Xianke Lin

Zhibin Bao, Sabir Hossain, Haoxiang Lang et al.

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.

Fei Liu, Zihao Lu, Xianke Lin

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.

Sabir Hossain, Xianke Lin

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.

Zihao Lu, Fei Liu, Xianke Lin

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.

Huilong Yu, Francesco Castelli-Dezza, Federico Cheli et al.

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.