Computational robotics : ECE 209AS Fall 2025

Logistics

Hours

Staff

Course overview

About this course

What to do if you are joining this class late (i.e. after week 0 / lecture 0)

  • Read the above slides to understand how the course is structured!
  • Read the announcements on Bruinlearn!
  • Make sure you are signed up for coauthor and post your introduction.
  • Watch lecture 1 and submit pset 1 immediately.
  • Read through the week 1 challenge problems, and work through one on your own.
    • Read through existing coauthor posts for insights.
    • Be ready to productively join a group to continue working on it in class.
  • Connect with the class to join / make a final project team.

Grading

150 pts total:

Schedule summary

Week Topic Lecture Pset Project milestone
0 About this course pdf pset 0 Introductions: Communicate your personal interests, abilities, and skills
1 Systems and State C1 pset 1 Teaming: find 2-4(ish) people with common interests
2 Planning / control on MDPs C2 pset 2 Project exploration: Develop 3-5(ish) project ideas
3 Discretization and function approximation C3 pset 3 Project proposal: Specify project expectations and schedule
4 Graph-search based motion planning C4 pset 4 Project outline: Identify project solution and narrative
5 Linear quadratic regulators C5 pset 5 Mathematical formulation: Develop relevant mathematical models
6 Bayesian filtering and POMDPs C6 pset 6 Infrastructure: Set up computational tools / environment
7 Kalman filtering and SLAM C7 pset 7 Benchmarking: Establish current state-of-the-art capabilites
8 Reinforcement learning C8 pset 8 Initial results: Demonstrate solution process
9 Imitation learning, gaussian processes C9 pset 9 Final results: Validate and support successful contributions
10 Society, sociology, humanity; current state of robotics research C10 pset 10 Communication: Refine presentation of contributions in oral and written forms

Weekly in-class challenge problems

Lecture videos

Box folder

C1

Lecture 1: Systems and State

Addenda / errata (pdf)

Problem set (pdf)

lec01a (29:28)

lec01b (26:02)

lec01c (26:35)

lec01d (74:20)

C2

Lecture 2: Planning / control on MDPs

Addenda / errata (pdf)

Problem set (pdf)

lec02a (34:57)

lec02b (24:39)

lec02c (40:10)

lec02d (38:58)

C3

Lecture 3: Discretization and function approximation

Addenda / errata (pdf)

Problem set (pdf)

lec03a (64:43)

lec03b (30:55)

lec03c (31:35)

lec03d (30:43)

C4

Lecture 4: Graph-search based motion planning

Addenda / errata (pdf)

Problem set (pdf)

lec04a (33:46)

lec04b (44:28)

lec04c (32:44)

lec04d (54:36)

C5

Lecture 5: Linear quadratic regulators

Addenda / errata (pdf)

Problem set (pdf)

lec05a (45:51)

lec05b (46:01)

C6

Lecture 6: Bayesian filtering and POMDPs

Addenda / errata (pdf)

Problem set (pdf)

lec06a (40:17)

lec06b (32:08)

lec06c (46:23)

lec06d (24:14)

C7

Lecture 7: Kalman filtering and SLAM

Problem set (pdf)

lec07a (58:25) - kalman filterkf slides (pdf)kf notes (pdf)

lec07b (39:34) - SLAMslam slides (pdf)

lec07c (28:00) - Active SLAM concepts

lec07d (23:07) - Active SLAM papers

C8

Lecture 8: Reinforcement learning

Addenda / errata (pdf)

Problem set (pdf)

lec08a (59:28)

lec08c (49:00)

lec08b (35:04)

C9

Lecture 9: Imitation learning, gaussian processes

Addenda / errata (pdf)

Problem set (pdf)

lec09a (42:48)

lec09c (54:57)

lec09b (43:11)

C10

Lecture 10: Society, sociology, humanity; state of current robotics research

Addenda / errata (pdf)

Problem set (pdf)

lec10 (1:18:02)

Auxilliary videos

A1

Presenting

How to plan, prepare, and give a successful presentation

A2

Engineering in society

Choose (at least) one of the following:

A3

Design for debugging

Design for debugging (3 part lecture)

Example dependency diagrams