Isaac ROS Pose Estimation

Pose estimation and tracking using FoundationPose in a difficult scene with camera motion blur, round objects with few features, reflective object material, and light reflections

Overview

Isaac ROS Pose Estimation contains three ROS 2 packages to predict the pose of an object. Please refer the following table to see the differences of them:

Node	Novel Object wo/ Retraining	TAO Support	Speed	Quality	Maturity
isaac_ros_foundationpose	✓	N/A	Fast	Best	New
isaac_ros_dope	x	x	Fastest	Good	Time-tested
isaac_ros_centerpose	x	✓	Faster	Better	Established

Those packages use GPU acceleration for DNN inference to estimate the pose of an object. The output prediction can be used by perception functions when fusing with the corresponding depth to provide the 3D pose of an object and distance for navigation or manipulation.

isaac_ros_foundationpose is used in a graph of nodes to estimate the pose of a novel object using 3D bounding cuboid dimensions. It’s developed on top of FoundationPose model, which is a pre-trained deep learning model developed by NVLabs. FoundationPose is capable for both pose estimation and tracking on unseen objects without requiring fine-tuning, and its accuracy outperforms existing state-of-art methods.

FoundationPose comprises two distinct models: the refine model and the score model. The refine model processes initial pose hypotheses, iteratively refining them, then passes these refined hypotheses to the score model, which selects and finalizes the pose estimation. Additionally, the refine model can serve for tracking, that updates the pose estimation based on new image inputs and the previous frame’s pose estimate. This tracking process is more efficient compared to pose estimation, which speeds exceeding 120 FPS on the Jetson Orin platform.

isaac_ros_dope is used in a graph of nodes to estimate the pose of a known object with 3D bounding cuboid dimensions. To produce the estimate, a DOPE (Deep Object Pose Estimation) pre-trained model is required. Input images may need to be cropped and resized to maintain the aspect ratio and match the input resolution of DOPE. After DNN inference has produced an estimate, the DNN decoder will use the specified object type, along with the belief maps produced by model inference, to output object poses.

NVLabs has provided a DOPE pre-trained model using the HOPE dataset. HOPE stands for Household Objects for Pose Estimation. HOPE is a research-oriented dataset that uses toy grocery objects and 3D textured meshes of the objects for training on synthetic data. To use DOPE for other objects that are relevant to your application, the model needs to be trained with another dataset targeting these objects. For example, DOPE has been trained to detect dollies for use with a mobile robot that navigates under, lifts, and moves that type of dolly. To train your own DOPE model, please refer to the Training your Own DOPE Model Tutorial.

isaac_ros_centerpose has similarities to isaac_ros_dope in that both estimate an object pose; however, isaac_ros_centerpose provides additional functionality. The CenterPose DNN performs object detection on the image, generates 2D keypoints for the object, estimates the 6-DoF pose up to a scale, and regresses relative 3D bounding cuboid dimensions. This is performed on a known object class without knowing the instance-for example, a CenterPose model can detect a chair without having trained on images of that specific chair.

Pose estimation is a compute-intensive task and therefore not performed at the frame rate of an input camera. To make efficient use of resources, object pose is estimated for a single frame and used as an input to navigation. Additional object pose estimates are computed to further refine navigation in progress at a lower frequency than the input rate of a typical camera.

Packages in this repository rely on accelerated DNN model inference using Triton or TensorRT from Isaac ROS DNN Inference. For preprocessing, packages in this rely on the Isaac ROS DNN Image Encoder, which can also be found at Isaac ROS DNN Inference.

Quickstarts

• Isaac ROS CenterPose

• Isaac ROS DOPE

• Isaac ROS FoundationPose

Packages

• isaac_ros_centerpose
  • Quickstart
  • Troubleshooting
  • API
• isaac_ros_dope
  • Quickstart
  • Try More Examples
  • Use Different Models
  • Troubleshooting
  • API
• isaac_ros_foundationpose
  • Quickstart
  • Try More Examples
  • Troubleshooting
  • API

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 other than Humble are not supported. This package depends on specific ROS 2 implementation features that were introduced beginning with the Humble release. ROS 2 versions after Humble have not yet been tested.

Platform	Hardware	Software	Notes
Jetson	Jetson Orin	JetPack 6.0	For best performance, ensure that power settings are configured appropriately. Jetson Orin Nano 4GB may not have enough memory to run many of the Isaac ROS packages and is not recommended.
x86_64	Ampere or higher NVIDIA GPU Architecture with 8 GB RAM or higher	Ubuntu 22.04+	CUDA 12.2+

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
2024-09-26	Update for ZED compatibility
2024-05-30	Added FoundationPose pose estimation package
2023-10-18	Adding NITROS CenterPose decoder
2023-05-25	Performance improvements
2023-04-05	Source available GXF extensions
2022-06-30	Update to use NITROS for improved performance and to be compatible with JetPack 5.0.2
2022-06-30	Refactored README, updated launch file & added nvidia namespace, dropped Jetson support for CenterPose
2021-10-20	Initial update