conda activate NavRL
cd NavRL/quick-demos

# DEMO I: Navigating to a predefined goal point
python simple-navigation.py

# DEMO II: Navigating to dynamically/randomly assigned goal points
python random-navigation.py

# DEMO III: Multi-robot navigation
python multi-robot-navigation.py

docker pull nvcr.io/nvidia/isaac-sim:2023.1.0-hotfix.1

docker run --name isaac-sim --entrypoint bash -it --runtime=nvidia --gpus all -e "ACCEPT_EULA=Y" --rm --network=host \
    -e "PRIVACY_CONSENT=Y" \
    -v ~/docker/isaac-sim/cache/kit:/isaac-sim/kit/cache:rw \
    -v ~/docker/isaac-sim/cache/ov:/root/.cache/ov:rw \
    -v ~/docker/isaac-sim/cache/pip:/root/.cache/pip:rw \
    -v ~/docker/isaac-sim/cache/glcache:/root/.cache/nvidia/GLCache:rw \
    -v ~/docker/isaac-sim/cache/computecache:/root/.nv/ComputeCache:rw \
    -v ~/docker/isaac-sim/logs:/root/.nvidia-omniverse/logs:rw \
    -v ~/docker/isaac-sim/data:/root/.local/share/ov/data:rw \
    -v ~/docker/isaac-sim/documents:/root/Documents:rw \
    nvcr.io/nvidia/isaac-sim:2023.1.0-hotfix.1

bash docker ps # check your container ID in another terminal

# Replace <id_container> with the output from the previous command
docker cp <id_container>:isaac-sim/. /path/to/local/folder # absolute path

# Set the ISAACSIM_PATH environment variable
echo 'export ISAACSIM_PATH="path/to/isaac_sim-2023.1.0-hotfix.1"' >> ~/.bashrc

cd NavRL/isaac-training
bash setup.sh

If the repo is installed correctly, you should be able to see the Isaac Sim window as shown below: 

![isaac-training-window](https://github.com/user-attachments/assets/14a4d8a8-e607-434f-af9d-42d0d945e8d7)


### Train your own RL agent
The training environment settings and hyerparameters can be found in 
```NavRL/isaac-training/training/cfg
```.

The following example demonstrates training with 1024 robots, 350 static obstacles, and 80 dynamic obstacles (an RTX 4090 is required). We recommend using [Wandb](https://wandb.ai/site/) to monitor your training and evaluation statistics.

After training for a sufficient amount of time, you should observe the robots learning to avoid collisions:

https://github.com/user-attachments/assets/2294bd94-69b3-4ce8-8e91-0118cfae9bcd


## II. Deployment Virtual Environment
This section provides the minimum conda environment setup required to deploy 
```NavRL
``` (including running on a real robot). If you have already created the  
```NavRL
``` conda environment during the [Isaac training step](#I-Training-in-NVIDIA-Isaac-Sim), you can skip this section. To create the conda environment, run the following commands:

Once the setup is complete, a conda environment named 
```NavRL
``` should be created. You can verify the installation by activating the environment:

## III. NavRL ROS1 Deployment
This section demonstrates an example of deploying NavRL with ROS1 and Gazebo using a quadcopter robot. Ensure that your system meets the following requirements:

- Ubuntu 20.04 LTS
- ROS1 Noetic

First, install dependencies and copy the 
```ros1
``` folder from this repository into your catkin workspace.

Then, set the environment vairable for Gazebo models.

Note that the environment variable should be set within the catkin_ws. For example, the correct 
```~./.bashrc
``` script should be  
```source ~/catkin_ws/src/ros1/uav_simulator/gazeboSetup.bash
``` instead of 
```source path/to/NavRL/ros1/uav_simulator/gazeboSetup.bash
```).

Finally, start the simulation and deploy NavRL navigation.

A Gazebo window will display the environment while an RViz window presents the data. Use RViz's 
```2D Nav Goal
``` tool to set the navigation target, as shown in the video below (note: the default environment and settings might be different from the video):


https://github.com/user-attachments/assets/b7cc7e2e-c01d-4e44-87e3-97271a3aaa0f


To change the environment settings, review the launch file at 
```ros1/uav_simulator/launch/start.launch
```. The parameters for each module are located in 
```ros1/navigation_runner/cfg/*.yaml
``` configuration files.


## IV. NavRL ROS2 Deployment
This section demonstrates an example of deploying NavRL with ROS2 and Isaac Sim using a Unitree Go2 quadruped robot. Ensure that your system meets the following requirements:
- Ubuntu 22.04 LTS
- ROS2 Humble

Before get started, please install the simulator based on [this link](https://github.com/Zhefan-Xu/isaac-go2-ros2).

First, copy the 
```ros2
``` folder from this repository into your ros2 workspace.

Then, start the simulation and deploy NavRL navigation.

An Isaac Sim window will display the environment while an RViz window presents the data. Use RViz's 
```2D Nav Goal
``` tool to set the navigation target. The navigation example is shown in the following video:


https://github.com/user-attachments/assets/4787f503-d8a3-4d7b-9d17-7057b2cff1eb


## V. Citation and Reference
If our work is useful to your research, please consider citing our paper.