Ikd tree: an efficient point cloud data structure in LiDAR SLAM
K-d tree is a common multidimensional data structure, which can be used for range search, nearest neighbor search and other problems. However, in practical applications, we often need to query and modify dynamic data. At this time, the traditional k-d tree seems to be powerless. In order to solve this problem, researchers put forward the concept of Dynamic k-d tree. Different from the traditional k-d tree, the dynamic k-d tree can support insert, delete and modify operations, and can maintain a balanced state. Dynamic k-d tree can be used for various multidimensional data structure problems, such as range search, nearest neighbor search, etc. This paper will introduce the basic principle and implementation method of dynamic k-d tree.
CasA:A Cascade Attention Network for 3-D Object Detection From LiDAR Point Clouds
3D object detection based on Light Detection and Ranging (LiDAR) point clouds has received a lot of attention in recent years due to its wide applications in smart cities and autonomous driving.
Do you know the four major methods of monocular vision to achieve 3D perception?
3D object detection is a critical task for autonomous driving. Many important areas of autonomous driving, such as prediction, planning, and motion control, often require a perfect representation of the 3D space around the ego vehicle. Monocular 3D Object Detection draws a 3D bounding box on an RGB image In recent years, researchers have been […]
LOCUS: A Multi-Sensor Lidar-Centric Solution for High-Precision Odometry and 3D Mapping in Real-Time
A high-precision odometer and 3D mapping system centered on LiDAR and multi-sensor collaboration. The system is the core perception system used by the CoSTAR team in the DARPA Subterranean Challenge. Figure 1 Testing our proposed lidar odometry system in the DARPA Subsurface Challenge. (a) Urban Circuit test environment and Husky wheeled robot, (b) Tunnel Circuit […]
Learning-based Localizability Estimation for Robust LiDAR Localization
LiDAR-based localization and mapping systems are a core component in many modern robotic systems. It directly inherits the depth and geometry information of the environment, allowing accurate motion estimation and high-quality map generation in real time. However, insufficient environmental constraints can lead to localization failures, which often occur in symmetric scenes such as tunnels. […]