A Review on Autonomous Vehicles: Progress, Methods and Challenges

Abstract

Vehicular technology has recently gained increasing popularity, and autonomous driving is a hot topic. To achieve safe and reliable intelligent transportation systems, accurate positioning technologies need to be built to factor in the different types of uncertainties such as pedestrian behavior, random objects, and types of roads and their settings. In this work, we look into the other domains and technologies required to build an autonomous vehicle and conduct a relevant literature analysis. In this work, we look into the current state of research and development in environment detection, pedestrian detection, path planning, motion control, and vehicle cybersecurity for autonomous vehicles. We aim to study the different proposed technologies and compare their approaches. For a car to become fully autonomous, these technologies need to be accurate enough to gain public trust and show immense accuracy in their approach to solving these problems. Public trust and perception of auto vehicles are also explored in this paper. By discussing the opportunities as well as the obstacles of autonomous driving technology, we aim to shed light on future possibilities.

A Spatiotemporal Calibration Algorithm for IMU–LiDAR Navigation System Based on Similarity of Motion Trajectories

“… Algorithm 1: LiDAR/IMU spatiotemporal calibration. Input: IMU set I [ 1 ], point cloud set P { P 1 , …, P N } Output: External spatial parameter T il, temporal parameter Δ t while (True) do Modeling Gyro measurement data set I i with B-splines Solving the motion between lidar frames by NDT algorithm Solving external parameters T il0 using hand–eye calibration Time offset Δ t 0 solving to minimize the Hausdorff distance Preintegration using IMU measurement for i = 1, …, K do Distortion correction of point cloud by initial calibration Construct IMU preintegration factor, lidar prior factor and lidar factor Perform nonlinear optimization on the data in the window to solve the state x i end end …”

“…It can fully use the advantages of different sensors, and they can then compensate each other, and achieve more accurate and robust perception and localization performance than that of a single sensor. Therefore, in recent years, it has received extensive attention, such as in driverless cars, field robots, high-precision map construction, and target tracking [ 1 , 2 , 3 , 4 ]. LiDAR is widely used in robot navigation due to its high measurement accuracy, insensitivity to light, and good reliability.…”

Radar Based Pedestrian Classification using Deep Learning Approach

“…Pedestrians play a crucial role in the rapidly evolving transportation sector brought on by technological advancements. The self-driving cars need a sensor that can pick up on foot traffic [1]. For this reason, developing these new technologies must concentrate on pedestrian safety.…”

Fractional mayfly optimization algorithm‐based Infrastructure‐to‐Vehicle and Vehicle‐to‐Vehicle scheduling for service message transmission in IoV‐fog

“…The vehicles transmit the messages by wireless communication 9–11 . Moreover, the vehicle can correspond with road side unit (RSU), which has a major function in offering routing as well as accessing the network for vehicles 12 . Recently, two major communication protocols are used in the IoV network, namely, cellular network‐based communication model and dedicated short‐range communication for vehicles 13 …”

“…[9][10][11] Moreover, the vehicle can correspond with road side unit (RSU), which has a major function in offering routing as well as accessing the network for vehicles. 12 Recently, two major communication protocols are used in the IoV network, namely, cellular network-based communication model and dedicated short-range communication for vehicles. 13 Vehicles in the IoV can perform incorporation of information as it helps to sustain the flow of traffic and to transmit efficient fleet management such that it can reduce the cause of accidents.…”