AA 174A / AA 274A / CS 237A / EE 260A

Principles of Robot Autonomy I

Fall 2021

Course Description

This course will cover basic principles for endowing mobile autonomous robots with planning, perception, and decision-making capabilities. Algorithmic approaches for trajectory optimization; robot motion planning; robot perception, localization, and simultaneous localization and mapping (SLAM); state machines. Extensive use of the Robot Operating System (ROS) for demonstrations and hands-on activities. Prerequisites: CS 106A or equivalent, CME 100 or equivalent (for calculus, linear algebra), and CME 106 or equivalent (for probability theory).

Meeting Times

Lectures meet on Tuesdays and Thursdays from 9:45am to 11:15am in NVIDIA Auditorium, Huang Engineering Center.

Students are expected to attend one 2-hour section each week (schedule details listed in the syllabus linked below); a mixture of online and in-person (meeting in the Skilling Lab) sections are offered.

Dr. Schmerling's office hours are on Thursdays 12:45pm to 1:45pm in Durand 217 and by appointment.

CA office hours are on Mondays from 1:00pm to 3:00pm (in-person, Skilling Lab), Tuesdays from 2:00pm to 4:00pm (online), and Thursdays from 6:00pm to 8:00pm (online).

Syllabus

The class syllabus can be found here.

Schedule

Subject to change. We will try to have the lecture slides and notes uploaded before each class period.

Week Topic Lecture Slides Lecture Notes Sections
1 Course overview, mobile robot kinematics
Introduction to the Robot Operating System (ROS)
Thursday: HW1 out
Lecture 1
Pre-knowledge quiz (solutions)
Lecture 2
Lecture 1 Notes
Lecture 2 Notes
2 Trajectory optimization
Trajectory tracking & closed loop control
Lecture 3; Code
Lecture 4
Lecture 3 Notes
Lecture 4 Notes
Section 1 Slides
Section 1 Handout
3 Motion planning I: graph search methods
Motion planning II: sampling-based methods
Tuesday: HW1 due, HW2 out
Lecture 5
Lecture 6; Code
Lecture 5 Notes
Lecture 6 Notes
Section 2 Slides
Section 2 Handout
4 Robotic sensors & introduction to computer vision
Camera models & camera calibration
Lecture 7
Lecture 8
Lecture 7 Notes
Lecture 8 Notes
Section 3 Slides
Section 3 Handout (In-Person)
Section 3 Handout (Virtual)
5 Image processing, feature detection & description
Information extraction & classic visual recognition
Tuesday: HW2 due, HW3 out
Lecture 9
Lecture 10
Lecture 9 Notes
Lecture 10 Notes
Section 4 Slides
Section 4 Handout (In-Person)
Section 4 Handout (Virtual)
6 Intro to localization & filtering theory
Parameteric filtering (KF, EKF, UKF)
Lecture 11
Lecture 12
Lecture 11 Notes
Lecture 12 Notes
Section 5 Slides
Section 5 Handout (In-Person)
Section 5 Handout (Virtual)
7 Tuesday: No lecture (Democracy Day)
Nonparameteric filtering (PF)
Thursday: Final project released
Friday: HW3 due, HW4 out
Lecture 13 Lecture 13 Notes Section 6 Slides
Section 6 Handout (In-Person)
Section 6 Handout (Virtual)
8 Markov localization and EKF localization
Simultaneous localization and mapping (SLAM)
Lecture 14
Lecture 15
Lecture 14 Notes
Lecture 15 Notes
Section 7 Slides
Section 7 Handout (In-Person)
Section 7 Handout (Virtual)
9 Multi-sensor perception & sensor fusion I (by Daniel Watzenig)
Multi-sensor perception & sensor fusion II (by Daniel Watzenig)
Lecture 16; Demo
Lecture 17
Lectures 16/17 Notes Section 8 Slides
Section 8 Handout (In-Person)
Section 8 Handout (Virtual)
N/A Thanksgiving Break
Sunday: HW4 due
10 Stereo vision
State machines
Tuesday: Final project check-in due
Lecture 18
Lecture 19
Lecture 18 Notes
Lecture 19 Notes
Follow this link to access the course website for the previous edition of Principles of Robot Autonomy I.