This course is intended to serve as an graduate-level overview of robotics, with an emphasis on perception and planning. We will study algorithms and data structures related to these topics, covering widely adopted, and state of the art techniques. Students will gain hands-on experience in implementing, and extending such algorithms using real robot data, as well as simulations.

After successfully taking this class, you will be able to implement:

1. A local dynamic motion planner capable of avoiding obstacles
2. A particle filter for mobile robot localization
3. A LIDAR SLAM algorithm for a ground robot
4. A kinematic-aware motion planner for a nonholonomic mobile robot

Assignments will be completed in teams of two to three students. Students in the hybrid section will implement the assignments on the UT-AUTOmata scale 1/10 autonomous cars. Students in the online-only section will implement the assignments in simulation, and with logged robot data.

Text Books

Suggested text books: Probabilistic Robotics, Planning Algorithms

Background

In order to take this course, you should have an understanding of introductory statistics, coordinate geometry, linear algebra, calculus, and algorithms and data structures. Programming experience with testing and debugging will be very helpful.

Links

• Piazza (For Q&A): https://piazza.com/utexas/fall2020/cs393r
• Canvas (For report submissions, and grading): https://utexas.instructure.com/courses/1290748
• UT AUTOmata reference manual: Link
• Interactive Particle Filters: Link
• Zoom meeting links for lectures, office hours, and lecture recordings are available on Canvas.

Lectures, Office Hours

Lectures: MW, 9:00AM - 10:30AM, Zoom link on Canvas

Instructor
Joydeep Biswas, joydeepb@cs.utexas.edu
Office hours: Fridays, 1:00-2:00PM CST, Zoom link on Canvas

Teaching Assistant
Tongrui Li, tli1998@utexas.edu
Office hours: Mondays, 4:30-5:30PM CST, Zoom link on Canvas