Autonomous Aerial Robotics

This is a collection of projects for the course ELEC5660 (Introduction to Aerial Robotics) @ HKUST, 2025 Spring.

Project Overview

Developed control algorithms, trajectory planning, and sensor fusion techniques for an autonomous aerial robot by utilizing rigid-body dynamics, A* path planning, PnP-based localization, visual odometry, and (augmented state) Extended Kalman Filter (EKF)-based state estimation to enable vision-based indoor navigation and real-time flight control.

The whole course’s projects are divided into the following sub-projects.

Sub-projects

• Project 1 - Phase 1: Controller Design and Simulation
  • Keywords: PID, Quadrotor Dynamics
• Project 1 - Phase 2: Trajectory Planning and Generation
  • Keywords: Trajectory Planning, Optimization-based Trajectory Generation, Minimum Snap Trajectory, (un)constrained Quadratic Programming
• Project 1 - Phase 3: Path Planning and Obstacle Avoidance
  • Keywords: Path Planning, Obstacle Avoidance, A*, Dijkstra’s Algorithm
• Project 1 - Phase 4: Autonomous Control of Real Drone
  • Keywords: Autonomous Control, Motion Capture System
• Project 2 - Phase 1: 3D-2D Pose Estimation (PnP)
  • Keywords: 3D-2D Pose Estimation, PnP, OpenCV, SVD, Linear Estimation
• Project 2 - Phase 2: Stereo Visual Odometry
  • Keywords: Stereo Visual Odometry, PnP, Optical Flow, RANSAC, OpenCV
• Project 3 - Phase 1: EKF
  • Keywords: Extended Kalman Filter (EKF), IMU, PnP, Sensor Fusion, State Estimation
• Project3 - Phase 2: Augmented State EKF
  • Keywords: Augmented State EKF, IMU, PnP, Stereo VO, Sensor Fusion, State Estimation