《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

[ICRA 2022] Exploration with Global Consistency Using Real-Time Re-integration and Active Loop Closure

A frontier exploration module implementied with ROS 2, C++, and Python.

This work contains a modified version of cartographer_frontier_detection and rrt_exploration. We implement an active exploration process and improve its robustness and performance. More details are…

AR tag tracking library for ROS

[RA-L'24] DUFOMap: Efficient Dynamic Awareness Mapping

Bird's Eye View Perception

BEVDet online real-time inference using CUDA, TensorRT, ROS1 & C++.

cartographer work space with detailed comments

Sparsify pose graph to speed the optimization process

VINS-RGBD-FAST is a SLAM system based on VINS-RGBD. We do some refinements to accelerate the system's performance in resource-constrained embedded platforms, like HUAWEI Atlas 200DK, Raspberry Pi.

An implementation of AVP-SLAM and some new contributions

卡码网-23种设计模式精讲，每种设计模式都配套代码练习题，支持 Java，CPP，Python，Go🔥

ROS Node and Costmap 2D plugin layer for frontier exploration

LiDAR SLAM = FAST-LIO + Scan Context

3D LIDAR-based Graph SLAM

C++/Python Sparse Volumetric TSDF Fusion

A ground segmentation algorithm for 3D point clouds based on the work described in “Fast segmentation of 3D point clouds: a paradigm on LIDAR data for Autonomous Vehicle Applications”, D. Zermas, I…

Ground Segmentation from Lidar Point Clouds

Efficient Online Segmentation of Ground&Wall Points for Multi-line Spinning LiDARs. //在线分割激光点云中的地面点和墙面点。

A Robust LiDAR-Inertial Odometry for Livox LiDAR

MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition

[ITSC'23] Dynamic points removal using octomap, clean dynamic from your point cloud maps automatically.

An Efficient Probabilistic 3D Mapping Framework Based on Octrees. Contains the main OctoMap library, the viewer octovis, and dynamicEDT3D.

Real-time detection of diverse dynamic objects in complex environments.

The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating

Converts a 3D Point Cloud into a 2D laser scan.

LET-NET: A lightweight CNN network for sparse corners extraction and tracking

POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and forecasting of multiple objects in BEVs.