MAE195: Introduction to Robot Motion Planning & Navigation

This is the website for the UCI course MAE 195 “Introduction to Robot Motion Planning and Navigation".

Instructor

Professor Solmaz S. Kia
Department of Mechanical and Aerospace Engineering
Email: solmaz-at-uci.edu
Website: http://solmaz.eng.uci.edu

Intended scope

A robot's ability to plan its movement without explicit human guidance and determine its location in the world are basic prerequisites for robotic autonomy. This course is an introduction to the principles used to design planning and navigation algorithms for robots. The objective of motion planning algorithms is to enable an autonomous mobile robot to determine its movements in a cluttered environment to achieve various goals while avoiding collisions. The first part of this class covers deterministic classical motion planning algorithms, including sensor-based planning, decomposition, search-based planning, and sampling-based planning. The second part introduces the concepts from probabilistic robotics and focuses on the localization problem for mobile robots.

Tentative syllabus

The course lectures and content will roughly follow this tentative outline

Motion planning overview
Sensor-based motion planning: the bug algorithms
Motion planning via decomposition and search 
Configuration spaces
Free configuration spaces via sampling and collision detection 
Sampling-based motion planning (probabilistic roadmaps, RRTs, collision-checking primitives)
A brief overview of basic concepts in probability 
Probabilistic motion models
Probabilistic sensor models 
Robot localization via Kalman filtering

And also

An introduction to Robot Operating System (ROS) and programming in ROS (In week 2 or 3 of the course; this will be a brief introduction and not part of the course curriculum. You can find out more about ROS at http://wiki.ros.org/ROS/Tutorials)
Possible guest lecture from an invited speaker from industry or government lab

Prerequisite

MAE 10; Familiarity with Matlab is essential to do HWs.

Textbook

The main reference for motion planning, which we will follow closely, is

[1] F. Bullo and S. L. Smith. Lecture notes on robotic planning and kinematics. Copyrighted Material. (These are lecture notes available online. Check it out at http://motion.me.ucsb.edu/book-lrpk/)

The broad references for the probabilistic robotics and localization are

[2] S. Thrun, W. Burgard, and D. Fox. Probabilistic Robotics. Intelligent Robotics and Autonomous Agents. The MIT Press, 2005.
[3] H. Choset, K. Lynch, S. Hutchinson, G. Kantor, et al. Principles of Robot Motion, Theory, Algorithms, and Implementations. The MIT Press, 2005.

Other recommended books with relevant on the subject are

[4] A gentle introduction to ROS by Jason O’Kane, available online at https://www.cse.sc.edu/~jokane/agitr/agitr-letter.pdf
[5] Planning Algorithms by Steve LaValle (Cambridge Univ. Press, New York, 2006) available online at http://lavalle.pl/planning/

Lecture time and Place

Lectures take place on Zoom (see Canvas for the link) at 2:00 pm - 3:20 pm on Tuesdays and Thursdays.

Office hour

Instructor: Thursdays, from 3:45 pm to 4:45 pm, on Zoom. Please, send me email through Canvas email describing the problem before coming to ofce hours. Be prepared to show attempts at solving the problem. If you have any questions about the course, please send me email via Canvas. I will try to respond as quickly as possible. Additionally, I will share questions that are particularly good (and their answers) with the rest of the class by broadcasting my answer to the entire class by email.

Exam

Midterm (tentative date): TBA
Final: as announced in the class schedules, in class Homework

Homework

There will be a set of homework problems per week posted in the class website. Homework assignments are due weekly (special dates for your reference are included in the webpage. You need to return your homework to the designated folder (in pdf format). You need to complete all exercises (points will be taken for incomplete work), although only one, randomly selected, will be corrected from each assignment.
NO LATE homework will be accepted.

Grading

Homework: 20%
Motion Planning Project: 15%
Localization Project: 15%
Midterm: 20%
Final: 30%
In exceptional cases, I reserve the right to give extra points for excellent performance on the midterm, final and active class participation. Please do not count on it as a way to avoid doing the other assignments.

Canvas

Your grades will be posted via Canvas.

Academic Integrity Policy

No form of academic dishonesty will be tolerated. Academic misconduct, in its most basic form, is gaining or attempting to gain a grade, degree, or other academic accomplishment by any means other than through your own work. The formal policy states, "No student shall engage in any activity that involves attempting to receive a grade by means other than honest effort, and shall not aid another student who is attempting to do so." All academic integrity cases will be processed through the Office of Student Conduct under the Academic Honesty Policy. Please see Academic Integrity Policy (https://aisc.uci.edu/students/academic-integrity/) more information.