University of California at Berkeley
Dept of Electrical Engineering & Computer Sciences

CS 287: Advanced Robotics, Fall 2013

Fall 2012 offering (reasonably similar to current year's offering)
Fall 2011 offering (reasonably similar to current year's offering)
Fall 2009 offering (not particularly closely matched to current year's offering)


Instructors:
Professor: Pieter Abbeel
TA: John Schulman
Lectures: Tuesdays and Thursdays, 3:30pm-5:00pm, 310 Soda Hall
Office Hours:
Pieter: Mondays 2:00-3:00pm (and by email arrangement) in 746 Sutardja Dai Hall
John: Fridays 1:30-2:30pm in 730 Sutardja Dai Hall
Bonus office hours: Wednesdays 9/11, 9/25, 10/16, 11/6 2-3pm 746 Sutardja Dai Hall (problem set due days)
Communication: Piazza is intended for general questions about the course, clarifications about assignments, student questions to each other, discussions about material, and so on. To sign up, go to the Piazza website and sign up with "UC Berkeley" and "CS287" for your school and class.


Announcements


Assignments


Assignment policy


Final Project

The final project could be either of the following, where in each case the topic should be closely related to the course: Ideally, the project covers interesting new ground and might be the basis for a future conference paper submission or product. You are encouraged to come up with your own project ideas, yet make sure to pass them by me before you submit your abstract.

Logistics and Timeline



Prerequisites


Class Goals


Grading


Syllabus and materials

Slides are made available as the semester progresses.
In the Fall 2011 edition a couple of students volunteered to record and post lecture videos. They posted them here. They might be of interest this year, too.

Tentative schedule (edits in progress):

Lecture Topic Readings Optional/Additional Readings
Th Aug 29 Course Introduction
Tu Sep 3 MDP's, Exact Methods: Value Iteration, Policy Iteration, Linear Programming, LP notes Sutton and Barto, Reinforcement Learning, Chapters 3 and 4
Th Sep 5 Discretization of Continuous State Space MDPs Moore and Atkeson, 1993, Munos and Moore, MLJ 2001,
Tu Sep 10 Function Approximation / Feature-based Representations Chow and Tsitsiklis, 1991, Gordon, 1995, Tsitsiklis and Van Roy, 1996, Kushner and Dupuis, 1992/2001,
Th Sep 12 LQR, iterative LQR / Differential Dynamic Programming
Tu Sep 17 Convex Optimization cvx_example.m Boyd and Vandenberghe, Chapters 9-11
Th Sep 19 Non-Convex Optimization through Sequential Convex Programming (SCP) v2, Locally Optimal Control through Optimization: Collocation, Shooting, Model Predictive Control (MPC) Nocedal and Wright, Chapter 18
Tu Sep 24 Trajectory Optimization for Motion Planning --- Guest Lecturer: John Schulman ; Optimization over SE(3), Needle Steering, Channel Planning --- Guest Lecturer: Sachin Patil
Th Sep 26 Self-driving Cars
Tu Oct 1 Motion Planning: PRM, RRT + variants Steven M. Lavalle, Motion Planning, Chapters 5, 14, RRT*, Karaman and Frazzoli, LQR trees, Tedrake, code example
Th Oct 3 Motion Planning: A* + variants Likhachev slides, Steven M. Lavalle, Motion Planning, Chapters 5, 14 Videos: Urban Challenge Parking, Quadruped, Mobile Manipulation; Papers: Likhachev, Gordon, and Thrun, ARA*: Anytime A* with Provable Bounds on Sub-Optimality; van den Berg, Shah, Huang, and Goldberg, Anytime Nonparametric A*; Koenig, Likhachev, and Furcy, Lifelong Planning A*
Tu Oct 8 Probability Motivation, Probability Review, Bayes Filters Intro: PR 1; Probability Review and Bayes Filters: PR 2
Th Oct 10 Multivariate Gaussians PR 3
Fr Oct 11 Stanford-Berkeley Robotics Symposium 310 Sutardja Dai Hall
Tu Oct 15 Kalman Filtering PR 3 From Gauss to Kalman
Th Oct 17 EKF, UKF PR 3 Julier and Uhlmann, the UKF
Tu Oct 22 Smoother, MAP
Th Oct 24 Maximum Likelihood, EM
Tu Oct 29 POMDPs --- Guest Lecturer: Sachin Patil
Th Oct 31 Inverse Optimal Control
Tu Nov 5 Learning Trajectories from Demonstrations --- Guest Lecturer: John Schulman
Th Nov 7 Inverse Optimal Control (continued, same slide deck as before)
Tu Nov 12 SEIF, EnKF, EKF-SLAM, Motion Models, Beam Sensor Models, Scan Matching Motion Models: PR 5.1, 5.2, 5.3; Beam Sensor: PR 6.1, 6.2, 6.3;
Th Nov 14 Optimization for Estimation, GraphSLAM, Particle Filters and Localization Particle Filters: PR 4, Localization: PR 8.1, 8.3 Doucet, Godsill, Andrieu, 1998, Arulampalam et al., 2002
Tu Nov 19 Mapping with Known Poses, Rao-Blackwellized Particle Filters, gMapping Mapping with Known Poses: PR 9 Doucet, de Freitas, Murphy, Russell, Grisetti, Stachniss, Burgard T-RO 2006
Th Nov 21 Kinect Fusion, Kintinuous and other recent 3-D work -- Guest Lecturer: Stephen Miller
Tu Nov 26 Projects speed-dating
Th Nov 28 Happy Thanksgiving!
Tu Dec 3 Guest Lecture: Mark Palatucci, Co-founder and Chief Product Officer of Anki Drive
Th Dec 5 Autonomous Helicopters and Course Wrap-Up Abbeel, Coates, Ng, IJRR 2010, videos and data
Tu Dec 10 2-5pm Project Presentations schedule
Th Dec 12 No lecture



Related materials

Most relevant book for estimation: There is no direct match for other lectures, but here are some related resources: