Quarter 1
Week | Recorded lectures (by end of week) |
Project deliverable (due Thu. 11am PT) |
Lab checkoff (due Thu. 6pm PT) |
---|---|---|---|
1 | A1, C1 | P1: Personal introductions | L1: Git setup |
2 | A2, D2 | P2: Team ideas | L1: Mathematical formulation |
3 | D3, C6 (*) | P2.5: Explication preparation (**) | L1: Python implementation; Design decisions on sensor selection |
4 | A3, D4 | P3: Problem explications | L2: Webots setup |
5 | D5, D6 | P4: Requirements review (RR) / System design review (SDR) | L2: Design decisions on state estimator |
6 | C2 (*) | L3: Assembly of hardware | |
7 | P5: VC pitches | L3: Design decision on mechanical design | |
8 | L4: Experimental design for integrated comparisons | ||
9 | P6: Preliminary design review (PDR) | L4: Final design decisions | |
10 | Weekly update | ||
11 | P7: Stakeholder demo |
All Project deliverables are defined in our lab git.
(*): C2 and C6 are listed out of order here, so if you have time you may want to watch C2 first to provide context for the first few minutes of C6. After that though, the two topics are independent so this order should be fine. Regardless, you’ll want to watch C6 before starting on L2.
(**): This is an ungraded but mandatory checkoff.
Engineering in society
Choose (at least) one of the following:
Presenting
Design for debugging
Design
for debugging and
block diagrams (3 part lecture)
Design Intro
Problem Definition
Requirements Definition
Design Methods: Creative
Design Methods: Rational 1
Design Methods: Rational 2
Lecture 1: Systems and State
Lecture 2: Planning / control on MDPs
Lecture 3: Discretization and function approximation
Lecture 4: Graph-search based motion planning
Lecture 5: Linear quadratic regulators
Lecture 6: Bayesian filtering and POMDPs
Lecture 7: Kalman filtering and SLAM
lec07a (58:25) - kalman filter — kf slides (pdf) — kf notes (pdf)
lec07b (39:34) - SLAM — slam slides (pdf)
Lecture 8: Reinforcement learning
Lecture 9: Imitation learning, gaussian processes
Lecture 10: Other topics in robotics