SLAM Overview: From Single Sensor to Heterogeneous Fusion

Abstract

After decades of development, LIDAR and visual SLAM technology has relatively matured and been widely used in the military and civil fields. SLAM technology enables the mobile robot to have the abilities of autonomous positioning and mapping, which allows the robot to move in indoor and outdoor scenes where GPS signals are scarce. However, SLAM technology relying only on a single sensor has its limitations. For example, LIDAR SLAM is not suitable for scenes with highly dynamic or sparse features, and visual SLAM has poor robustness in low-texture or dark scenes. However, through the fusion of the two technologies, they have great potential to learn from each other. Therefore, this paper predicts that SLAM technology combining LIDAR and visual sensors, as well as various other sensors, will be the mainstream direction in the future. This paper reviews the development history of SLAM technology, deeply analyzes the hardware information of LIDAR and cameras, and presents some classical open source algorithms and datasets. According to the algorithm adopted by the fusion sensor, the traditional multi-sensor fusion methods based on uncertainty, features, and novel deep learning are introduced in detail. The excellent performance of the multi-sensor fusion method in complex scenes is summarized, and the future development of multi-sensor fusion method is prospected.

ConCs-Fusion: A Context Clustering-Based Radar and Camera Fusion for Three-Dimensional Object Detection

“…Three-dimensional object detection refers to the task of detecting and recognizing objects in a 3D scene and estimating their relevant parameters. This information is crucial for applications such as autonomous driving and intelligent robots [21,22]. In Section 2.1, we will discuss the 3D object detection methods using camera, LiDAR, and radar separately.…”

A Review of Sensing Technologies for Indoor Autonomous Mobile Robots

“…SLAM is a technique used by mobile robots to determine their location in an unknown environment while simultaneously constructing an accurate map of the environment. The localization component estimates the robot’s position on an existing map, while the mapping component constructs the environment’s map [ 10 , 11 , 12 ]. The two components are interdependent in completing the map building process and enhancing accuracy through continuous iteration.…”

“…The optimization algorithm is iterated to minimize the error of the edges to find the optimal solution [13]. the robot's position on an existing map, while the mapping component constructs the environment's map [10][11][12]. The two components are interdependent in completing the map building process and enhancing accuracy through continuous iteration.…”

Extrinsic calibration method for integrating infrared thermal imaging camera and 3D LiDAR

“…The fusion of radar and infrared cameras can greatly enhance the completeness of vehicle perception information, including position, motion status and size (Zhangu et al, 2021;Dalirani et al, 2023). For indoor environments within buildings, early fusion of laser LiDAR with visual sensors primarily involved visible light color cameras and depth cameras (Chen et al, 2022;Wang et al, 2022). Visible light color cameras and depth cameras have high resolutions, providing detailed information about the color and texture of the surrounding environment.…”