DroneOS - AI-Powered Autonomous Fleet Dispatch
DroneOS is an autonomous drone control framework built on PX4 Autopilot and ROS2. At its core is drone_core, a custom C++ SDK that exposes high-level flight control as ROS2 services — arm, takeoff, position commands, land. An OpenClaw AI agent runs on a Vultr VPS and acts as the fleet dispatcher. When emergency incidents come in through the dispatch service, they're routed to the agent via a bridge over WebSocket. The agent evaluates incident priority, checks drone availability and location, then sends flight commands through ROS2 to dispatch drones autonomously. The architecture is two servers connected over Tailscale VPN. The Vultr VPS runs the OpenClaw gateway, dispatch service, communication bridge, and React frontend. A separate simulation server runs PX4 SITL with Gazebo, dual drone_core nodes, rosbridge, and camera feeds. This is the same split you'd have in production — cloud command center talking to drones over VPN, except the drones are simulated. The frontend is a real-time dashboard connected to rosbridge over WebSocket. It shows the incident queue with priority levels, a map with drone positions, live camera feeds from both drones with picture-in-picture toggle, and an AI activity log showing every decision the agent makes. Operators see what the AI is doing and can override with natural language commands through the same OpenClaw agent. The dispatch service simulates a 911 CAD system generating incidents — medical emergencies, fires, property damage — each with priority levels and coordinates. The AI doesn't follow scripts. It decides which drone to send based on priority, proximity, and availability. The framework supports real hardware. Production Docker configs exist for Raspberry Pi companion computers communicating with Pixhawk flight controllers over serial. The simulation runs the same software stack. Live demo: http://207.148.9.142:3000 Source: https://github.com/ortegarod/drone-os
Category tags:Additional links:
"Impressed with this just make it scalable and go ahead"
Shaktesh Pandey
Founder
"super cool use case. Congrats! Love the use of all the latest tech"
Pawel Czech
Co-founder/Partner
"Architecture: drone_core: C++ SDK with high-level ROS2 services (arm, takeoff, land) OpenClaw AI agent: Fleet dispatcher running on Vultr VPS Dispatch service: Simulates 911 CAD system Tailscale VPN: Cloud to simulation connectivity Key Features: Real 911 emergency dispatch (simulated) AI decides which drone to send based on priority, proximity, availability Live camera feeds from drones Natural language override commands Production-ready for real hardware (Raspberry Pi + Pixhawk) Live demo: http://207.148.9.142:3000 Tech Stack: C++, ROS2, PX4, Python, React, Docker Pros: ✅ REAL hardware integration (not just simulation) ✅ Working live demo! ✅ Production Docker configs for real drones ✅ Excellent documentation ✅ Emergency services use case (huge impact potential) ✅ Video demo ✅ Solves real problem (emergency response time)"
Sanem Avcil
"The best idea I've seen so far with the PX4 and simulations integrated super well!! Could see this working with real drones with QGC integration in the near future. "
Syed Affan
Co Founder
"This project presents a highly original and technically strong approach to solving a challenging, time-critical problem. The application of automation and autonomous drone systems is impressive and clearly focused on reducing reaction time. However, beyond speed, real-world adoption will depend on building trust, particularly around automating dispatch decisions, replacing pilots, and ensuring safe drone operations. Strengthening validation, reliability, and regulatory considerations would significantly enhance the business case and overall impact."
.png&w=96&q=75){kind=small}
Hari Kanagala
Group Product Manager AI
"Constructive feedback Clarify real-world constraints and safety boundaries While the autonomy and decision-making are impressive, the project would benefit from clearer handling of real-world constraints such as airspace restrictions, fail-safe behaviors, loss of connectivity, and regulatory compliance. Explicitly stating what the AI will not do is as important as what it can do in safety-critical systems. Demonstrate operational evaluation beyond simulation The simulation is strong, but the system’s credibility would increase with metrics or scenarios showing how well the AI performs under stress—e.g., conflicting high-priority incidents, partial drone availability, or delayed telemetry—to assess robustness and decision quality. Positive feedback Exceptional systems thinking and production realism The clean separation between cloud control and drone execution, use of the same stack for simulation and production, and transparent AI activity logging demonstrate a mature, real-world engineering mindset that stands out."
Mallika Rao
Engineering Leader
For Innovators & Creators