Multicopter UAV simulation for control/RL experiments.

This repository provides a tutorial on setting up and simulating multiple drones using ROS 2, ArduPilot, and Gazebo Harmonic. It includes installation steps, required configurations, launch files, and example scenarios to help you build and test a multi-drone simulation environment.

This contain a drone simulated in V-REP (CoppeliaSim)

A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

Multi-agent drone swarm simulation framework built on PyBullet for robotics and reinforcement learning.

NSER-IBVS: Numerically Stable Efficient Reduced Image-Based Visual Servoing with knowledge distillation for autonomous drone control and navigation in GPS-denied environments. ICCV 2025

Learn drone autonomy from simulation to real flight: ROS2 Humble, ArduPilot SITL, Gazebo Harmonic, MAVROS, Raspberry Pi companion computer. Step-by-step beginner tutorials, hardware-verified.

A Unity-based quadrotor simulation for AI training, reinforcement learning, and autonomous drone navigation. Features realistic flight physics, ML-Agents integration and Python support.

Modern drone control station

UAVLnQ: An Architecture for Security Analysis of Cyber-Physical Network Behavior in UAV Swarms

Simulation of drone navigation through a procedurally generated disaster environment in CoppeliaSim. Features a quadcopter equipped with an RGB-D camera, manual keyboard or RC joystick control and dynamic obstacle generation for AI-based navigation and dataset collection.

High performance drone simulation environment for ultra efficient simulation of the drone's PoV. Can also be used to benchmark machine learning models.

ArduGazeboSim is a comprehensive Docker-based simulation environment for ArduPilot and Gazebo Classic 11, designed for drone development and testing. This project provides a complete containerized setup with ROS Noetic, allowing developers to work seamlessly across different machines without worrying about dependencies.

A 3D autonomous drone simulation with AI-powered flight capabilities using deep reinforcement learning. Features realistic physics, LiDAR obstacle detection, and a neural network that learns to navigate complex environments through both reinforcement learning and imitation learning from human demonstrations.

Fly-in is a graph-based drone routing simulator that uses capacity-aware pathfinding and real-time Pygame visualization.

A web-based 3D simulation of the University of Minnesota campus, showcasing a drone fleet delivery service. It features dynamic interactions among helicopters, humans, robots, drones, packages, and porch pirates, utilizing design patterns and C++ best practices for a robust and efficient system.

A sanitized, open-source sample template of the Nongin Aerial Wings Aid Ground Control System (NAWA GCS). Simulates real-time dual-drone disaster response (Scout & Delivery), telemetry overlay, automatic sequential supply dispatch, and ground-reloading in a fully offline client-side React sandbox.

Tools and background services to use quadcopter sims in hardware-in-the-loop simulation

Fire detection & precision landing drones with DroneKit, YOLOv4, OpenCV and ROS

Run drone simulators, firmware, and experiment scripts from a unified interface (currently Sphinx, more planned)