CSE 571: AI-Based Mobile Robotics

Spring 2021
TTh 10:00-11:20, online

Instructor

Dieter Fox (Office hours: Fri 10:30-11:30 am)

Teaching Assitants

Adam Fishman (Office hours: Tue/Thu 3:00-4:00 pm)
Junha Roh

Email and discussion

Canvas: https://canvas.uw.edu/courses/1448792

Please access Zoom class lectures via Canvas.

Discussion board: https://us.edstem.org/courses/4944/discussion/

Use this board to discuss the content of the course. Feel free to discuss homeworks, projects, and any confusion over topics discussed in class. It is also acceptable to ask for clarifications about the statement of homework problems, but not about their solutions.

Robot: Duckiebot with Jetson Nano

We managed to have Duckiebot robot kits sent to each student. These will be used in the homeworks and projects.

Textbook

There is no required textbook for the class. Many of the lectures and homework assignments will have associated papers and chapters from:

Probabilistic Robotics, S. Thrun, W. Burgard, and D. Fox., MIT Press, Cambridge, MA, September 2005.

Homework

There will be three homeworks with programming components done in Python.
  • Homework #1, due April 20th, 11:59 pm (pdf, code)
  • Homework #2, due TBA (pdf, code)
  • Homework #3, due TBA (pdf, code)

Project

Projects will be done in teams of two or three. We expect that most projects will leverage the Duckiebots. However, we are open to alternatives should you have access to adeuquate project environments via your research.
  • Project 0.5, due April 19th, 11:59 pm (pdf)
  • Project 1 (pdf)
  • Project 2 (pdf, code)

Grading

You will submit your assignments (both writeups and code) to gradescope. You have all been enrolled into the class. Please check your email.
  • Homeworks (40%)
  • Project (60%)

Late policy

You are allowed to use 6 late days throughout the quarter. After this, assignments turned in late will incur a penalty of 20%, for each day. Please plan ahead and don't expect more.

Academic Honesty Policy

While we encourage students to discuss homeworks, each student must write up their own solution. It’s fine to use a source for generic algorithms (with attribution), but it is not allowed to copy solutions to the problems. Additionally, students may not post their code online. If we determine that a student posted their code online, they will get an automatic 50% reduction on the entire assignment (math + code) and if they copy code for the problems from another student or from online, they will get an automatic 0% for the entire assignment.

Anonymous Feedback

Please send your feedback via https://feedback.cs.washington.edu/

Lectures (preliminary)

Date Topic Slides Reading (textbook/papers) Homework Project
Mar 30 Introduction Intro Chapter 1, 2 of Probabilistic Robotics - -
Apr 1 Bayesian state estimation, Filtering Prob Intro Chapter 1, 2 of Probabilistic Robotics - -
Apr 2 - - -

Homework 1 posted

-
Apr 6 Bayesian state estimation, Neural Networks Gaussians Chapter 6, 9 of Deep Learning - -
Apr 8 Neural Networks - Chapter 6, 9 of Deep Learning - -
Apr 9 - - - -

Project 0.5 posted

Apr 13 Motion and Sensor Models Motion models, sensor models Chapter 5, 6 of Probabilistic Robotics - -
Apr 14 - - - -

Lab Session 1-3 pm

Apr 15 Sensor Models, Kalman Filters (linear, EKF) - Chapters 3 and 7 (skip 3.5 and derivations) -
Apr 16 - - - -

Project 1 will be posted

Apr 19 - - - -

Project 0.5 Due

Apr 20 Kalman Filters (linear, EKF) - Chapters 3 and 7 (skip 3.5 and derivations)

Homework 1 Due

Homework 2 will be posted

-
Apr 22 Particle Filters I - Chapters 4 and 8 (skip derivations) - -
Apr 27 Particle Filters II - - -

Open-ended Project Proposal Due

Apr 29 Occupancy maps, SLAM - Chapters 9 and 10, Octomaps - -
May 4 Graph-SLAM and Fast-SLAM - GTSAM, Chapter 11 and 13 - -
May 6 Fast-SLAM, Exploration - Multi-robot, Curiosity-driven learning, Object modeling

Homework 3 will be posted

Homework 2 Due

-
May 11 Deterministic planning - Motion planning, A* slides from 473 -

Open-ended Project Mid-progress Report Due

May 13 Sampling based planning w/ RRTs - Complex motion planning, Anytime and replanning A*, RRT -

Project 2 will be posted

May 18 RRTs, Markov Decision Processes - Book chapter 14 - -
May 25 MDPs, Inverse Reinforcement Learning - - - -
May 27 Task and motion planning - - -

Project 2 Final Report Due

Jun 1 Learning to grasp - GraspNet, clutter - -
Jun 3 Summary - SE3-Nets, Langrangian Networks - -
Jun 8

Open-ended Project Presentation

Jun 10

Open-ended Project Final Report Due