data is tough. Due to their mobility, edge computing systems have strict energy consumption constraints, and sensor data are usually quite varied. High-speed autonomous automobile safety demands plenty of computing power with low energy use. Vehicle-to-everything (V2X) communications can improve peripheral performance and energy. Studying how V2X-enabled automobiles interact with one other and infrastructure is needed. Autonomous driving requires safeguarding edge computing systems from attacks across the sensor and computing stack [36]. Edge YOLO is a method for detecting movable objects proposed in the study and is adapted specifically for edge computing technology. 
Vehicular cloud computing (VCC), which advances cloud computing, enables intelligent transportation, autonomous driving, vehicle control, Internet surfing, online documentation, and infotainment applications. The authors’ survey examined privacy and safety issues in VCC research. The authors examine security, privacy, VCC design, feature analysis, and application scenarios. To address VCC security and privacy challenges, the authors first evaluate the various attack surfaces of linked VCC, including the in-vehicle network, V2X network, and vehicular cloud [37].
Various techniques have been explored for object detection and tracking in the literature. One common approach is using LiDAR-based object detection, where LiDAR sensors measure the distance and position of objects in the vehicle’s vicinity. Research works, such as [38][39], have focused on using LiDAR data for accurate object detection and tracking. The research work of [38] proposes a comprehensive data acquisition and analytics platform specifically designed for automated driving systems. The platform integrates various data sources, including LiDAR data, from connected vehicles to provide real-time and post-processing analytics. 
The SAVP system uses Fog-computing and Blockchain technologies to improve the collaborative IoT-cloud platform for building and administering AV SP systems. Fog nodes connect edge devices that support the Internet of Things to parking-related services [40]. A lightweight, integrated Blockchain and cryptography (LIBC) module at each fog node authorizes and grants AV access in every parking phase to meet privacy and security concerns. A proof-of-concept implementation of the proposed SAVP system showed that its average response time, efficiency, privacy, and security were very good, opening the way for a proven system [41][42].

4.3. Solar Power Electric Vehicles

Ad hoc networks provide an environment of cooperation and coordination among self-operated nodes, which allows communication to occur typically through several hops. Nodes sometimes refuse to work with one another because of their social likeness and mobility. This study examines the primary causes of selfish behavior adaptation in nodes and management strategies for such nodes. It is possible to control the selfish nodes by restricting or encouraging their network participation.
A thorough analysis of the design challenges, communication strategies, and routing protocols of UAVs with unresolved research questions. In UAV communication, preserving data links’ integrity is an ongoing research topic. The data-centric routing algorithm opens up new research possibilities. The topic of UAV communication while addressing nodes in 3D is still substantially unexplored. The distribution of audio-video data severely constrains the FANET application scenario’s requirement for bandwidth. Noise is added to the transmission as data transfer bandwidth is increased. Network latency reduction in dense ad hoc network deployment remains a crucial research area. The non-Line-of-Sight communication FANET architecture is still substantially unexplored. One of the biggest obstacles facing FANETs is still communication. 
Researchers have paid more attention to VANET due to its greater mobility, dynamic connection, and decentralized administration. Security is the main issue preventing the VANET from disseminating data effectively. Effective security frameworks are necessary for the VANET’s secure message processing & sharing. There are several network security issues that VANET faces that are also present in traditional wireless networks.

5. Cyber Attacks and Management

5.1. Cyber Attacks

Over the past few years, autonomous automobile excitement has increased quickly as numerous major technology companies support the idea. Google established the Waymo subsidiary to create and sell consumer-ready autonomous cars worldwide. The organization wagers that driverless cars will soon fundamentally alter how we travel, along with numerous other players in the tech and automotive sectors. Safer roads, less reliance on fossil fuels, and more affordable transportation will all be dramatic improvements. Figure 5 shows the potential attacks on sensors, protocols, and in-vehicle systems.
Technologies 11 00117 g006
Figure 5. Autonomous Vehicles Attack Surface.

5.2. Attacks Management

GPS: To prevent GPS-targeted attacks, a variety of defenses have been deployed. For instance, the false signals differ visually from those transmitted by satellites. Attacks that consider the signal’s power, the time between broadcasts, and the signal clock information could be detected using this method [43]. Ref. [44] utilized the receiver’s correlation function distortions to evaluate the GPS signal’s accuracy. Investigate the direction of arrival (DoA), which uses an antenna array to thwart attacks because the DoA of GPS signals would disclose a different carry phase than spoofing signals. Other methods use GPS broadcasts to embed cryptographic algorithms for assault defense. Encrypt GPS L1 P(Y) code to see if a spoofing attempt is being made. 

LiDAR: Changing the way LiDAR transmits and receives light is one possible technique. If the adversary intends to carry out the attack effectively, they must coordinate the false laser with the LiDAR laser. Defensive strategies for LiDAR have been shown in Figure 6. The LiDAR laser can prevent an assailant by repeatedly firing laser pulses in one direction, say three times. As LiDAR can only receive lasers from a fixed angle while rotating, limiting the impact of attacks by reducing the receiving angle is possible; however, doing so also lowers LiDAR’s sensitivity.

Technologies 11 00117 g010
Figure 6. Defense Approaches of Attacks Against Sensors.
Camera: Due to the camera’s vulnerability brought on by its optical characteristics, it is challenging to design a completely secure camera. Redundancy, for some threats, photochromic lenses and removable near-infrared cut filters may be sufficient [4], despite any potential weaknesses or new problems they may create.
Ultrasonic sensors: The first technique allows for the authentication of physical signals by utilizing the idea of changing waveform properties. The second method uses two or more sensors to identify attackers, regain the ability to recognize obstacles and identify attacks [45].

5.2.2. Defence Approaches for In-Vehicle Systems

The simplest method to thwart the jamming attack is to demand that the car owner double-check that the door is locked before driving away. Light or sound may be employed to verify that an automobile is correctly locked. However, the defense is only effective against assaults that use jamming alone. The remote confirmation method is useless if the intruder can replay the “unlock” signal; the door might lock properly. Therefore, the most basic form of defense is to lock the doors before exiting the vehicle. The quickest way to stop a relay assault is to shield the key when unused. The antenna on the side of the key cannot receive or transmit the signal from the key fob if the key is enclosed in a box. The passive remote keyless system’s most attractive feature is disabled because using this method of entry requires the user to take their key out, which is inconvenient for them [46].
Distance bounding can be used to defend against the Relay attack. A distance-bounding approach uses quick message exchanges to confirm the distance between the participants. The door will not automatically open until the claim is confirmed the separation between the key fob and the vehicle. Numerous keyless entry systems and car immobilizer attacks make an effort to compromise the cryptographic protocols. Enhancing the authentication process is one option. Therefore, emerging remote keyless entry (RKE) processes should employ a more protected key distribution and cryptographic algorithm scheme.

5.2.3. Defence Approaches for In-Vehicle Protocols

Encrypting data during transmission is one of the key methods for enhancing the safety of bus communications. Asymmetric and asymmetric encryption-based communication systems for automobiles should be used with cryptographic approaches to ensure excellent performance and adequate security [47]. Stop code tampering and data sniffing by using methods like encryption and obfuscation. Proper and economic protection from reverse engineering is obfuscation. To successfully encrypt the data link between both the external memory and the ECU’s internal memory, additionally, on-the-fly decryption is used. Finally, encrypting and authenticating data with AES-128 combined with keyed hash MAC could decrease the bus load.
Automotive Open System Architecture is a consideration for MAC. Attackers cannot send unauthorized CAN signals because they lack the authentication key. The MAC assault, however, is utilized. The error frame transmission can also be used to halt unauthorized CAN messages. The fundamental notion is that if a node discovers any unauthorized messages, it should immediately send an error frame to replace them. and prevent the receiving node from receiving them. Gateway is a well-liked and trustworthy type of defense, the system’s motor bus entrance. A backbone-based architecture has now replaced the central gateway-based architecture of the in-vehicle system. The gateway handles error protection, message verification, and protocol conversion in addition to carrying the message from numerous ECUs [48].

5.3. Traditional Security Devices

The research on how human drivers might react to cyberattacks on autonomous vehicles carried out in a driving simulator sheds light on the difficulties and dangers that may arise from using these vehicles. The participant’s ability to continue driving and regain control of the car while being attacked by cybercriminals was evaluated throughout the experiment. In addition, the participants’ situational awareness during a cyberattack was assessed to demonstrate the seriousness of this kind of risk to autonomous vehicles. Similarly, the findings of prior studies on cyberattacks against autonomous vehicles were validated by the research. The participant’s reactions to potential cyberattacks on the vehicle and the infrastructure were evaluated, and specific cyberattacks that could occur on currently available vehicle technology were identified.
In the context of the 5G IoV, many proposed security solutions will be the most effective remedies against the assaults that could be launched. Some strategies are successful, while others are not. Even though the suggested approaches have a high success rate, the effort required to implement them can be a significant obstacle to their widespread application. Despite this, the ecosystem for 5G IoV still requires these security solutions because of their reliability in protecting against cyberattacks [49][50].
Operations research on autonomous driving and decision support systems gains significant knowledge from the research [51]. Increasing the highly automated car market raises three significant issues. Weather, traffic, cybersecurity concerns, and the ADS’ human aspect all contribute to these issues. Second, the study emphasizes the human factor when automated and human-driven cars interact. MV and ADS drivers’ skills and preferences affect transportation network efficiency. The ADS needs cognition to handle driving modes and interact with all relevant parties.

5.4. Threat Modeling Approaches

The scholars modeled the hostile environment by using SPICE to observe how the transmission line and the parasitic capacitance of the FETs in the transceiver affected the signal. Their goal was to determine whether or not these factors affected the signal. After performing a detailed schematic analysis, the CAN transceivers were modeled with the help of realistic channel and n-channel MOSFETs [52]. The two most important contributions the study makes are an adaptation of the TMT that makes it applicable to automotive threat modeling and a demonstration of the actual application of the approach to the identification of security threats in the control unit of a vehicle. Both of these are presented here [53]. Electronic Control Units (ECUs), sensors, and inter-vehicle communications were the primary areas of concentration for the authors of the article as they offered an in-depth analysis of these components in relation to autonomous vehicles.
Attacks on and defenses against autonomous cars are organized by time period to show technology evolution. An overview of 15 research papers from 2008 to 1029 on autonomous vehicle assaults and reactions is available. A full examination of autonomous vehicle attacks shows that future attacks will target vehicle-to-everything (V2X) communication technology rather than other vehicle components. Autonomous vehicle security research involves using artificial intelligence and big data to protect them [54]. 

5.5. Authentication Schemes

The security and integrity of the vehicle’s control systems and the safety of the passengers and other road users depend on authentication techniques in autonomous vehicles. Authentication procedures ensure that only approved systems and software are operating on the vehicle to avoid unauthorized access or modifications jeopardizing the car’s safety. Autonomous vehicles are susceptible to cyberattacks, including man-in-the-middle, denial-of-service, and spoofing [55]. By confirming the vehicle’s identity and the veracity of messages, authentication techniques can assist in defending against these kinds of assaults. By limiting access to the vehicle’s control systems or personal data to only those permitted, biometric-based authentication schemes can be utilized to protect passengers’ privacy. By enabling vehicles to confirm the identification of other vehicles and trust the information they receive, such as traffic and weather conditions, can increase road safety. To enable secure communication between vehicles and between vehicles and infrastructure, such as traffic lights, toll booths, and parking garages, authentication systems are crucial [56].

5.6. Over-The-Air (OTA) Updates

This solution enables wireless updates to the vehicle’s control systems that are secure and authenticated. Similar to how smartphones and other connected devices receive updates, autonomous vehicles can download and install software remotely with OTA updates [57]. Bug fixes, security patches, and new features or capabilities can all be included in these upgrades. OTA updates are crucial for autonomous vehicles because they enable ongoing system maintenance and enhancement without requiring the car to be physically taken in for servicing. Additionally, in the event of a security vulnerability or other problem, OTA updates can be utilized to distribute and deploy necessary updates rapidly. Article [58] created a framework that successfully distinguishes between harmful and benign software executables. Windows and Linux operating system executables were collected to create two datasets for testing and training. They supported transfer learning by utilizing the created CNN models to identify dangerous executables created for autonomous vehicles.
The security of the OTA update process is one of the primary issues since it necessitates a safe and impenetrable way of confirming the validity and integrity of the update. It is crucial to have a strong authentication system in place since an attacker could tamper with the update and harm the user or the car. For OTA updates to function correctly, a dependable and consistent Internet connection may not be accessible in all locations or at all times.

5.7. Zero-Trust Architecture

A zero-trust architecture for AVs can provide a secure and scalable solution for the security of connected vehicles, and it can help promote the widespread adoption and deployment of these technologies. To reduce the hazards associated with conventional centralized systems, a decentralized and secure communication infrastructure for automobiles has been proposed in ref. [59]. The zero-trust architecture is founded on the ideas of safe data transfer and secure device management, and it is made to give car owners and passengers more security and privacy. A cryptographic protocol system enables safe communication between vehicles and between vehicles and other systems, such as secure pairing and authentication. To guarantee the validity and integrity of the software running on automobiles, they also advocate the usage of secure software updates.
Next-generation cars can benefit from zero-trust architecture’s security and scalability, and it has the potential to become a pillar of connected vehicle security. In addition to helping to encourage the widespread acceptance and deployment of these technologies, the proposed design can be crucial in reducing the dangers related to autonomous vehicles and the Internet of Things [60][61].

6. Forensics Approaches

6.1. Forensic Tools

Digital forensics in cloud computing involves the investigation of digital evidence related to a particular incident, such as a cyber-attack, data breach, or another security incident, in a cloud computing environment. In cloud computing, data and services are stored and accessed remotely, making investigations more complex and challenging. Data collection methods include using tools (like those used to track file activity), artifacts (such as virtual machine images), & logs (e.g., audit logs). Keeping the data secure is the responsibility of the storage activity, while the management activity conducts a forensics investigation and information extraction for reconstructing the incident’s timeline [62].

6.2. Forensics Standards for Autonomous Vehicles

Autonomous, connected vehicles operate without human interaction, relying on onboard sensor computations. However, CAV decision-making could go wrong for various reasons, resulting in undesirable events. The connected autonomous driving compliance safety rules are now only possible with a solid forensic investigative framework or standard. NIST has been working to develop the framework for interoperability standards for CAVs and other intelligent transportation systems. ISO/IEC 27037 is the sole forensics standard for processing digital data. The standard outlines procedures for identifying, gathering, acquiring, and storing any digital evidence that could be crucial to a legal proceeding [63].
There currently needs to be widely accepted standards for autonomous vehicle forensics. However, several organizations and initiatives are working to develop guidelines and best practices for investigating incidents involving autonomous vehicles. The NIST has developed a research program to provide standards and best practices for automated vehicles’ reliable and secure operation. The program addresses privacy, security, safety, and ethical considerations in designing and using autonomous systems. In addition, The National Highway Traffic Safety Administration (NHTSA) is a U.S. government agency responsible for regulating and enforcing safety standards for automobiles and other motor vehicles. It includes the testing and deploying of autonomous vehicles with recommendations for data recording and retention in the event of a crash. The guidelines also emphasize the importance of cooperation between the vehicle manufacturer and relevant authorities in the event of an incident. The SAE has also published standards for autonomous vehicles, including data logging and retention recommendations. The standards are intended to ensure the reliable and consistent operation of autonomous cars and to give investigators a framework for analyzing accidents involving these vehicles. As the use of autonomous vehicles continues to grow, additional standards and guidelines will likely be developed to address specific issues related to autonomous vehicle forensics. However, at this time, there are yet to be widely accepted standards for this field. The digital forensics factors are the two components of a framework created for managing DFR [64].

6.3. Forensics Challenges in Autonomous Vehicles

Communications between vehicles, infrastructure, networks, and pedestrians are part of the dynamic ecosystem that makes up an autonomous vehicle (V2V, V2I, V2N, and V2P). It is a more challenging setting than other IoT systems because it includes mobile restrictions, a huge network scale, non-uniform node distribution, and dynamic topological structures [65]. CAVs are complex systems that hold much digital data, including sensitive personal data, which presents various challenges. Data are transferred through buses for internal communication stored in physical memory, and external network connection is saved in the cloud. Many components for communication and storage result in a need for more norms and frameworks for CAV forensics, and the complicated requirements and design of CAVs prevent the use of traditional digital forensic techniques. It is important to note that autonomous vehicle forensics is a rapidly evolving field, and technical and legal challenges may be associated with accessing and analyzing the data generated by these vehicles. However, as autonomous vehicles become increasingly widespread, the importance of autonomous vehicle forensics is likely to grow, and it will become increasingly important to develop standard practices and techniques for investigating incidents involving these vehicles [66].

7. Simulators

7.1. CARLA

Intel Labs created the open-source CARLA (Car Learning to Act) simulator for research on autonomous vehicles. It offers a highly detailed and realistic urban environment for testing and developing autonomous vehicles and other agents like pedestrians and bicycles. The simulator has a lot of features, including:
  • A sizable, intricate urban area including streets, buildings, traffic lights, and other elements typical of cities.
  • Realistic lighting and weather conditions, including varying day lengths, seasons, and weather phenomena like snow, rain, and fog [67].
  • Support for various sensors, including LiDAR, radar, and cameras, which may be set up to imitate various sensor kinds and noise levels.
  • A scenario system that is flexible and adaptable, enabling developers to generate and test a variety of situations, including various traffic densities, driving behaviors, and weather conditions.
  • A Python API that makes it simple for developers to build custom agents and behaviors and control and interact with the simulation [68].
  • Support for the Open DRIVE format enables simulation developers to import actual road networks.
  • Support for the Unreal Engine enables physics-based interactions between agents and realistic graphics.

7.2. Apollo

Baidu created the open-source Apollo platform for autonomous vehicles. It has various resources and technologies, including a simulator, for the research and development of autonomous vehicles. The following elements are part of the Apollo platform
  • The Apollo Simulator is a physics-based, highly realistic simulator that may be used to test and create autonomous vehicle systems. It supports several sensors, including LiDAR, radar, and cameras, and contains a variety of realistic landscapes [69].
  • Perception is a module collection that analyzes sensor data and identifies environmental items such as lane markers, traffic lights, and other cars.
  • Planning is a collection of modules for creating plans for the vehicle’s motion, such as trajectory and path planning.
  • Control, A group of modules that carry out instructions and manage the vehicle’s motion, including low-level steering, throttle, and braking controllers [70].
  • HD Map is a high-definition map that can give the car precise information about its surroundings, such as the road’s geometry, lane markings, and traffic lights.
  • Cybersecurity is a collection of modules to protect autonomous vehicle systems against cyberattacks.
  • Cloud-based services is a group of cloud-based services that can be used to remotely access the car and store and exchange data [19].

7.3. AirSim

Microsoft created the AirSim simulator, which focuses on drones and other aerial vehicles but can also be applied to ground vehicles. The Unreal Engine, the foundation of this open-source simulator, enables realistic graphics and physics-based interactions [71]. It offers a variety of characteristics that help design and test autonomous systems, such as:
  • Realistic settings is an AirSim that offers a range of settings, such as urban, rural, and natural settings, which can be utilized to assess the effectiveness of autonomous systems in various contexts [71].
  • AirSim supports cameras, LiDAR, and GPS sensors, which can be set up to simulate various sensor kinds and noise levels.
  • Interactions that are based on physics: AirSim models the physics of flight, including wind, turbulence, and other elements that may have an impact on how well aerial vehicles perform.
  • AirSim enables programmers to design and test various scenarios, including weather, illumination, and traffic density conditions [72].
  • AirSim offers a Python API that makes it simple for developers to build, manage, and interact with the simulation [73].
  • AirSim allows testing of fleet-based or swarm-based systems by simulating many vehicles simultaneously.

7.4. Gazebo

A 3D physics-based environment is provided by the open-source robot simulator Gazebo for testing and developing robotic systems. The Open Source Robotics Foundation (OSRF) created it, and the Gazebo community currently looks after its upkeep [74]. It may be used to model various robotic systems, including manipulator arms, aircraft, and ground vehicles. The following are some of the main aspects of Gazebo:
  • Gazebo models 3D physics-based simulations such as robotic system dynamics, including the impact of gravity, friction, and collisions.
  • It features a range of settings, including urban, rural, and natural ones, which can be used to assess how well robotic systems function in various contexts [74].
  • It features support for cameras, LiDAR, and GPS sensors, which may be customized to imitate a variety of sensor kinds and noise levels.
  • With Gazebo, developers can design and test a variety of situations, such as those with varying weather, lighting, and traffic volumes.
  • It has C++, Python, and MATLAB APIs that make it simple for developers to build, manage, and interact with the simulation [75].
  • Simulating numerous robots at once is supported by Gazebo, which makes it possible to test swarm- or fleet-based systems.
  • Gazebo offers a plugin architecture that enables programmers to design unique plugins to provide new features or alter the simulation’s behavior.

7.5. SUMO

An open-source traffic simulation tool that may be used to model and simulate traffic in urban settings is called SUMO (Simulation of Urban Mobility). The SUMO community maintains it after being created by the German Aerospace Center (DLR). SUMO can simulate various traffic situations involving automobiles, buses, bicycles, and pedestrians. Public transportation systems like trains and buses can also be modeled using it. SUMO has several important components, including
  • SUMO replicates individual vehicle movement on the road network while considering traffic lights, signs, and other traffic regulations.
  • It contains a range of settings, such as urban, suburban, and rural settings, which can be utilized to test the effectiveness of traffic systems in various contexts [76].
  • Simulating a wide range of traffic scenarios with support for diverse vehicle kinds, traffic densities, and traffic patterns is possible with SUMO.
  • It offers C++, Python, and Java APIs that make it simple for developers to build, manage, and interact with the simulation [77].
  • It is capable of simulating a variety of forms of transportation, including trains, buses, bicycles, and pedestrians, in addition to automobiles and buses.
  • SUMO has a plugin architecture that enables programmers to build unique plugins to include new features or alter the simulation’s behavior.
Critical Analysis: Simulators can only partially replicate the complexity and variability of the real world. Simulators may not be able to fully replicate the behavior of other road users or the exact conditions of the road surface. Also, simulators cannot replicate the unexpected events in the real world.

8. International Standards and Guidelines

Following ISO 21448, called SOTIF (Safety of the Intended Functionality), autonomous vehicles must meet certain functional safety requirements. It contains requirements for risk assessment and management, as well as the handling of sensor data and the management of vehicle systems citeschnellbach2019development. It covers the full lifespan of the vehicle, from design and development to testing and operation. Guidelines for the cybersecurity of autonomous vehicles are provided by ISO/SAE 21434, commonly known as Cybersecurity Engineering for Road Vehicles. It contains requirements for risk assessment and management, as well as the handling of sensor data and the management of vehicle systems [78]. It covers the full lifespan of the vehicle, from design and development to testing and operation.
Best Practices for Automated Vehicle Cybersecurity from NHTSA: The National Highway Traffic Safety Administration (NHTSA) has released rules for the cybersecurity of autonomous vehicles in this document. Risk assessment, threat modeling, and incident response are only a few areas it addresses [79]. This standard, SAE J3061, offers recommendations for the cybersecurity of autonomous cars. It contains requirements for risk assessment and management, the handling of sensor data, and the management of vehicle systems [80]. It covers the whole vehicle life cycle, from design and development to testing and operation.
Guidelines for creating and using control systems for automated vehicles are outlined in PAS 1880:2020. The publication offers comprehensive instructions on how to carry out autonomous vehicle testing, including on- and off-road testing and testing using simulations, as shown in Figure 7.
Technologies 11 00117 g012
Figure 7. International Standards and Guidelines.

8.1. Guidelines for Improving AVs Security

The possible repercussions of security failures or breaches make protecting autonomous vehicles (AVs) crucial. Many sensitive data are gathered, processed, and transmitted by the sophisticated systems built into AVs, including personal data, navigational data, and real-time traffic data [81]. Here are some general pointers for enhancing the security of autonomous vehicles:
  • Protect the software and hardware components by ensuring that every piece of hardware and software has been properly tested for vulnerabilities and developed with security in mind.
  • Encrypt all data: To avoid unauthorized access or theft, any data sent through the vehicle or kept there should be encrypted.
  • Watch over and restrict access: Establish rigorous access restrictions and keep a close eye on all communications going to and coming from the vehicle. Update software frequently: Update the software frequently to repair flaws and enhance security features.
  • Implement cybersecurity measures: To identify and stop cyberattacks, employ cybersecurity measures such as firewalls and intrusion detection systems [82].
  • Conduct penetration testing: To find and fix system vulnerabilities, conduct penetration testing regularly.
  • Plan for response and recovery: Create a thorough response strategy that addresses reporting events and restoring systems during a security breach.
  • Users should be informed about the value of security and the best practices for operating the vehicle safely and securely.

8.2. Guidelines for End Users

End users can reduce the danger of accidents or mishaps by following guidelines that assure autonomous vehicles’ safe and secure use. Here are some recommendations for autonomous car users:
  • Before using the vehicle, familiarize yourself with the operating instructions and safety precautions by reading the manual.
  • Recognize the vehicle’s limitations: Autonomous vehicles are not fault-proof and are still susceptible to errors. Be conscious of the vehicle’s capabilities and limitations at all times.
  • Know when to take control: In some circumstances, autonomous vehicles may ask you to take the wheel. Knowing when and how to drive safely while doing so is crucial [83].
  • Always buckles up: Even if you are not driving, buckle up when you ride in an autonomous car.
  • Update the vehicle’s software frequently to guarantee that you have access to the most recent security and safety features.
  • Avoid attempting to modify or meddle with the vehicle’s systems because doing so could harm the vehicle’s performance and safety [82].
  • Inform the manufacturer or your local authorities immediately if you experience any problems or issues with the car.
  • Prepare for crises by becoming familiar with your vehicle’s emergency protocols and being ready to act if necessary [84].

9. Conclusions

One of the key benefits of AVs is their potential to reduce accidents and save lives significantly. With advanced sensors, machine-learning algorithms, and sophisticated control systems, AVs can detect and respond to potential hazards faster and more accurately than human drivers. This has the potential to greatly reduce the number of accidents on our roads and save countless lives. In addition to safety benefits, AVs offer increased efficiency and reduced traffic congestion. By communicating with each other and the surrounding infrastructure, AVs can optimize their routes and speed, reducing travel time and improving overall traffic flow. This has the potential to reduce the economic and environmental costs associated with congestion greatly. However, despite their many benefits, AVs pose significant challenges that must be addressed before becoming a reality. One of the most significant challenges is the need for robust standards to ensure the safety and reliability of AVs. This includes developing clear guidelines for AV testing and deployment and establishing regulations for the data and communication networks necessary to support AVs. In conclusion, autonomous vehicles represent a significant advancement in transportation technology that has the potential to bring about many benefits to society. However, their widespread adoption also poses significant challenges that must be addressed before AVs become a reality. These challenges include the need for robust standards, cybersecurity, threat modeling approaches, and the public health implications of AVs. Additionally, the paper highlights the importance of developing artificial intelligence techniques and forensics for AVs to ensure their safety and reliability.

This entry is adapted from the peer-reviewed paper 10.3390/technologies11050117

References

  1. Kim, S.; Shrestha, R. Security and Privacy in Intelligent Autonomous Vehicles. In Automotive Cyber Security; Springer: Berlin/Heidelberg, Germany, 2020; pp. 35–66.
  2. Saab, S.S.; Shen, D.; Orabi, M.; Kors, D.; Jaafar, R.H. Iterative learning control: Practical implementation and automation. IEEE Trans. Ind. Electron. 2021, 69, 1858–1866.
  3. Anita, E.M.; Jenefa, J. A survey on authentication schemes of VANETs. In Proceedings of the 2016 International Conference on Information Communication and Embedded Systems (ICICES), Chennai, India, 25–26 February 2016; pp. 1–7.
  4. Cui, J.; Liew, L.S.; Sabaliauskaite, G.; Zhou, F. A review on safety failures, security attacks, and available countermeasures for autonomous vehicles. Ad Hoc Netw. 2019, 90, 101823.
  5. Wuthishuwong, C.; Traechtler, A. Vehicle to infrastructure based safe trajectory planning for Autonomous Intersection Management. In Proceedings of the 2013 13th international conference on ITS telecommunications (ITST), Tampere, Finland, 5–7 November 2013; pp. 175–180.
  6. Agrawal, S.; Elger, G. Concept of infrastructure based environment perception for in2lab test field for automated driving. In Proceedings of the 2021 IEEE International Smart Cities Conference (ISC2), Manchester, UK, 7–10 September 2021; pp. 1–4.
  7. Liu, S.; Yu, B.; Tang, J.; Zhu, Y.; Liu, X. Communication challenges in infrastructure-vehicle cooperative autonomous driving: A field deployment perspective. IEEE Wirel. Commun. 2022, 29, 126–131.
  8. Akabane, A.T.; Immich, R.; Bittencourt, L.F.; Madeira, E.R.; Villas, L.A. Towards a distributed and infrastructure-less vehicular traffic management system. Comput. Commun. 2020, 151, 306–319.
  9. Lim, K.; Tuladhar, K.M. LIDAR: Lidar information based dynamic V2V authentication for roadside infrastructure-less vehicular networks. In Proceedings of the 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, 11–14 January 2019; pp. 1–6.
  10. Campbell, S.; O’Mahony, N.; Krpalcova, L.; Riordan, D.; Walsh, J.; Murphy, A.; Ryan, C. Sensor technology in autonomous vehicles: A review. In Proceedings of the 2018 29th Irish Signals and Systems Conference (ISSC), Belfast, UK, 21–22 June 2018; pp. 1–4.
  11. Olaverri-Monreal, C. Autonomous vehicles and smart mobility related technologies. Infocommun. J. 2016, 8, 17–24.
  12. Rossi, F.; Zhang, R.; Hindy, Y.; Pavone, M. Routing autonomous vehicles in congested transportation networks: Structural properties and coordination algorithms. Auton. Robot. 2018, 42, 1427–1442.
  13. Abbas, A.; Krichen, M.; Alroobaea, R.; Malebary, S.; Tariq, U.; Jalil Piran, M. An opportunistic data dissemination for autonomous vehicles communication. Soft Comput. 2021, 25, 11899–11912.
  14. Ahmed, M.L.; Iqbal, R.; Karyotis, C.; Palade, V.; Amin, S.A. Predicting the public adoption of connected and autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 2021, 23, 1680–1688.
  15. Acheampong, R.A.; Cugurullo, F. Capturing the behavioural determinants behind the adoption of autonomous vehicles: Conceptual frameworks and measurement models to predict public transport, sharing and ownership trends of self-driving cars. Transp. Res. Part F Traffic Psychol. Behav. 2019, 62, 349–375.
  16. Golbabaei, F.; Yigitcanlar, T.; Paz, A.; Bunker, J. Individual predictors of autonomous vehicle public acceptance and intention to use: A systematic review of the literature. J. Open Innov. Technol. Mark. Complex. 2020, 6, 106.
  17. Lavasani, M.; Jin, X.; Du, Y. Market penetration model for autonomous vehicles on the basis of earlier technology adoption experience. Transp. Res. Rec. 2016, 2597, 67–74.
  18. Choi, J.K.; Ji, Y.G. Investigating the importance of trust on adopting an autonomous vehicle. Int. J. Hum.-Comput. Interact. 2015, 31, 692–702.
  19. Garcia, D.; Kreutzer, C.; Badillo-Urquiola, K.; Mouloua, M. Measuring trust of autonomous vehicles: A development and validation study. In Proceedings of the HCI International 2015-Posters’ Extended Abstracts: International Conference, HCI International 2015, Los Angeles, CA, USA, 2–7 August 2015; Proceedings, Part II 17. Springer: Berlin/Heidelberg, Germany, 2015; pp. 610–615.
  20. Dirsehan, T.; Can, C. Examination of trust and sustainability concerns in autonomous vehicle adoption. Technol. Soc. 2020, 63, 101361.
  21. Legacy, C.; Ashmore, D.; Scheurer, J.; Stone, J.; Curtis, C. Planning the driverless city. Transp. Rev. 2019, 39, 84–102.
  22. Shatu, F.; Kamruzzaman, M. Planning for active transport in driverless cities: A conceptual framework and research agenda. J. Transp. Health 2022, 25, 101364.
  23. Fox, S.J. Planning for density in a driverless world. NEULJ 2017, 9, 151.
  24. González-González, E.; Cordera, R.; Stead, D.; Nogués, S. Envisioning the driverless city using backcasting and Q-methodology. Cities 2023, 133, 104159.
  25. Wagner, P. Traffic control and traffic management in a transportation system with autonomous vehicles. Auton. Driving Tech. Leg. Soc. Asp. 2016, 301–316.
  26. Gora, P. Simulation-based traffic management system for connected and autonomous vehicles. In Road Vehicle Automation 4; Springer: Berlin/Heidelberg, Germany, 2018; pp. 257–266.
  27. Kopelias, P.; Demiridi, E.; Vogiatzis, K.; Skabardonis, A.; Zafiropoulou, V. Connected & autonomous vehicles–Environmental impacts–A review. Sci. Total Environ. 2020, 712, 135237.
  28. Rojas-Rueda, D.; Nieuwenhuijsen, M.; Khreis, H. Autonomous vehicles and public health: Literature review. J. Transp. Health 2017, 5, S13.
  29. Basma, H.; Halaby, H.; Radwan, A.B.; Mansour, C. Design of optimal rule-based controller for plug-in series hybrid electric vehicle. In Proceedings of the 32nd International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, Wroclaw, Poland, 23–28 June 2019.
  30. Kontar, W.; Ahn, S.; Hicks, A. Autonomous vehicle adoption: Use phase environmental implications. Environ. Res. Lett. 2021, 16, 064010.
  31. Khoury, J.; Khoury, J.; Zouein, G.; Arnaout, J.P. A practical decentralized access protocol for autonomous vehicles at isolated under-saturated intersections. J. Intell. Transp. Syst. 2019, 23, 427–440.
  32. Rojas-Rueda, D.; Nieuwenhuijsen, M.J.; Khreis, H.; Frumkin, H. Autonomous vehicles and public health. Annu. Rev. Public Health 2020, 41, 329–345.
  33. Mchergui, A.; Moulahi, T.; Zeadally, S. Survey on artificial intelligence (AI) techniques for vehicular ad hoc networks (VANETs). Veh. Commun. 2022, 34, 100403.
  34. Javed, A.R.; Usman, M.; Rehman, S.U.; Khan, M.U.; Haghighi, M.S. Anomaly detection in automated vehicles using multistage attention-based convolutional neural network. IEEE Trans. Intell. Transp. Syst. 2020, 22, 4291–4300.
  35. Yaqoob, I.; Khan, L.U.; Kazmi, S.A.; Imran, M.; Guizani, N.; Hong, C.S. Autonomous driving cars in smart cities: Recent advances, requirements, and challenges. IEEE Netw. 2019, 34, 174–181.
  36. Liu, S.; Liu, L.; Tang, J.; Yu, B.; Wang, Y.; Shi, W. Edge computing for autonomous driving: Opportunities and challenges. Proc. IEEE 2019, 107, 1697–1716.
  37. Masood, A.; Lakew, D.S.; Cho, S. Security and privacy challenges in connected vehicular cloud computing. IEEE Commun. Surv. Tutor. 2020, 22, 2725–2764.
  38. Xia, X.; Meng, Z.; Han, X.; Li, H.; Tsukiji, T.; Xu, R.; Zheng, Z.; Ma, J. An Automated Driving Systems Data Acquisition and Analytics Platform. Transp. Res. Part C Emerg. Technol. 2023, 151, 104120.
  39. Meng, Z.; Xia, X.; Xu, R.; Liu, W.; Ma, J. Hydro-3D: Hybrid Object Detection and Tracking for Cooperative Perception Using 3D Lidar. IEEE Trans. Intell. Veh. 2023.
  40. Sami, H.; Mourad, A.; Otrok, H.; Bentahar, J. Fscaler: Automatic resource scaling of containers in fog clusters using reinforcement learning. In Proceedings of the 2020 International Wireless Communications and Mobile Computing (IWCMC), Limassol, Cyprus, 15–19 June 2020; pp. 1824–1829.
  41. Shahzad, A.; Gherbi, A.; Zhang, K. Enabling Fog–Blockchain Computing for Autonomous-Vehicle-Parking System: A Solution to Reinforce IoT–Cloud Platform for Future Smart Parking. Sensors 2022, 22, 4849.
  42. Javed, A.R.; Hassan, M.A.; Shahzad, F.; Ahmed, W.; Singh, S.; Baker, T.; Gadekallu, T.R. Integration of blockchain technology and federated learning in vehicular (iot) networks: A comprehensive survey. Sensors 2022, 22, 4394.
  43. Psiaki, M.L.; Powell, S.P.; O’Hanlon, B.W. GNSS spoofing detection using high-frequency antenna motion and carrier-phase data. In Proceedings of the 26th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 2013), Nashville, TN, USA, 16–20 September 2013; pp. 2949–2991.
  44. Wesson, K.D.; Gross, J.N.; Humphreys, T.E.; Evans, B.L. GNSS signal authentication via power and distortion monitoring. IEEE Trans. Aerosp. Electron. Syst. 2017, 54, 739–754.
  45. Lim, K.; Islam, T.; Kim, H.; Joung, J. A Sybil attack detection scheme based on ADAS sensors for vehicular networks. In Proceedings of the 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, 10–13 January 2020; pp. 1–5.
  46. Zhou, M.; Qin, Z.; Lin, X.; Hu, S.; Wang, Q.; Ren, K. Hidden voice commands: Attacks and defenses on the VCS of autonomous driving cars. IEEE Wirel. Commun. 2019, 26, 128–133.
  47. Cao, Y.; Xiao, C.; Cyr, B.; Zhou, Y.; Park, W.; Rampazzi, S.; Chen, Q.A.; Fu, K.; Mao, Z.M. Adversarial sensor attack on lidar-based perception in autonomous driving. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, London, UK, 11–15 November 2019; pp. 2267–2281.
  48. Sheehan, B.; Murphy, F.; Mullins, M.; Ryan, C. Connected and autonomous vehicles: A cyber-risk classification framework. Transp. Res. Part A Policy Pract. 2019, 124, 523–536.
  49. Saber, O.; Mazri, T. Security of Autonomous Vehicles: 5g Iov (internet of Vehicles) Environment. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2022, 48, 157–163.
  50. Hasan, M.K.; Islam, S.; Gadekallu, T.R.; Ismail, A.F.; Amanlou, S.; Abdullah, S.N.H.S. Novel EBBDSA based Resource Allocation Technique for Interference Mitigation in 5G Heterogeneous Network. Comput. Commun. 2023, 209, 320–330.
  51. Sajid, F.; Javed, A.R.; Basharat, A.; Kryvinska, N.; Afzal, A.; Rizwan, M. An efficient deep learning framework for distracted driver detection. IEEE Access 2021, 9, 169270–169280.
  52. Ma, Z.; Schmittner, C. Threat modeling for automotive security analysis. Adv. Sci. Technol. Lett. 2016, 139, 333–339.
  53. Mohammed, A.Z.; Man, Y.; Gerdes, R.; Li, M.; Celik, Z.B. Physical layer data manipulation attacks on the can bus. In Proceedings of the Intl. Workshop on Automotive and Autonomous Vehicle Security (AutoSec), Online, 24–28 April 2022.
  54. Kim, K.; Kim, J.S.; Jeong, S.; Park, J.H.; Kim, H.K. Cybersecurity for autonomous vehicles: Review of attacks and defense. Comput. Secur. 2021, 103, 102150.
  55. Manvi, S.S.; Tangade, S. A survey on authentication schemes in VANETs for secured communication. Veh. Commun. 2017, 9, 19–30.
  56. Du, X.; Htet, K.K.K.; Tan, K.K. Development of a genetic-algorithm-based nonlinear model predictive control scheme on velocity and steering of autonomous vehicles. IEEE Trans. Ind. Electron. 2016, 63, 6970–6977.
  57. Khatun, M.; Glaß, M.; Jung, R. An approach of scenario-based threat analysis and risk assessment over-the-air updates for an autonomous vehicle. In Proceedings of the 2021 7th International Conference on Automation, Robotics and Applications (ICARA), Prague, Czech Republic, 4–6 February 2021; pp. 122–127.
  58. Qureshi, A.; Marvi, M.; Shamsi, J.A.; Aijaz, A. eUF: A framework for detecting over-the-air malicious updates in autonomous vehicles. J. King Saud-Univ.-Comput. Inf. Sci. 2021, 34, 5456–5467.
  59. Kondaveety, V.B.; Lamkuche, H.; Prasad, S. A zero trust architecture for next generation automobiles. AIP Conf. Proc. 2022, 2519, 030088.
  60. Alipour, M.A.; Ghasemshirazi, S.; Shirvani, G. Enabling a Zero Trust Architecture in a 5G-enabled Smart Grid. arXiv 2022, arXiv:2210.01739.
  61. Lian, Z.; Zeng, Q.; Wang, W.; Gadekallu, T.R.; Su, C. Blockchain-based two-stage federated learning with non-IID data in IoMT system. IEEE Trans. Comput. Soc. Syst. 2022, 10, 1701–1710.
  62. Alexakos, C.; Katsini, C.; Votis, K.; Lalas, A.; Tzovaras, D.; Serpanos, D. Enabling digital forensics readiness for internet of vehicles. Transp. Res. Procedia 2021, 52, 339–346.
  63. Yang, G.; Xue, Y.; Meng, L.; Wang, P.; Shi, Y.; Yang, Q.; Dong, Q. Survey on autonomous vehicle simulation platforms. In Proceedings of the 2021 8th International Conference on Dependable Systems and Their Applications (DSA), Yinchuan, China, 5–6 August 2021; pp. 692–699.
  64. Elyas, M.; Maynard, S.B.; Ahmad, A.; Lonie, A. Towards a systemic framework for digital forensic readiness. J. Comput. Inf. Syst. 2014, 54, 97–105.
  65. Sun, Y.; Wu, L.; Wu, S.; Li, S.; Zhang, T.; Zhang, L.; Xu, J.; Xiong, Y.; Cui, X. Attacks and countermeasures in the internet of vehicles. Ann. Telecommun. 2017, 72, 283–295.
  66. Sharma, P.; Gillanders, J. Cybersecurity and Forensics in Connected Autonomous Vehicles: A Review of the State-of-the-Art. IEEE Access 2022, 10, 108979–108996.
  67. Vivan, G.P.; Goberville, N.; Asher, Z.D.; Brown, N.; Rojas, J.F. No Cost Autonomous Vehicle Advancements in CARLA through ROS; SAE International: Warrendale, PA, USA, 2021.
  68. Pérez-Gil, Ó.; Barea, R.; López-Guillén, E.; Bergasa, L.M.; Gomez-Huelamo, C.; Gutiérrez, R.; Diaz-Diaz, A. Deep reinforcement learning based control for Autonomous Vehicles in CARLA. Multimed. Tools Appl. 2022, 81, 3553–3576.
  69. Bojarski, M.; Del Testa, D.; Dworakowski, D.; Firner, B.; Flepp, B.; Goyal, P.; Zhang, X. End to end learning for self-driving cars. arXiv 2016, arXiv:1604.07316.
  70. Dai, F.; Chen, M.; Wei, X.; Wang, H. Swarm intelligence-inspired autonomous flocking control in UAV networks. IEEE Access 2019, 7, 61786–61796.
  71. Shah, S.; Dey, D.; Lovett, C.; Kapoor, A. Airsim: High-fidelity visual and physical simulation for autonomous vehicles. In Proceedings of the Field and Service Robotics: Results of the 11th International Conference; Springer: Berlin/Heidelberg, Germany, 2018; pp. 621–635.
  72. Bondi, E.; Dey, D.; Kapoor, A.; Piavis, J.; Shah, S.; Fang, F.; Dilkina, B.; Hannaford, R.; Iyer, A.; Joppa, L.; et al. Airsim-w: A simulation environment for wildlife conservation with uavs. In Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies, Menlo Park and San Jose, CA, USA, 20–22 June 2018; pp. 1–12.
  73. Yao, S.; Zhang, J.; Hu, Z.; Wang, Y.; Zhou, X. Autonomous-driving vehicle test technology based on virtual reality. J. Eng. 2018, 2018, 1768–1771.
  74. Koenig, N.; Howard, A. Design and use paradigms for gazebo, an open-source multi-robot simulator. In Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)(IEEE Cat. No. 04CH37566), Sendai, Japan, 28 September–2 October 2004; Volume 3, pp. 2149–2154.
  75. Furrer, F.; Burri, M.; Achtelik, M.; Siegwart, R. Rotors—a modular gazebo mav simulator framework. Robot. Oper. Syst. (Ros) Complet. Ref. 2016, 1, 595–625.
  76. Krajzewicz, D. Traffic simulation with SUMO–simulation of urban mobility. Fundam. Traffic Simul. 2010, 145, 269–293.
  77. Krajzewicz, D.; Erdmann, J.; Behrisch, M.; Bieker, L. Recent development and applications of SUMO-Simulation of Urban MObility. Int. J. Adv. Syst. Meas. 2012, 5.
  78. Schmittner, C.; Griessnig, G.; Ma, Z. Status of the Development of ISO/SAE 21434. In Proceedings of the Systems, Software and Services Process Improvement: 25th European Conference, EuroSPI 2018, Bilbao, Spain, 5–7 September 2018; Proceedings 25. Springer: Berlin/Heidelberg, Germany, 2018; pp. 504–513.
  79. Martin, J.; Carter, A. Nhtsa cybersecurity research. In Proceedings of the 25th International Technical Conference on the Enhanced Safety of Vehicles (ESV) National Highway Traffic Safety Administration, Washington, DC, USA, 5 June 2017.
  80. Schmittner, C.; Ma, Z.; Reyes, C.; Dillinger, O.; Puschner, P. Using SAE J3061 for automotive security requirement engineering. In Proceedings of the Computer Safety, Reliability, and Security: SAFECOMP 2016 Workshops, ASSURE, DECSoS, SASSUR, and TIPS, Trondheim, Norway, 20 September 2016; Proceedings 35. Springer: Berlin/Heidelberg, Germany, 2016; pp. 157–170.
  81. Udayakumar, P. Manage and Secure AVS. In Design and Deploy Azure VMware Solutions: Build and Run VMware Workloads Natively on Microsoft Azure; Springer: Berlin/Heidelberg, Germany, 2022; pp. 341–387.
  82. Anderson, J.M.; Nidhi, K.; Stanley, K.D.; Sorensen, P.; Samaras, C.; Oluwatola, O.A. Autonomous Vehicle Technology: A Guide for Policymakers; Rand Corporation: Santa Monica, CA, USA, 2014.
  83. Abu Bakar, A.I.; Abas, M.A.; Muhamad Said, M.F.; Tengku Azhar, T.A. Synthesis of autonomous vehicle guideline for public road-testing sustainability. Sustainability 2022, 14, 1456.
  84. Mohsin, A.H.; Zaidan, A.; Zaidan, B.; Albahri, O.; Ariffin, S.A.B.; Alemran, A.; Enaizan, O.; Shareef, A.H.; Jasim, A.N.; Jalood, N.; et al. Finger vein biometrics: Taxonomy analysis, open challenges, future directions, and recommended solution for decentralised network architectures. IEEE Access 2020, 8, 9821–9845.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
Video Production Service
Feedback