JacopoPan/aerial-autonomy-stack
An open framework to simulate and deploy perception-based PX4/ArduPilot drone swarms with ROS2, YOLO, LiDAR, NVIDIA Jetson
Supports autopilot-agnostic control via PX4 Offboard and ArduPilot Guided modes through action-based ROS2 interfaces, enabling both GNSS-denied and velocity/acceleration setpoint flight. Implements a dual-network architecture (SIM_SUBNET for sensor data, AIR_SUBNET for inter-vehicle comms) with Zenoh bridges, plus steppable Gymnasium environments for faster-than-real-time multi-instance training. Integrates KISS-ICP LiDAR odometry, ONNX-accelerated YOLO inference, and multi-Jetson hardware-in-the-loop testing across amd64/arm64 Docker containers.
349 stars.
Stars
349
Forks
65
Language
C++
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/JacopoPan/aerial-autonomy-stack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.