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

Principles of Robot Autonomy II

Winter 2021

Course Description

This course teaches advanced principles for endowing mobile autonomous robots with capabilities to autonomously learn new skills and to physically interact with the environment and with humans. It also provides an overview of different robot system architectures. Concepts that will be covered in the course are: Reinforcement Learning (RL) and its relationship to optimal control, contact and dynamics models for prehensile and non-prehensile robot manipulation, imitation learning and human intent inference, as well as different system architectures and their verification. Students will learn the theoretical foundations for these concepts. Prerequisites: CS106A or equivalent, CME 100 or equivalent (for linear algebra), CME 106 or equivalent (for probability theory), and AA 174A/274A.

Course Assistants

Erdem Bıyık Abhishek Cauligi

Meeting Times

Lectures meet virtually on Mondays and Wednesdays from 1:00pm to 2:20pm. All office hours are also virtual.

Prof. Bohg's office hours are on Fridays 1:00pm to 2:00pm, and by appointment.
Prof. Pavone's office hours are on Fridays 4:00pm to 5:00pm, and by appointment.
Prof. Sadigh's office hours are on Fridays 9:00am to 10:00am, and by appointment.
CA office hours are on Tuesdays from 4:00pm to 6:00pm and Fridays from 10:00am to 12:00pm.

Syllabus

The class syllabus can be found here.

Schedule

Subject to change. Lecture recordings will be posted on Canvas.

Blue: learning-based control and perception
Red: interaction with the physical environment
Green: interaction with humans
Orange: system architectures, verification & validation

Week Topic Lecture Slides Lecture Notes
1 (Jan 11) Course overview, intro to ML for robotics
(Jan 13) Markov decision processes, intro to RL
(Jan 15) HW1 out
Lecture 1
Lecture 2
Lecture 1
Lecture 2
2 (Jan 18) Martin Luther King Jr. Day (no class)
(Jan 20) Model-based and model-free RL for robot control

Lecture 3

Lecture 3
3 (Jan 25) Learning-based perception
(Jan 27) Fundamentals of grasping
(Jan 29) HW1 due, HW2 out
Lecture 4
Lecture 5
Lecture 4
Lectures 5 & 6 & 7
4 (Feb 01) Grasp force optimization and planar pushing
(Feb 03) Learning-based grasping and manipulation
(Feb 05) Exam 1
Lecture 6
Lecture 7
Lectures 5 & 6 & 7
Lectures 5 & 6 & 7
5 (Feb 08) Interactive perception
(Feb 10) Guest Lecture - Teaching Robots in the Home (by Jeremy Ma)
Lecture 8
6 (Feb 15) Presidents' Day (no class)
(Feb 17) Imitation learning I
(Feb 19) HW2 due, HW3 out

Lecture 10

Lectures 10 & 11 & 12 & 13
7 (Feb 22) Imitation learning II
(Feb 24) Learning from pairwise comparisons and physical feedback
(Feb 26) Exam 2
Lecture 11
Lecture 12
Lectures 10 & 11 & 12 & 13
Lectures 10 & 11 & 12 & 13
8 (Mar 01) Interaction-aware control, intent inference, and shared autonomy
(Mar 03) System architectures
(Mar 05) HW4 out
Lecture 13
Lecture 14
Lectures 10 & 11 & 12 & 13
Lecture 14
9 (Mar 08) Specifications and model checking
(Mar 10) Formal verification of neural networks (by Changliu Liu)
(Mar 12) Exam 3, HW3 due
Lecture 15 Lecture 15
10 (Mar 15) System-level verification via stress testing (by Thomas Kühbeck)
(Mar 17) Paper presentations
(Mar 19) HW4 due
Lecture 17