autonomous-flight

KR (KumarRobotics) autonomous flight system for GPS-denied quadrotors

Langostino - An open-source autonomous drone platform using ROS2 and AI-powered flight control. A complete reference implementation for building, understanding, and extending real-world drone autonomy.

Open ROS/PX4-based UAV development platform for research, education, and competition.

Autonomous UAV navigation system featuring real-time 2.5D occupancy-grid mapping, A* global path planning, and depth + LiDAR sensor fusion for dynamic obstacle avoidance in complex urban environments. Fully integrated with ROS 2, PX4 Offboard control, and Gazebo simulation for high-fidelity testing and deployment.

A lightweight Navigation stack for the drone

ROS2 Humble + MAVROS + ArduPilot integration framework. Test in SITL simulation, deploy to real hardware (Cube Orange, Pixhawk). Flight-tested on Raspberry Pi 4.

Autonomous Indoor Drone with Simulation and Hardware-Setup using ROS and SLAM

Python sample codes and documents about Autonomous Quadrotors algorithms. This project can be used as a technical guide book to study the algorithms and the software architectures for beginners.

This repository contains Python codes running on a Raspberry Pi 4 which is used as an on-board computer of an UAV. The codes are highly rely on DroneKit and OpenCV libraries.

Viability-Guided Sim-to-Real Transfer for a Small Fixed-Wing Glider in Uncertain Indoor Updrafts

A detailed repository with step-by-step instructions on implementing an autonomous UAV: All algorithms can be simulated on the px4 SITL simulator using ROS based Gazebo Simulator

Uses a downward facing camera to see a landing target, and guides the drone to land there. This node will consume and leverage topics with the Xeni drone nodes.

Quadrotor design and control

A behaviour tree based flight control node. Specify the drone mission in an XML file, and start the node.

International UAV Competition Mission Software – Autonomous Fixed-Wing UAV Controller & Payload Delivery

ARAV is an Autonomous Robotic Aerial Vehicle developed by Alberto Ceballos and Joan Bessa at ISAE-SUPAERO.

Embedded software and autonomous control logic for the Eflatun UAV team projects.

Minecraft elytra autopilot engine — protocol-level autonomous flight navigation using Mineflayer. Vanilla physics-compliant per-tick velocity updates, anti-cheat Bézier curves, FSM state machine, Nether hazard avoidance, and precision landing. Includes multi-AI-agent audit with cross-model scoring.

🤖 Live object tracking and autonomous visual servo control system for DJI Tello drone using YOLOv4 (Darknet) and OpenCV.

In this project, I applied 3D Notion Planning techniques to implement a drone agent capable of plan and execute missions in a complex urban environment.