Open Source ChromeOS Drone Software

pilottai is an AI-based autonomous drone navigation system utilizing reinforcement learning for real-time decision-making. It is designed for simulating and training drones to fly safely through dynamic environments using AI-based controllers.

ar-drone is a Node.js client library for controlling Parrot AR.Drone quadcopters over their network protocol. It provides a high-level API for common flight operations such as takeoff, landing, altitude changes, rotation, directional movement, and hovering. Programs can receive navigation telemetry including flight state, altitude, and other sensor data. Camera output can be accessed as raw video streams or converted into PNG frames through FFmpeg. The library also exposes predefined flight animations, LED sequences, configuration commands, and emergency recovery controls. An interactive REPL lets developers experiment with drone commands directly before building autonomous scripts. Lower-level UDP controls are available for applications that need closer access to the drone's command protocol.

Gym-PyBullet-Drones is an open-source Gym-compatible environment for training and evaluating reinforcement learning agents on drone control and swarm robotics tasks. It leverages the PyBullet physics engine to simulate quadrotors and provides a platform for studying control, navigation, and coordination of single and multiple drones in 3D space.