Head Teaching Assistant and Lecturer - MEAM 620: Advanced Robotics

Course Description

The capstone course for the Robotics Masters program at the University of Pennsylvania. Helped TA this course for 3 separate years: 2016, 2018, and 2019. Covering a wide range of topics, this course teaches the basics of how to design the control and perception for an autonomous quadrotor. It is a heavily project based course. In 2019, I lectured for the majority of the perception based part. In all of the years, I helped design the homework for the perception part of the course, and also maintained the autograder for the projects (using my experience from CIS 390: Planning and Perception).

Course Details

Number of Students

30-40 Students

Topics Covered

Planning and Control

• Coordinate Frames and Transformations
• Kinematics, Dynamics for Quadrotors
• Basic Linear PD Controllers
• Non-linear controllers
• Graph Search, Dijkstras, A*, Path Planning
• Trajectory Planning (and some optimization)
• Differential Flatness (for Quadrotors)
• Bayesian Filters: Kalman Filters, Extended Kalman Filters

  Perception

• Camera Models, Camera Calibration
• Projective Geometry, analysis and estimation from measurements
• Pose from Projective Geometry
• Procrustes
• Feature trackinga and Optical Flow
• Basic Outlier Rejection: RANSAC, and Hough Transform
• Motion Field Equations, linear and angular velocity estimation
• Essential Matrices
• Stereo, Multi-view Stereo
• 2 View Structure from Motion

Lectures Given

• Camera Models, Camera Calibration (slides)
• Projective Geometry, analysis and estimation from measurements (slides)
• Pose from Projective Geometry (slides)
• Procrustes (slides)
• Feature trackinga and Optical Flow (slides)
• Basic Outlier Rejection: RANSAC, and Hough Transform (slides)
• Motion Field Equations (slides)
• Essential Matrices (slides)