Drone Computing COURSE

Introduction

This course operates as a high-level research presentation combined with an engineering capstone. Because the course consists of a select cohort of students, it is collaborative and student participation-driven. The core objective is for the entire cohort to function as a unified engineering team to design, build, program, and deploy an autonomous drone system capable of solving a complex real-world challenge: autonomous wildlife management and threat evasion. The CAR Lab, directed by Dr. Weisong Shi, provides the drones, the onboard compute, and FAA Part 107–licensed pilots to support the course lab.

COURSE OUTLINE

1. Hardware, OS & Sensors

FAA Part 107, & Licensing
Commercial Application Landscapes
Drone Hardware Architecture Overview
Embedded Live Connection
Low-Level Sensor Ingestion & Filtering

2. Flight Control & Mission Scripting

Closed-Loop Control & PID Theory
PID Tuning Implementation & Constraints
State Machines & Waypoint Mission Scripting
Fail-safes, Geofencing, and Emergency Code
Modern Edge Ingestion Protocols

3. TinyML on the Edge

TinyML for Microcontrollers & SBCs

4. Path Planning & Remote Sensing

Path Planning Algorithms in Production
Vector-Based Threat Evasion Calculus
Commercial Remote Sensing Applications
Target Tracking & Visual Servoing
Harassment Pattern Generation

5. Integration & Capstone Validation

Monolithic Code Integration & Stress Testing
Multi-Agent Systems & Modern Coordination
Post-Flight Data Analysis & Diagnostics
Full System Field Integration Testing

✨ Check the previous syllabus here for more information.

Syllabus_ Drone Computing_2026.pdf

COURSE TEXTBOOK

📚Drone Computing: Autonomous Systems in the Field

COURSE MATERIALS

Programming the drones

Programming_The_Drone.pdf

✨To find more course materials and slides, please go here!

PHOTOS

COURSE LAB

Check our lab video here!

Course Development Team

Dr. Matthew Saponaro, Vijay Bajracharya, Zixuan Wang, Zhuoyang Fu

Page updated

Google Sites

Report abuse