Langostino
An open-source autonomous drone platform using ROS2 and AI-powered flight control, designed to be understood, built, and extended.
- Drone
- Open source
- Works with AI
- ROS 2
- 3D printable
Suggested by Robotheca, created by @swarm-subnet (opens in a new tab), from github.com/swarm-subnet/Langostino (opens in a new tab). Pinned to commit 035b334 (opens in a new tab).
- Hardware license
- MIT (opens in a new tab)
- Software license
- MIT (opens in a new tab)
- Commercial use
- Allowed
This repository contains executable files that Robotheca doesn't check. Only run them if you trust the creator.
Which files (8 scripts, 1 firmware image)
- mapproxy/launch_mapproxy.sh (opens in a new tab)
- scripts/launch.sh (opens in a new tab)
- scripts/network_setup_22_04.sh (opens in a new tab)
- scripts/network_setup_24_04.sh (opens in a new tab)
- scripts/setup_22_04.sh (opens in a new tab)
- scripts/setup_24_04.sh (opens in a new tab)
- scripts/verify_setup.sh (opens in a new tab)
- src/swarm_ai_integration/scripts/ai_flight_node_wrapper.sh (opens in a new tab)
- inav-custom-firmware/inav_8.0.1_SPEEDYBEEF405V4.hex (opens in a new tab)
Photo and 3D model
3D preview converted from github.com/swarm-subnet/Langostino at 035b334, under MIT. View the original files from GitHub (472 KB) (opens in a new tab)
What it can do
Written by Robotheca from the project's documents.
- Autonomous flight driven by an AI model that outputs velocity commands to the flight controller
- Uses a front-facing LiDAR and GPS/IMU telemetry for observations and position hold
- Logs flight data to CSV via a black box recorder node
- Offline map tile server available for ground station use
Works with AI
Found by Robotheca in the project's files at commit 035b334, its robot.yaml and Robotheca's notes on its documents. Never guessed; Robotheca doesn't run the code.
“Autonomous flight driven by an AI model that outputs velocity commands to the flight controller”
Robotheca's notes: What it can do
Bill of materials
15 parts15 of 15 parts shown
15 of 15 parts have no price in the source, so there is no parts total. Read from docs/assembly/BOM.md at the pinned commit.
Build guide
The guide appears here as you scroll.
Guide by @swarm-subnet (README.md), under MIT.
More guides
Wiring and electronics
Notes written by Robotheca from the project's documents.
Main parts
- INAV-based flight controller (SpeedyBee F405 V4 stack with 55A 4-in-1 ESC)
- Brushless motors (iFlight XING-E Pro 2306 1700KV) with 6-inch propellers
- Raspberry Pi 5 running ROS2 Humble as companion computer
- LiDAR time-of-flight distance sensor, front-facing
- HGLRC M10 GPS module with compass
- ExpressLRS 2.4G radio link (RadioMaster Boxer transmitter, SpeedyBee Nano receiver)
- 4S LiPo battery (1300mAh) with 5V UBEC regulator
Connections
- Flight controller communicates with the Raspberry Pi over a serial port (/dev/ttyAMA0) using the MSP protocol at 115200 baud
- LiDAR connects to the Raspberry Pi over I2C bus 1 at address 0x08
- Battery feeds the flight controller stack and a 5V UBEC that powers the Raspberry Pi and sensors
- Wiring diagram is provided in assets/fc-wiring.png
Cables and connectors
From the parts list.
- Ovonic 4S LiPo 1300mAh 100C (XT60) × 1
