1
Artificial Intelligence in Autonomous Vehicles—A Survey of Trends and Challenges

Umamaheswari Rajasekaran, A. Malini* and Mahalakshmi Murugan

Thiagarajar College of Engineering, Madurai, India

Abstract

The potential for connected automated vehicles is multifaceted, and automated advancement deals with more of Internet of Things (IoTs) development enabling artificial intelligence (AI). Early advancements in engineering, electronics, and many other fields have inspired AI. There are several proposals of technologies used in automated vehicles. Automated vehicles contribute greatly toward traffic optimization and casualty reduction. In studying vehicle autonomy, there are two categories of development available: high-level system integrations like new-energy vehicles and intelligent transportation systems and the other involves backward subsystem advancement like sensor and information processing systems. The Advanced Driver Assistance System shows results that meet the expectations of real-world problems in vehicle autonomy. Situational intelligence that collects enormous amounts of data is considered for high-definition creation of city maps, land surveying, and quality checking of roads as well. The infotainment system of the transport covers the driver’s gesture recognition, language transaction, and perception of the surroundings with the assistance of a camera, Light Detection and Ranging (LiDAR), and Radio Detection And Ranging (RADAR) along with localization of the objects in the scene. This chapter discusses the history of autonomous vehicles (AV), trending research areas of artificial intelligence technology in AV, state-of-the-art datasets used for AV research, and several Machine Learning (ML)/Deep Learning (DL) algorithms constituting the functioning of AV as a system, concluding with the challenges and opportunities of AI in AV.

Keywords: Vehicle autonomy, artificial intelligence, situational intelligence, datasets, safety standards, network efficiency, algorithms

1.1 Introduction

An autonomous vehicle in simple terms is that its movements are from the start to predecided stop in “autopilot” mode. Autonomous vehicle technology is developed to provide several pros in comparison with human-driven transport. Increased safety on the road is one such potential primacy—connected vehicles could drastically decrease the number of casualties every year. The automated driving software is the most comfortable transport system that highly supports the class of people who could not drive because of age and physical constraints. Autonomous vehicles help them to find a new smart ideas, and it is predicted that it could provide them with different opportunities to work in fields that require driving. Automated decisions are taken without any human intervention, and the necessary actions are implemented to ensure stability of the system. The smart connected vehicles are supported by an AI-based self-driving system that responds to external conditions through the ability to sense their surroundings using Adaptive Driver Control (ADC) that uses lasers and radars enabled with ML and DL technologies. To extract object information from noisy sensor data, these components frequently employ machine learning (ML)-based algorithms. An understandable representation of autonomous vehicles as a system is shown in Figure 1.1.

The history of driverless cars took the spark from the year 1478 with Da Vinci creating the first driverless automobile prototype. In Da Vinci’s vehicle, there was a self-propelled robot that was driven by springs. It had programmable steering and could output predetermined routes. This brief history shows where the roots of artificial intelligence may be found in philosophy, literature, and the human imagination. Autonomous vehicles (AVs) were first conceptualized in the 1930s. It was the Houdina Radio Control project that demonstrated a radio-controlled “driverless” car. In the mid-20th century, General Motors took the initiative to develop a concept car called Firebird II. This was considered the basis for the first cruise control car named “Imperial” designed by the Chrysler company in 1958. Back in the 1990s, organizations slowly proceeded by considering safety measures including cruise and brake controls. After the turn of the century, blind-spot detection and electronic stability controls through sensors were made available in self-driven vehicles. One of the biggest achievements in the year 1995 was the VaMP-designed autonomous vehicle that drives (almost) by itself for 2,000 km. Between 1995 and 1998, the National AHS Consortium was held for cars followed by the PATH organization that conducted the automated bus and truck demos. In the year 2009, the Google Self-Driving Car Project began; eventually, Tesla Multinational Automotive released the update in autopilot software. Self-driving cars designed by Google, having met with a test drive accident in the year 2016, were considered a major damage to the development of AVs. At the end of 2016, the Bolt and Super Cruise in Cadillac have autonomous controls. At the start of January 2022, Volvo unveiled Ride Pilot, a new Level 3 autonomous driving technology, at the CES consumer electronics expo. Without human input, the system navigates the road using LiDAR, radar, ultrasonic sensors, and a 360-degree camera setup.

Figure 1.1 Representation of the AV system.

As of 2019, self-driven vehicles possess the following features: Free-hand handles the steering, but monitoring the system is also needed. With additional improvement in free-hand steering, the adaptive cruise control (ACC) keeps the vehicle at a predetermined displacement from the surrounding objects. When an interruption is encountered like the motorist crossing the lane, the car insists that the system slows down and changes the lane. One of the main problems with AV mobility is how to combine sensors and estimate circumstances to distinguish between risky scenarios and less dangerous ones. AV’s mobility is quite tedious, but continuous accepted releases in this field give better mobility to the vehicles. AI gives a fantastic change in the technological revolution. The Department of Transportation (DOT) and NHTSA deal with safety in addition to automation protocols. Section 1.2 of this chapter presents a detailed survey of machine learning and deep learning algorithms used in the AV literature where the important AV-pipeline activities are analyzed individually. Section 1.3 presents a survey of the state-of-the-art datasets used in autonomous vehicles, and Section 1.4 discusses the industry standards, risks, challenges, and opportunities, with Section 1.5 summarizing the analysis.

1.2 Research Trends of AI for AV

To provide readers a comprehensive picture of the status of the literature in AI on AV, the current research trends of ML/DL algorithms in the design of autonomous vehicles are presented.

The systems rely on several technological advancements in AI technicalities. When looking into the automation ideology in vehicles, it comprises six different levels. Starting from level 0, the human driver operates with no self-control in the cars. We could say that there is no self-working at level 0. At the first level, the Advanced Driver Assistance System (ADAS) in vehicles supports the driver with either accelerating or steering controls. In addition to level 1, the ADAS provides brake controls to the system such as Automated Emergency Braking System (AEBS). However, the driver must pay complete attention to the surroundings—level 2. At level 3, almost all automation processes are performed by the system, but driver’s access is required in certain operations. Real-time high-definition maps must be accessible, complete, and detailed. These maps are necessary, and they are used to decide their path and trajectory. Further development of level 3 is that the vehicle’s advanced driving system (ADS) provides complete automation without a human even if a person does not respond to a request in some circumstances. A vehicle’s six degrees of freedom are indicated by the stance, which is monitored by AV pose sensors: x, y, z, ϕ, θ, and ψ; here, x, y, and z depicts actual positions of the system at level 4. Eventually, at level 5, virtual chauffer concept is introduced by ADS along with ACC and does all the driving in all circumstances. Autonomous vehicles can be successfully implemented in a range of use case situations combining the complete working of sensors, actuators, maps, detectors, etc. It is necessary to demonstrate the functionalities in real-life environments like urban and rural developments combining smart vehicles.

LiDAR technology ensures the functional and safe operation of an autonomous vehicle. LiDAR is more efficient in creating 3D images of the surroundings that is considered critical in urban settings [1]. A rotating roof-mounted LiDAR sensor creates and maintains a live 3D map of a 60-m range of surroundings and thus generates a specific route for travel to the destination specified by the driver. Radars are mounted to measure the distance between obstructions and are placed at the front and rear. To determine the car’s position in the lane concerning the 3D map, a sensor on the left rear wheel tracks and signals the system’s sideway movement. All of the sensors are connected to the AI program, which receives the dataset in accordance. Thirdly, collaborative mapping efforts gather massive amounts of raw data at once utilizing GPS...