Search

Visual perception plays an important role in autonomous driving. One of the primary tasks is object detection and identification. Since the vision sensor is rich in color and texture information, it can quickly and accurately identify various road information. The commonly used technique is based on extracting and calculating various features of the image. The recent development of deep learning-based method has better reliability and processing speed and has a greater advantage in recognizing complex elements. For depth estimation, vision sensor is also used for ranging due to their small size and low cost. Monocular camera uses image data from a single viewpoint as input to estimate object depth. In contrast, stereo vision is based on parallax and matching feature points of different views, and the application of deep learning also further improves the accuracy. In addition, Simultaneous Location and Mapping (SLAM) can establish a model of the road environment, thus helping the vehicle perceive the surrounding environment and complete the tasks. In this paper, we introduce and compare various methods of object detection and identification, then explain the development of depth estimation and compare various methods based on monocular, stereo, and RDBG sensors, next review and compare various methods of SLAM, and finally summarize the current problems and present the future development trends of vision technologies., Comment: 39 pages, 17 figures

This paper reviews vision-based localization methods in GPS-denied environments and classifies the mainstream methods into Relative Vision Localization (RVL) and Absolute Vision Localization (AVL). For RVL, we discuss the broad application of optical flow in feature extraction-based Visual Odometry (VO) solutions and introduce advanced optical flow estimation methods. For AVL, we review recent advances in Visual Simultaneous Localization and Mapping (VSLAM) techniques, from optimization-based methods to Extended Kalman Filter (EKF) based methods. We also introduce the application of offline map registration and lane vision detection schemes to achieve Absolute Visual Localization. This paper compares the performance and applications of mainstream methods for visual localization and provides suggestions for future studies., Comment: 32 pages, 15 figures

Autonomous vehicles can enhance overall performance and implement safety measures in ways that are impossible with conventional automobiles. These functions are executed through vehicle control systems, which have been the subject of considerable research. Autonomous cars have a distinct advantage as they possess various perception sensors that can predict road surface conditions and other phenomena ahead of time. Many modern automotive control systems treat the road slope as a constant and do not account for changes in the road profile in their vehicle models. As a result, vehicle states may be miscalculated, which, in the worst-case scenario, may result in accidents. This is particularly true for high center-of-gravity vehicles like trailers and delivery trucks. With the help of perception sensors in autonomous vehicles, a road slope estimation system can be developed to aid these control systems in making informed decisions regarding the vehicle's state. The current review is divided into three logical steps that can be discussed in the following manner: the first section describes and reviews the individual steps for developing a road slope estimation system. The second one provides a detailed review of previous investigations that implemented different methods that employ this prediction system to improve overall vehicle performance. Finally, a roll control system is presented as an innovative idea that builds on the whole discussion. A rollover prevention system with prediction abilities is presented because (1) it proves to be a critical safety feature, especially for heavy vehicles like buses, trucks, delivery trailers, etc., and (2) not enough research has been conducted on technologies that integrate a roll stability controller with a slope estimation system., Comment: 16 pages, 15 figures

Delivery robots aim to achieve high precision to facilitate complete autonomy. A precise three-dimensional point cloud map of sidewalk surroundings is required to estimate self-location. With or without the loop closing method, the cumulative error increases gradually after mapping for larger urban or city maps due to sensor drift. Therefore, there is a high risk of using the drifted or misaligned map. This article presented a technique for fusing GPS to update the 3D point cloud and eliminate cumulative error. The proposed method shows outstanding results in quantitative comparison and qualitative evaluation with other existing methods., Comment: 10 pages, 11 figures

Autonomous driving has been among the most popular and challenging topics in the past few years. On the road to achieving full autonomy, researchers have utilized various sensors, such as LiDAR, camera, Inertial Measurement Unit (IMU), and GPS, and developed intelligent algorithms for autonomous driving applications such as object detection, object segmentation, obstacle avoidance, and path planning. High-definition (HD) maps have drawn lots of attention in recent years. Because of the high precision and informative level of HD maps in localization, it has immediately become one of the critical components of autonomous driving. From big organizations like Baidu Apollo, NVIDIA, and TomTom to individual researchers, researchers have created HD maps for different scenes and purposes for autonomous driving. It is necessary to review the state-of-the-art methods for HD map generation. This paper reviews recent HD map generation technologies that leverage both 2D and 3D map generation. This review introduces the concept of HD maps and their usefulness in autonomous driving and gives a detailed overview of HD map generation techniques. We will also discuss the limitations of the current HD map generation technologies to motivate future research., Comment: 25 pages, 17 figures, submitted to a journal

Perception and localization are essential for autonomous delivery vehicles, mostly estimated from 3D LiDAR sensors due to their precise distance measurement capability. This paper presents a strategy to obtain the real-time pseudo point cloud instead of the laser sensor from the image sensor. We propose an approach to use different depth estimators to obtain pseudo point clouds like LiDAR to obtain better performance. Moreover, the training and validating strategy of the depth estimator has adopted stereo imagery data to estimate more accurate depth estimation as well as point cloud results. Our approach to generating depth maps outperforms on KITTI benchmark while yielding point clouds significantly faster than other approaches., Comment: 9 pages, 5 figures

Hybrid energy storage systems that combine lithium-ion batteries and supercapacitors are considered as an attractive solution to overcome the drawbacks of battery-only energy storage systems, such as high cost, low power density, and short cycle life, which hinder the popularity of electric vehicles. A properly sized hybrid energy storage system and an implementable real-time power management system are of great importance to achieve satisfactory driving mileage and battery cycle life. However, dimensioning and power management problems are quite complicated and challenging in practice. To address these challenges, this work proposes a Bi-level multi-objective design and control framework with the non-dominated sorting genetic algorithm-II and fuzzy logic control as key components, to obtain an optimal sized hybrid energy storage system and the corresponding optimal real-time power management system based on fuzzy logic control simultaneously. In particular, a vectorized fuzzy inference system is devised, which allows large-scale fuzzy logic controllers to run in parallel, thereby improving optimization efficiency. Pareto optimal solutions of different hybrid energy storage systems incorporating both optimal design and control parameters are obtained and compared to show the achieved enhancements of the proposed approach.