This repository contains ROS2 Humble packages implementing hybrid path planning algorithms, including reeds_shepp_hybrid_astar and dubins_hybrid_star

A novel visual tool

Segment Anything in High Quality [NeurIPS 2023]

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

This repository is an official implementation of the paper "LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection".

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)

My implementation of Graspnet Graspness.

Deep learned, NVIDIA-accelerated 3D object pose estimation

Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

The navigation system of "sentry" for Next-E team in RoboMaster2023

YOLOv8 TensorRT C++ Implementation

YOLOv8-ROS-TensorRT-CPP detect, segment & pose including ros1 & ros2.

BEVFusion-ROS-TensorRT-CPP real time inference including ros1 & ros2.

基于YOLOV5 的ROS2功能包，可以快速完成物体识别与位姿发布。 A ROS2 package based on YOLOV5 that enables fast object recognition and pose publishing.

基于 YOLOv5 的 ROS 2 封装，允许用户使用给定的模型文件和图像话题进行实时物体检测。

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

3D目标检测与位姿估计学习笔记

This repository shows how to solve ONNX export issue in Segment Anything model

ROS2 node for 3D object detection using TAO-PointPillars.

This ros2 project mainly implements two functions. data_sub can subscribes realsense camera topic and save each frame to one image file(.jpg). data_pub loop publishes each image topic to ros2.

Here is the method to build a grid map and get rid of the laser distortion

ROS 1 and ROS 2 node that converts sensor_msgs/PointCloud2 LIDAR data to nav_msgs/OccupancyGrid 2D map data based on intensity and / or height. 🤖

A*-Path-Planner-for-2D-grid-map-in-ROS

导航“前端”，将定位后的三维点云实时或离线三维到二维栅格化，并计算代价生成代价地图。

Universal grid map library for mobile robotic mapping

VisionOS App + Python Library to stream head / wrist / finger tracking data from Vision Pro to any robots.