fan-ziqi / viplanner_data_generator

Matterport and Unreal Engine Data Generator For ViPanner

viplanner_data_generator

viplanner_data_generator can generator data for the ViPlanner project. It provides tools to collect and sample viewpoints from Matterport and Carla.

The current version was developed as part of the ViPlanner project (Paper | Code) and are based on the IsaacLab framework.

Installation

1. Install Isaac Sim using the IsaacLab installation guide.

git clone [e-mail]:isaac-sim/IsaacLab.git
git clone [e-mail]:fan-ziqi/viplanner_data_generator.git

2. Link the extensions into the IsaacLab extension directory

cd <path-to-your-IsaacLab-repo>/source/extensions
ln -s <path-to-your-viplanner-data-generator-repo>/extensions/omni.viplanner.importer .
ln -s <path-to-your-viplanner-data-generator-repo>/extensions/omni.viplanner.collector .

3. Then run the IsaacLab installer script.

cd <path-to-your-IsaacLab-repo>
./isaaclab.sh -i

Usage

Standalone scripts can be used to custmize the functionalities and easily integrate different parts of the extensions for your own projects. Here we provide a set of examples that demonstrate how to use the different parts:

You need to search and modify the USD_PATH, PLY_PATH and SAVE_PATH in the code. All require an absolute path.

• Sample Trajectories from Matterport:

  python standalone/omni.viplanner.collectors/check_matterport_trajectory_sampling.py
  

• Sample Trajectories from Carla (Unreal Engine):

  python standalone/omni.viplanner.collectors/check_carla_trajectory_sampling.py
  

• Sample Viewpoints and Render Images from Matterport:

  python standalone/omni.viplanner.collectors/check_matterport_viewpoint_sampling.py
  

• Sample Viewpoints and Render Images from Carla (Unreal Engine):

  python standalone/omni.viplanner.collectors/check_carla_viewpoint_sampling.py
  

Citing

If you use this code in a scientific publication, please cite the following paper:

@article{roth2023viplanner,
  title     ={ViPlanner: Visual Semantic Imperative Learning for Local Navigation},
  author    ={Pascal Roth and Julian Nubert and Fan Yang and Mayank Mittal and Marco Hutter},
  journal   = {2024 IEEE International Conference on Robotics and Automation (ICRA)},
  year      = {2023},
  month     = {May},
}

License

This code belongs to the Robotic Systems Lab, ETH Zurich. All right reserved

Authors: Pascal Roth, Ziqi Fan
Maintainer: Pascal Roth, [e-mail]

This repository contains research code, except that it changes often, and any fitness for a particular purpose is disclaimed.