isaac_ros_nvblox

NVIDIA-ISAAC-ROSApache-2.0活跃维护

基于 NVIDIA GPU 加速的 3D 场景重建工具,为 ROS2 机器人提供 Nav2 局部代价地图,让机器人在 Jetson 上实时构建三维环境并用于导航避障。

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

v5.0-0发布于 2026-09-22 03:29 UTC765star149fork同步于 2026-11-07 07:30 UTC

怎么上手

由 README 提炼,执行前请确认
README 未给出可直接执行的安装命令,需按官方文档的 Quickstart 依次完成环境搭建、下载 Quickstart 资产、安装包和运行示例 launch 文件
硬件要求按 README 说明

README 的性能表覆盖 x86_64 配 RTX 5090/3090/A3000 桌面或笔记本,以及 Jetson AGX Thor、AGX Orin、Orin Nano;未给出显存要求。Jetson Nano 不支持动态重建。

下载:源码 zip·GitHub Releases(安装包)本站不镜像安装包

项目说明

由 README 自动翻译提炼

基于 GPU 加速的 ROS 2 三维重建与 Nav2 局部代价地图工具,用深度相机或 LiDAR 实时建图避障

基于 NVIDIA GPU 加速的 3D 场景重建工具,为 ROS2 机器人提供 Nav2 局部代价地图,让机器人在 Jetson 上实时构建三维环境并用于导航避障。

核心能力

  • 用 GPU 实时重建三维场景并输出二维代价地图
  • 通过 costmap 插件把重建结果接入 Nav2 做避障规划
  • 支持深度相机与三维 LiDAR 作为输入
  • 提供静态、行人重建、动态重建三种建图模式
  • 用 RViz 网格插件实时流式更新彩色重建

容易踩的坑

安装与运行步骤分散在 Isaac ROS 官方文档中,README 本身不含可直接复制的命令;行人重建模式依赖 PeopleSemSegNet DNN 模型,需额外准备;Jetson Nano 上动态重建不受支持

内容由模型根据 README 生成,可能不完整或不准确,以官方文档为准。看原文 README

最近发版

5 个版本v5.0-0
  1. v5.0-05.0.0最新正式版2026-09-22 · 2026-09-22 03:29 UTC

    这个版本没有写更新说明。

  2. v4.6-04.6.02026-08-19 · 2026-08-19 02:50 UTC

    这个版本没有写更新说明。

  3. v4.5-04.5.02026-07-07 · 2026-07-07 01:04 UTC

    这个版本没有写更新说明。

  4. v4.4-04.4.02026-05-01 · 2026-05-01 03:46 UTC

    这个版本没有写更新说明。

  5. v4.3-04.3.02026-03-24 · 2026-03-24 03:51 UTC

    这个版本没有写更新说明。

用户点评

登录用户的真实使用记录,可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译

    Isaac ROS Nvblox

    Nvblox ROS 2 integration for local 3D scene reconstruction and mapping.

    Overview

    Isaac ROS Nvblox contains ROS 2 packages for 3D reconstruction and cost maps for navigation. isaac_ros_nvblox processes depth and pose to reconstruct a 3D scene in real-time and outputs a 2D costmap for Nav2. The costmap is used in planning during navigation as a vision-based solution to avoid obstacles.

    isaac_ros_nvblox is designed to work with depth-cameras and/or 3D LiDAR. The package uses GPU acceleration to compute a 3D reconstruction and 2D costmaps using nvblox, the underlying framework-independent C++ library.

    Above is a typical graph that uses isaac_ros_nvblox. Nvblox takes a depth image, a color image, and a pose as input, with which it computes a 3D scene reconstruction on the GPU. In this graph the pose is computed using visual_slam, or some other pose estimation node. The reconstruction is sliced into an output cost map which is provided through a cost map plugin into Nav2. An optional colorized 3D reconstruction is delivered into rviz using the mesh visualization plugin. Nvblox streams mesh updates to RViz to update the reconstruction in real-time as it is built.

    isaac_ros_nvblox offers several modes of operation. In its default mode the environment is assumed to be static. Two additional modes of operation are provided to support mapping scenes which contain dynamic elements: people reconstruction, for mapping scenes containing people, and dynamic reconstruction, for mapping scenes containing more general dynamic objects. The graph above shows isaac_ros_nvblox operating in people reconstruction mode. The color image corresponding to the depth image is processed with unet, using the PeopleSemSegNet DNN model to estimate a segmentation mask for persons in the color image. Nvblox uses this mask to separate reconstructed persons into a separate people-only part of the reconstruction. The Technical Details provide more information on these three types of mapping.

    Performance

    The following tables provides timings for various functions of nvblox core on various platforms.

    (*): Dynamics not supported on Jetson Nano.


    Documentation

    Please visit the Isaac ROS Documentation to learn how to use this repository.


    Packages

    Latest

    Update 2026-09-21: Compatibility and integration updates for the Isaac ROS 5.0.0 release