AUV-ODIN-mujoco

Paper: Glocal trajectory generation and tracking control for autonomous underwater vehicles with optimal coverage sensor networks

This project provides a unified framework for glocal trajectory planning and real-time tracking control of a fleet of Autonomous Underwater Vehicles (AUVs) equipped with distributed sensors. The aim is to maximize area coverage while ensuring safe, robust, and connected operations in dynamic marine environments.

2D map

3D map

Obstacle attack

Key features

• Global Planning using the GT-MC heuristic for optimized AUV distribution
• Local Trajectory Generation using Model Predictive Control (MPC) with Control Barrier Functions (CBF) for safety
• Robust Tracking with Sliding Mode Control (SMC) and thruster allocation optimization
• Physics-based Simulation via MuJoCo

Project Structure

.
├── data
│   ├── ex_generate_waypoints
│   └── global_data
├── mujoco_model
├── notebook
│   ├── 2D_local_path_finding
│   ├── 3D_local_path_finding
│   ├── AUV_model
│   ├── AUV_mujoco
│   └── setup_path.py
└── src
    ├── control
    ├── dynamics
    ├── guidance
    ├── mathematical

---

Installation

1. Clone the repository

   git clone https://github.com/duccuongvu/AUV-ODIN-mujoco.git
   cd AUV-ODIN-mujoco

2. Create and activate a virtual environment (optional but recommended):

   python3 -m venv venv
   source venv/bin/activate

3. Install the required dependencies:

   pip install -r requirements.txt

4. Ensure all required dependencies are installed. If any are missing, install them manually:

   pip install numpy scipy matplotlib mujoco casadi scikit-image mediapy

5. Run example scripts or notebooks to ensure everything is set up correctly:

Cite

@article{CUONGVU2025122902,
title = {Glocal trajectory generation and tracking control for autonomous underwater vehicles with optimal coverage sensor networks},
journal = {Ocean Engineering},
volume = {342},
pages = {122902},
year = {2025},
issn = {0029-8018},
doi = {https://doi.org/10.1016/j.oceaneng.2025.122902},
url = {https://www.sciencedirect.com/science/article/pii/S0029801825025855}
}