Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Autonomous Drones with ROS2, Gazebo & ArduPilot: Build a UAV
New

Autonomous Drones with ROS2, Gazebo & ArduPilot: Build a UAV

Master drone autonomy with ROS2, Gazebo & ArduPilot: control theory, aerodynamics, AI perception, swarm coordination
New
Created byFerbin Richard
Last updated 8/2026
English
English

What you'll learn

  • Build a complete multirotor airframe in URDF and Xacro, with correct inertia tensors, sensor plugins, and a verified mass and thrust-to-weight budget.
  • Run real ArduPilot firmware in a software-in-the-loop simulation, and explain precisely which parts are real code and which parts are simulated physics.
  • Write ROS2 nodes in Python that command a drone through MAVROS and pymavlink, using services, actions, parameters, and the right QoS for each topic.
  • Operate a three-container Docker sim stack, and debug it: no heartbeat, missing telemetry, arming refusals, and FDM sockets pointed at the wrong host.

Course content

13 sections • 117 lectures • 11h 33m total length

  • Introduction4:24
  • 1.2 Who This Is For3:54
  • 1.3 Multirotor vs Others4:25
  • 1.4 Course Map4:28
  • 1.5 How This Course Works4:14
  • 1.6 Meet Your Instructor1:17
  • 1.7 Get the Assets1:36

Requirements

  • Basic Python. You should be comfortable with functions, classes, and imports. No ROS2, drone, or robotics experience is needed, we build from the ground up.
  • A Linux machine running Ubuntu 22.04 or 24.04, or a virtual machine. Everything else installs via Docker, so there is nothing complicated to set up.
  • No drone hardware required. The entire course runs in simulation on your laptop, and you never risk a real airframe to learn on.
  • Comfort with a terminal helps but is not assumed. Every command is shown on screen and explained before it is run.

Description

This course contains the use of artificial intelligence.

Ever wondered how a drone holds a precise altitude while wind pushes it sideways, plans a survey that covers an entire perimeter without wasting a single second of battery, and tells an intruder apart

from a fence post? In this course, you'll build and fly a fully simulated autonomous drone from the ground up, using the exact industrial stack real aerial robotics teams run: ROS2 Jazzy, Gazebo Harmonic,

ArduPilot SITL, and QGroundControl.


This isn't a vibe-coding course. Every hard topic is taught in three layers: the intuition (a picture or a live sim demo), the numbers (the actual math, derived plainly, worked on screen term by term),

and the code/config (how it maps to ROS2, Gazebo, and ArduPilot, and what breaks when you change it).


You'll start from zero installing ROS2, Gazebo, and Docker and work up through:


- Core ROS2 concepts: nodes, topics, services, parameters, launch files, TF2 gimbal frames, and DDS/QoS

- Reading and modifying a real multirotor's URDF/Xacro description, including mass, inertia, and collision physics

- Standing up the same Dockerized ArduPilot + Gazebo + QGroundControl stack used in real aerial robotics

- Control theory taught properly: state-space modeling, PID derived from scratch, cascaded loops, and Bode intuition

- The real aerodynamics at play: momentum theory, blade element theory, power curves, and thrust-to-weight

- Motor mixing across 6 degrees of freedom, flight modes, and wind disturbance rejection

- State estimation with GPS trilateration and an Extended Kalman Filter, plus GPS-denied flight using optical flow

- Coverage geometry: the boustrophedon sweep derived from camera footprint and altitude, and geofence enforcement in code

- Training and evaluating a YOLO-based object detector for aerial intrusion detection

- Swarm coordination as a real distributed-systems problem: consensus, task allocation, collision avoidance, and communication constraints

- A capstone mission where you fuse piloting, coverage, detection, and multi-drone handover into one autonomous run you own end-to-end


Along the way I share real war stories from building actual autonomous vehicles: a detector that flagged a fence post as a person, GPU render crashes, geofences that silently refuse commands, and a fleet

handover that left a coverage gap.


By the end, you'll have hands-on, physics-grounded experience with the same tools and techniques used in real aerial robotics and physical AI, a strong foundation for further study or a portfolio-ready

capstone project.


Who this course is for:

  • Python developers who want to move into robotics and need a real ROS2 project rather than another tutorial that stops at publishing a string.
  • Engineering students and recent graduates who want drone and autonomy work on their resume, built in simulation with no hardware budget required.
  • Working engineers moving into UAV, aerospace, or field robotics roles who need ArduPilot, MAVLink, and SITL simulation as practical working knowledge.
  • Anyone who has tried to set up a drone simulator, hit cryptic failures, and wants a stack that works plus the debugging skills to fix it when it breaks.

Report abuse