UAV Search & Rescue Simulation

Multi-Agent Reinforcement Learning for Coordinated UAV Search and Rescue in a Simulated Unity Environment.

This project focuses on using MARL, where autonomous drone agents learn to collaborate efficiently to complete search and rescue missions. The drones will search a forest to find people and animals in danger of wildfires. Human supervisors will be able to issue high-level commands, while the MARL agents interpret, coordinate and execute search and rescue tasks. 

Tools ⚙️

• Unity 
• ML-Agents Toolkit

Devlogs🎥

The blogs below showcase the work I have produced for my Final Project, "Training Drones":

• Drone Controls
• Training AI 
• Gameplay