ME CS 132 2017

From Robotics
Revision as of 17:41, 9 February 2017 by Jbowkett (Talk | contribs) (Sampling Based Methods and Graphs Search Algorithms)

Jump to: navigation, search

This is the homepage for ME/CS 132(a,b) (Advanced Robotics: Navigation and Vision) for Winter/Spring 2017.

Course Staff, Hours, Location

Position Name Office Office Hours (changing weekly) Email Phone
Instructor Joel Burdick 245 Gates-Thomas send mail for an appointment jwb at robotics dot caltech dot edu 626-395-4139
Teach Asst. Joseph Bowkett 205 Gates-Thomas TBD jbowkett at caltech dot edu 626-395-1989
Teach Asst. Daniel Pastor Moreno 205 Gates-Thomas TBD dpastorm at caltech dot edu 626-395-1989
Teach Asst. Yoke Peng Leong Annenberg TBD ypleong at caltech dot edu 626-395-????
Administrative Sonya Lincoln 250 Gates-Thomas 7:30am-noon; 1:00pm-4:30pm lincolns at caltech dot edu 626-395-3385


Lecture Schedule: Based on a vote in class, for the near future we will meet at these times and locations:

  • Wednesday: 7:30-10:30 pm. Room 135 Gates-Thomas

Note: As the course enrollment firms up, we will vote one more time to see if we can find a better meeting time.

Announcements For ME/CS 132(a,b)

  • 02/01/17: Office Hours for Homework #2 will be held 7:30-9:00 pm on Thurs., Feb. 1 in 135 Gates-Thomas
  • 01/22/17: Office Hours for Hmmeowrk #1 will be held 8-10 pm on Sunday, Jan. 22 in 135 Gates-THomas.
  • 01/05/17: The meeting time and place have been set for the class lectures.
  • 01/04/17: The permanent lecture hours and location will be determined at the course organizational meeting.

Course Text and References

1) The main text for the first half of the course is:

  • Planning Algorithms by Steve LaValle (UIUC).

You can buy this book on-line at Amazon. A preprint of the text is available freely on-line, and is adequate for all course activities.

2) The following book is recommended (but not required):

  • Principles of Robot Motion: Theory, Algorithms, and Implementations, by Howie Choset, Kevin Lynch, Seth Hutchinson, George Kantor, Wolfram Burgard, Lydia Kavraki, and Sebastian Thrun.

This text is available at Amazon in both new and used versions.

3) Interested students may wish to also consult the following classic (but now out-of-print) text on motion planning: Robot Motion Planning by J.C. Latombe. A copy is available in the Caltech library.

Course Lecture Schedule for ME/CS 132(a)

Week Date Topic Reading Optional Reading Homework
1
Introduction and Review of Rigid Body Kinematics
4 Jan (Wed.) Class Overview & Mechanics
The basic motion planning problem
Course Overview Chapter 1 of Lavalle -No Homework-
6 Jan (Fri.) Review of Motion Planning Problems and Issues
2
Intro to C-space and the Basic Motion Planning Problem
11 Jan (W) Configuration Space (C-space)
Review of Planar Rigid Body Kinematics
Lavalle 4.2.1; Lavalle Chapter 3.2.2 (pages 94-97)
Notes on C-obstacles; The Star Algorithm;
MLS Ch 2.1, Pages 19-23
Lavalle Chapter 3.1
Homework 1,
Solution 1
13 Jan (F) Configuration-Space Obstacles Lavalle Chapter 4.3
Notes on Parametrized C-obstacles
Picture of C-Obstacle; C-space Visualization Video;Mathematica Demo of Manipulator C-Obstacles;
3
C-obstacles and the Classical Motion Planning Algorithms
18 Jan (W) Computing C--space obstacles
Review of Classical Motion Planning Algorithms
The Road Map
Lavalle 4.3 (pages 155-167)
Lavalle 6.1, Lavalle 6.2 (focusing on roadmaps)
No Homework Assigned
4
Roadmap Motion Planning Algorithms
25 Jan (W) The Road Map (continued)
Intro to Potential Field Methods
Lavalle 6.1, Lavalle 6.2 (focusing on roadmaps) Homework #2
Instructions for OMPL and ROS Virtual Machine Setup
5
Potential Field and Cellular Decomposition Algorithms
1 Feb (W) Potential Fields continued
Cellular Decomposition Methods
Lavalle 6.3 (Cellular Decompositions) No Homework Assigned
6
Sampling Based Methods and Graphs Search Algorithms
7 Feb (W) Sampling Based Planning Methods br> Brief Tutorial on Graph Searching Lavalle, Sections 5.2-5.5 (Samplinlg Based Methods)
Lavalle, Section 2.1 and 2.2
Notes on A-star
Homework #3
Instructions for Lab 2
Files for Lab 2

Course Mechanics, Grading, and Collaboration Policy

Grading

The final grade will be based on homework sets, and a final exam or final project:

  • Homework (70%): Homework sets will be handed out every 7-10 days, and are due at 5 pm on the due date (which will always coincide with a class meeting). Homeworks can be dropped off in class, or deposited in the box outside of 245 Gates-Thomas. Some homeworks will require computation. MATLAB or Mathematica should be sufficient to solve every homework posed in this course, though students can choose their favorite programming language. Code is considered part of your solution and should be included in with the problem set when appropriate.
  • Final exam/project (30%): Students have the option to take a final exam (a limited time take-home format exam which is open book, open note, and computer allowed) or select a final project. The final project must incorporate some aspect of the course, and the topic and scope my be approved by the course instructor. The final exam will due at 5:00 pm the last day of finals. The final project is similarly due at 5:00 pm on the last day of finals.
  • Late Homework Policy: Students may automatically take a 2-day extension on two homeworks during each quarter.

Collaboration Policy

Collaboration on homework assignments is encouraged. You may consult outside reference materials, other students, the TA, or the instructor, but you must cite any use of material from outside references. All solutions that are handed in should be written up individually and should reflect your own understanding of the subject matter. Computer code and graphical plots are considered part of your solution, and therefore should be done individually (you can share ideas, but not code). No collaboration is allowed on the examinations.