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: human reconstruction, for mapping scenes containing humans, and dynamic reconstruction, for mapping scenes containing more general dynamic objects. The graph above shows isaac_ros_nvblox operating in human 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 humans-only part of the reconstruction. The Technical Details provide more information on these three types of mapping.

Quickstarts

Isaac ROS Nvblox

Performance

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

Dataset	Voxel Size (m)	Component	x86_64 w/ 4090 Ti (Desktop)	x86_64 w/ RTX3000 Ti (Laptop)	AGX Orin
Replica	0.05	TSDF	0.4 ms	3.6 ms	1.6 ms
		Color	1.7 ms	2.5 ms	4.2 ms
		Meshing	1.6 ms	4.0 ms	12.3 ms
		ESDF	1.9 ms	8.4 ms	8.4 ms
Redwood	0.05	TSDF	0.2 ms	0.2 ms	0.5 ms
		Color	1.1 ms	1.6 ms	2.4 ms
		Meshing	0.6 ms	1.5 ms	2.7 ms
		ESDF	1.5 ms	2.6 ms	4.2 ms

Supported Platforms

This package is designed and tested to be compatible with ROS 2 Humble running on Jetson or an x86_64 system with an NVIDIA GPU.

Note

Versions of ROS 2 earlier than Humble are not supported. This package depends on specific ROS 2 implementation features that were only introduced beginning with the Humble release.

Platform	Hardware	Software	Notes
Jetson	Jetson Orin Jetson Xavier	JetPack 5.1.2	For best performance, ensure that power settings are configured appropriately.
x86_64	NVIDIA GPU	Ubuntu 20.04+ CUDA 11.8+

Docker

To simplify development, we strongly recommend leveraging the Isaac ROS Dev Docker images by following these steps. This will streamline your development environment setup with the correct versions of dependencies on both Jetson and x86_64 platforms.

Note

All Isaac ROS Quickstarts, tutorials, and examples have been designed with the Isaac ROS Docker images as a prerequisite.

Customize your Dev Environment

To customize your development environment, reference this guide.

Updates

Date	Changes
2023-10-18	General dynamic reconstruction.
2023-04-05	Human reconstruction and new weighting functions.
2022-12-10	Updated documentation.
2022-10-19	Updated OSS licensing.
2022-08-31	Update to be compatible with JetPack 5.0.2. Serialization of Nvblox maps to file. Support for 3D LIDAR input and performance improvements.
2022-06-30	Support for ROS 2 Humble and miscellaneous bug fixes.
2022-03-21	Initial version.