Awesome

🤖 AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments

</div>

🤗 AGR-Family Works

OMEGA (RA-L 2024.12): The First AGR-Tailored Dynamic Navigation System.
HE-Nav (RA-L 2024.09): The First AGR-Tailored ESDF-Free Navigation System.
AGRNav (ICRA 2024.01): The First AGR-Tailored Occlusion-Aware Navigation System.

🎉 Chinese Media Reports/Interpretations

AMOV Lab Research Scholarship -- 2024.11: 5000 RMB
AMOV Lab Research Scholarship -- 2024.10: 5000 RMB

📢 News

[2024/01]: AGRNav is accepted to ICRA 2024.
[2023/11]: The code for training SCONet is in another repository.
[2023/09]: The 3D model in the simulation environment can be downloaded in OneDrive.
[2023/08]: 🔥 We released the code of AGRNav in the simulation environment.

</br>

If you find this work helpful, kindly show your support by giving us a free ⭐️. Your recognition is truly valued.

If you find this work useful in your research, please consider citing:

@INPROCEEDINGS{wang2024agrnav,
  author={Wang, Junming and Sun, Zekai and Guan, Xiuxian and Shen, Tianxiang and Zhang, Zongyuan and Duan, Tianyang and Huang, Dong and Zhao, Shixiong and Cui, Heming},
  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)}, 
  title={AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments}, 
  year={2024},
  pages={11133-11139}
}

🔧 Hardware List

Hardware	Link
AMOV Lab P600 UAV	link
AMOV Lab Allapark1-Jetson Xavier NX	link
Wheeltec R550 ROS Car	link
Intel RealSense D435i	link
Intel RealSense T265	link
TFmini Plus	link

</div>

❗ Considering that visual positioning is prone to drift in the Z-axis direction, we added TFmini Plus for height measurement. Additionally, GNSS-RTK positioning is recommended for better localization accuracy.

🤑 Our customized Aerial-Ground Robot cost about RMB 70,000.

🛠️ Installation

The code was tested with python=3.6.9, as well as pytorch=1.10.0+cu111 and torchvision=0.11.2+cu111.

Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.

Clone the repository locally:

 git clone https://github.com/jmwang0117/AGRNav.git

We recommend using Docker to run the project, which can reduce the burden of configuring the environment, you can find the Dockerfile in our project, and then execute the following command:

 docker build . -t skywalker_robot -f Dockerfile

After the compilation is complete, use our one-click startup script in the same directory:

 bash create_container.sh

Next enter the container and use git clone our project

 docker exec -it robot bash

Re-clone the repository locally

 git clone https://github.com/jmwang0117/AGRNav.git

Since need to temporarily save the point cloud, please check the path in the following file:

/root/AGRNav/src/perception/launch/inference.launch

/root/AGRNav/src/perception/SCONet/network/data/SemanticKITTI.py

/root/AGRNav/src/perception/script/pointcloud_listener.py

SCONet pre-trained model is in the folder below:

/root/AGRNav/src/perception/SCONet/network/weights

If you want to use our 3D AGR model, please download the AGR model to the folder below:

/root/AGRNav/src/uav_simulator/Utils/odom_visualization/meshes

And modify the code on line 503 in the following file to AGR.dae

/root/AGRNav/src/uav_simulator/Utils/odom_visualization/src/odom_visualization.cpp

Run the following commands

catkin_make
source devel/setup.bash
sh src/run.sh

You've begun this project successfully; enjoy yourself!

💽 Dataset

SemanticKITTI

🏆 Acknowledgement

Many thanks to these excellent open source projects: