AI-UAS01

Artificial Intelligence in Unmanned Aerial Systems (AI-Driven Drones)

Dr. Sarah Mitchell

Lead AI & Robotics Instructor

16-24 weeks
9 Modules
Intermediate to Advanced
450+ Enrolled
15,000 BDT
One-time payment
  • Hybrid (Video + Live Sessions)
  • Certificate of Completion
  • Hands-on Projects
  • Lifetime Access
  • 24/7 Support
Module 1: Introduction to Drones & UAS Fundamentals Foundation
History of UAVs and modern use-cases
Drone types (quad, fixed-wing, hybrid), structures, propulsion
Flight principles: thrust, lift, drag, yaw, pitch, roll
Flight controllers (Pixhawk, Ardupilot, Betaflight, DJI SDK)
Sensors: IMU, gyroscope, magnetometer, GPS, barometer, Camera, LiDAR, ToF
Lab: Operate drone, calibrate sensors, connect to Mission Planner/QGroundControl
Module 2: Programming for Drones Coding
Python and ROS (Robot Operating System) for drone control
MAVLink protocol, DroneKit-Python / ROS MAVROS
Autonomous commands: takeoff, waypoint navigation, RTL, hold
Lab: Automate takeoff, GPS navigation, return-to-home, telemetry visualization
Module 3: Computer Vision for Drones CV & AI
Fundamentals of computer vision & image preprocessing
Object detection: YOLOv8 / YOLO-NAS, SSD / Faster-RCNN
Object tracking: SORT / Deep SORT, ORB / KLT tracking
Semantic segmentation (U-Net)
Edge AI: running models on Jetson Nano / Raspberry Pi 5
Lab: Detect cars/people, build Deep SORT tracker, deploy YOLO on Jetson Nano
Module 4: AI-based Flight Control & Navigation Advanced
Kalman Filters for drone localization
Sensor fusion: IMU + GPS + camera
Visual Odometry & SLAM for drones (ORB-SLAM, RTAB-Map)
Autonomous landing using CV
Path planning algorithms: A*, RRT*, Dijkstra
Reinforcement learning for path optimization
Lab: Visual landing with ArUco markers, ORB-SLAM2, obstacle-aware navigation
Module 5: Deep Learning for Drone Intelligence Deep Learning
CNNs, RNNs, LSTMs for drone data
Reinforcement Learning (OpenAI Gym)
Multi-agent swarm AI
Drone behavior prediction models
Edge AI optimization: TensorRT, ONNX
Lab: Train aerial image classifier, RL-based navigation, optimize YOLO with TensorRT
Module 6: Drone Simulation Environments Simulation
Tools: Gazebo, AirSim (Microsoft), PX4-SITL, CopterSim, DJI Simulator
Create virtual drone models
Simulate weather, obstacles, missions
AI flight planning in simulation
Lab: Develop autonomous mission in AirSim, connect MAVLink → SITL → ROS, test SLAM
Module 7: Autonomous Delivery Drones Application
Package weight sensors & pick-and-drop mechanism
Obstacle avoidance (CV + LiDAR fusion)
AI route optimization using ML
Landing zone detection
Lab: Detect safe landing zones, implement geofencing, delivery mission simulation
Module 8: Safety, Regulations & Ethical AI Use Legal & Ethics
Drone laws in different countries
BVLOS (Beyond Visual Line of Sight) rules
Flight permissions, geofencing
AI ethics in surveillance & fail-safe systems
Lab: Prepare risk assessment, configure failsafe behaviors in Pixhawk
Module 9: Real-World Applications & Final Project Capstone
Agriculture drone (spray, crop health monitoring)
Disaster response & surveillance
Mapping & 3D reconstruction
Medical delivery drones & wildlife monitoring
Final Project: Choose from AI-based autonomous drone, delivery system, SLAM navigation, aerial detection, swarm coordination, or crop health monitoring

Program Overview

This comprehensive course is designed for professionals and students who want to master the integration of Artificial Intelligence with Unmanned Aerial Systems. You will learn everything from drone fundamentals to advanced AI applications including computer vision, autonomous navigation, SLAM, and deep learning for drone intelligence. The course combines theoretical knowledge with hands-on projects using industry-standard tools and real drone hardware.

Course Outcome

Upon completion, you will receive a "Certificate of Completion" and gain expertise in Python, ROS, OpenCV, YOLO, Deep Learning for Drones, SLAM, and Autonomous Navigation. You'll be equipped to work on cutting-edge drone AI projects in agriculture, surveillance, delivery, and more.

What You'll Learn

  • Master drone fundamentals and flight principles
  • Program drones with Python, ROS, and MAVLink
  • Implement computer vision with YOLO, OpenCV
  • Build autonomous navigation systems with SLAM
  • Apply deep learning for drone intelligence
  • Develop real-world applications in agriculture, delivery, surveillance
  • Deploy AI models on edge devices (Jetson Nano, Raspberry Pi)
  • Complete hands-on projects with simulation and real hardware

Course Prerequisites

To get the most out of this course, you should have:

  • Basic Python programming
  • Linear algebra & machine learning fundamentals
  • Basic electronics / embedded systems
  • Drone flight basics (recommended)

Who This Course Is For

This course is perfect for:

  • Engineering students specializing in robotics or AI
  • Software developers wanting to enter drone technology
  • Robotics professionals looking to specialize in UAVs
  • AI/ML engineers interested in autonomous systems
  • Drone hobbyists ready for advanced applications

Tools & Technologies Used

Programming Languages

  • Python (Primary language)
  • C++ (For performance-critical tasks)

AI/ML Frameworks

  • PyTorch & TensorFlow
  • OpenCV (Computer Vision)
  • ROS (Robot Operating System)
  • YOLO, CNN/UNet, Deep SORT
  • Reinforcement Learning Models

Hardware

  • Pixhawk Flight Controller
  • Jetson Nano / Raspberry Pi 5
  • LiDAR, GPS, FPV Camera
  • Quadcopter platforms

Simulation Tools

  • AirSim (Microsoft)
  • Gazebo
  • PX4 SITL
  • CopterSim & DJI Simulator

Cloud AI (Optional)

  • AWS Rekognition
  • Google Vision API
  • Azure Machine Learning