alessioluciani / distributed-uav-rl-protocol Goto Github PK

View Code? Open in Web Editor NEW

An implementation of a distributed protocol for cooperative sensing and sending operations of Unmanned Aerial Vehicles (UAVs). It is built on top of TensorFlow Agents and uses reinforcement learning techniques (e.g. Deep Q-Learning, Actor-Critic) to compute ideal trajectories.

Jupyter Notebook 73.50% Python 26.50%

distributed-uav-rl-protocol's Introduction

Distributed UAV RL Protocol

An implementation of a distributed protocol for cooperative sensing and sending operations of Unmanned Aerial Vehicles (UAVs) [1]. It is built on top of TensorFlow Agents and uses reinforcement learning techniques (e.g. Deep Q-Learning, Actor-Critic) to compute ideal trajectories.

Install dependencies

Download and install Miniconda
Run conda env create -f environment.yml
Run conda activate durp
That's it!

Run the simulation

We also developed a simple GUI using the PyQt5 library to test the effects of applying different scenarios on the simulation. To run it, launch the simulator from the project directory with default arguments using:

./simulation.py

or to see the list of available options run:

./simulation.py --help

Simulator preview

Images credits

Icons made by Freepik, photo3idea_studio, and Roundicons from www.flaticon.com

References

[1] Jingzhi Hu, Hongliang Zhang, Lingyang Song, Robert Schober, & H. Vincent Poor. (2020). Cooperative Internet of UAVs: Distributed Trajectory Design by Multi-agent Deep Reinforcement Learning.

Recommend Projects

alessioluciani / distributed-uav-rl-protocol Goto Github PK