Welcome to 16-362: Mobile Robot Algorithms Laboratory

Hello students and visitors! This is the official webpage for 16-362: Mobile Robot Algorithms Laboratory.

• Class Dates and Times: Tuesdays and Thursdays 0930-1050 ET in NSH 3002
• Instructor: Wennie Tabib
• Office: LL 05, Building Collaborative Innovation Commons
• Contact: wtabib (at) cmu.edu

This lecture-based course comprises four modules that present both theory and practice of mobile robot algorithms. These modules will be associated with three assignments and a project through which students will build a autonomy software package. In assignment 1, we will write a vehicle dynamics simulation and develop linear control capabilities. Assignment 2 aims at adding mapping and state estimation capability. Assignment 3 will enable students to add motion planners. The project combines the capabilities from the three modules into an individual student project that may leverage the software system developed through the prior assignments.

Learning Objectives

When you complete this course, you will be able to:

• Aerial Robot Autonomy: Implement a framework for autonomous quadrotor navigation and exploration.
• Development Skills: Plan software development efforts that address robotics applications.
• Software Artifacts: Develop a nontrivial mobile robot application.
• Algorithmic Familiarity: Implement key probabilisitc algorithms in mobile robotics.

Pre-requisites

Undergraduate-level understanding of probability, statistics, and algorithms is assumed. Experience with Python and basic familiarity with linear algebra, probability theory, and ordinary differential equations will benefit the student throughout the semester.

Learning Resources

There is no textbook required for this course. Slides and additional references for further reading will be provided with each lecture on the course website.

Assessments

This course implements software for mobile robots. Consequently, the assessments depend heavily on programming. We will be using the Python programming languages throughout the course. Your final grade in this course will be assessed according to:

• 75% Homework
  • assignment1: 25% (Transforms, Quadrotor Dynamics, and Control)
  • assignment2: 25% (Mapping and State Estimation)
  • assignment3: 25% (Quadrotor Planning)
• 25% Project
  • 10%: form groups of 2-3 and present your project proposal on Oct. 23 or Oct. 30
    • The project proposal presentations should include:
      • Motivation
      • Related work
      • Approach you will implement
      • How you will evaluate your approach
      • Timeline
      • Anticipated results
  • 15%: final project presentation (Dec. 2, Dec. 4)

Homework and Late Day Policy

Three mandatory assignments will be provided during the semester. All homework will be distributed using GitHub and collected using AutoLab. AutoLab will enable auto-grading and feedback for students to help them finalize submissions. Grades are available a few minutes after uploading the assignment. You may submit as many times as you’d like (i.e., unlimited number of submissions are allowed).

You will have 12 late days that you may use throughout the semester. You can use them all on one assignment or spread them out over multiple assignments. Leftover late days will be converted to extra credit at a value of 0.5% per remaining late day (maximum extra credit for 12 late days is 6%). If you use all your late days, and submit late you will be penalized by 25 points per day. Each assignment is worth 100 points so this means using all your late days and submitting two days late will result in a maximum score of 50 points (or 50%).

This late day policy exists to help students avoid potential situations where multiple complex assignments from different classes are all due at approximately the same time.

Project

Students will be required to work together in teams of 2-3 to complete a group project. The project will be worth 25% of the final grade. 10% of that grade will come from group formation and presenting a project proposal. The remaining 15% will come from the final project presentation, which is scheduled on the last 2 days of class. Late days may not be used on the project.

Course Staff

Instructor: Wennie Tabib

Teaching Assistants: Mike Anoruo and Lucky Kant Nayak

Previous Course Offerings

Mobile Robot Algorithms Laboratory by Wennie Tabib, Fall 2024

Mobile Robot Algorithms Laboratory by Wennie Tabib and Kshitij Goel, Fall 2023