Difference between revisions of "ME/CS 132a, Winter 2012"
Line 129:  Line 129:  
    
16 Feb (Th)  16 Feb (Th)  
−  [http://www.cds.caltech.edu/~stsuei/me132_2012/me132a/lectures/lecture11.pdf Linear Kalman Filter]  +  [http://www.cds.caltech.edu/~stsuei/me132_2012/me132a/lectures/lecture11.pdf Linear Kalman Filter], [http://www.cds.caltech.edu/~stsuei/me132_2012/me132a/lectures/KF_proof.pdf Proof of Kalman Filter] 
Thrun 3.2  Thrun 3.2  
Nick Hudson  Nick Hudson  
Line 135:  Line 135:  
rowspan=2 align="center"  8  rowspan=2 align="center"  8  
21 Feb (Tu)  21 Feb (Tu)  
−  Extended Kalman Filter  +  [http://www.cds.caltech.edu/~stsuei/me132_2012/me132a/lectures/lecture12.pdf Extended Kalman Filter, Unscented Kalman Filter] 
Thrun 3.3  Thrun 3.3  
Nick Hudson  Nick Hudson  
    
23 Feb (Th)  23 Feb (Th)  
−  Particle Filter  +  [http://www.cds.caltech.edu/~stsuei/me132_2012/me132a/lectures/lecture13.pdf Particle Filter] 
Thrun 3.4  Thrun 3.4  
Nick Hudson  Nick Hudson 
Revision as of 04:47, 24 February 2012
Advanced Robotics: Navigation and Vision 
Instructors

Teaching Assistants (me132tas@caltech.edu)
Course Mailing List: me132students@caltech.edu (sign up) 
Announcements
 TA office hours will be held on Mondays from 46pm in SFL 22.
 Jan 12: Please sign up for the mailing list and vote on a time for office hours before 10pm tonight!
 First lecture on 1/5
Course Information
Prerequisites
There are no formal prerequisites for the course. ME 115 ab (Introduction to Kinematics and Robotics) is recommended but not necessary. Students are expected to have basic understanding of linear algebra, probability and statistics. We will review some of the required background materials during the first week of lectures. Besides these, students should have some prior programming experience and know at least one of the following languages: C, Python, or MATLAB. Depending on the background of the class, we will hold tutorials for some of the programming languages to help students get started.
Grading
There are no midterm/final exams for this course. The grade will be based on weekly homework (60%) and two weeklong labs (20% each). Late homework will not be accepted without a letter from the health center or the Dean. However, you are granted a grace period of five late days throughout the entire term for weekly homework. Please email the TAs and indicate the number of late days you have used on the homework. No grace period is allowed for weeklong labs.
 Homework: Homework is usually due in one week after it is assigned. You can choose to turn in a hard copy in class or send an electronic copy to Stephanie Tsuei (stsuei at caltech.edu). If you are unable attend the lecture, contact the TAs to find an alternative way to turn in your homework.
 Labs: Students will form groups of 23 people and perform lab experiments together. Detail of this will be announced later in the course.
Collaboration Policy
Students are encouraged to discuss and collaborate with others on the homework. However, you should write your own solution to show your own understanding of the material. You should not copy other people's solution or code as part of your solution. You are allowed to consult the instructors, the TAs, and/or other students. Outside reference materials can be used except for solutions from prior years or similar courses taught at other universities. Outside materials must be cited if used.
Course Texts
There are two required textbooks:
 David A. Forsyth and Jean Ponce, Computer Vision: A Modern Approach (2nd Edition), Prentice Hall, 2011.
 Chapter 1 (Caltech access only)
 Sebastian Thrun, Wolfram Burgard, and Dieter Fox, Probabilistic robotics, MIT Press, 2005.
Additionally, there is an optional textbook that is available as a free download
 Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010.
Supplementary Reading
 P. Hebert, N. Hudson, J. Ma, J.W. Burdick (2011). Fusion of Stereo Vision, ForceTorque, and Joint Sensors for Estimation of InHand Object Location. Proc. of the IEEE Int'l Conf. on Robotics and Automation (ICRA), pp. 59355941. [pdf]
 P. Hebert, N. Hudson, J. Ma, T. Howard, T. Fuchs, M. Bajracharya, J.W. Burdick (2012). Combined Shape, Appearance and Silhouette for Simultaneous Manipulator and Object Tracking. Proc. of the IEEE Int'l Conf. on Robotics and Automation (ICRA), to appear. [pdf]
Lecture Notes
Week  Date  Topic  Reading  Instructor 
1  5 Jan (Th)  Course Overview, Illumination, Radiometry, and a (Very Brief) Introduction to the Physics of Remote Sensing  Forsyth 2.1, 3.1, 3.2  Larry Matthies 
2  10 Jan (Tu)  Cameras and Calibration  Forsyth Ch. 1  Larry Matthies 
12 Jan (Th)  Radiometry, Reflectance, and Color  Forsyth 3.3, 3.4, 3.5  Larry Matthies  
3  17 Jan (Tu)  Low Level Image Processing  Forsyth 4.1, 4.2, 4.5  Roland Brockers 
19 Jan (Th)  Feature Detection and Matching  Forsyth ch 5  Roland Brockers  
4  24 Jan (Tu)  Stereo Vision  Forsyth ch 7  Roland Brockers 
26 Jan (Th)  Tracking and Outlier Detection  Forsyth 10.4, 11  Yang Cheng  
5  31 Jan (Tu)  Structure from motion and visual odometry  Forsyth ch 8  Adnan Ansar 
2 Feb (Th)  Overview of Range Sensors, Introduction to Lab 1  Forsyth ch 14  Jeremy Ma  
6  7 Feb (Tu)  No Class (Lab 1)  
9 Feb (Th)  No Class (Lab 1)  
7  14 Feb (Tu)  Introduction to Estimation  Thrun 1, 2  Nick Hudson 
16 Feb (Th)  Linear Kalman Filter, Proof of Kalman Filter  Thrun 3.2  Nick Hudson  
8  21 Feb (Tu)  Extended Kalman Filter, Unscented Kalman Filter  Thrun 3.3  Nick Hudson 
23 Feb (Th)  Particle Filter  Thrun 3.4  Nick Hudson  
9  28 Feb (Tu)  Mapping  Thrun 9  Jeremy Ma 
1 Mar (Th)  Mapping, Introduction to Lab 2  Jeremy Ma  
10  6 Mar (Tu)  No class (Lab 2)  
8 Mar (Th)  No class (Lab 2) 
Homework
Please pay attention to the implementation guidelines when writing code for homework.
 HW 1 (due Tuesday, Jan. 17)
 HW 2 (due Tuesday, Jan. 24)
 HW 3 (due Tuesday, Jan. 31)
 HW 4 (due Tuesday, Feb. 7)
 Lab 1
 HW 5 (due Tuesday, Feb. 21)
 Sample Code (Feel free to translate to another language  it's not that much)
 HW 6 (due Tuesday, Feb. 28)
Solutions
Solutions are only accessible from the Caltech network. You can use VPN if you want to access the solutions from offcampus.