DroneOS
A modern framework for autonomous drone development
Open-source and built on PX4 and ROS 2. From simulation to real hardware.
A C++ SDK and Python API that abstracts raw flight controller topics into high-level drone operations. AI dispatch demonstrated in simulation.
AI Fleet Dispatch
Autonomous emergency response — AI receives incidents, evaluates the fleet, selects the best drone, and dispatches it. Incident to airborne in ~10 seconds.
Cloud-to-Drone Control
Commands from anywhere over Tailscale VPN. Real-time telemetry, camera feeds, and fleet status streamed to the ground station via WebSocket.
Simulation-in-the-Loop
Full PX4 SITL environment with Gazebo. Test AI decision-making and fleet coordination in simulation before flying real hardware.
Roadmap
What we're building next at the intersection of AI, autonomy, and real-world drone systems.
Object Detection in Simulation
Connect camera feeds and object detection to the AI dispatch pipeline in Gazebo. Infrastructure exists — integration is next.
Modular Plugin Architecture
Restructure into swappable modules — flight stack adapters, perception backends, AI integrations.
4G Reliability for AI Dispatch
Validate the full AI dispatch loop over cellular on real hardware. Basic drone control works — AI dispatch hasn't been tested live.
Multi-Flight-Stack Support
Abstract beyond PX4 to support ArduPilot and other autopilot systems.
Technical Notes
Notes, experiments, and documentation from building DroneOS.