CISC829 F2012

Course information

Title	CISC829-011 Mobile Robot Programming
Description	A hands-on approach to implementing mobile robot algorithms in simulation and on a group of small wheeled robots. Includes low- level motor control and reactive obstacle avoidance; high-level control including navigation, localization, and planning; vision-based sensing for tracking and mapping; and issues surrounding multi-robot cooperation.
When	Tuesdays and Thursdays, 3:30-4:45 pm
Where	Smith 102A
Instructor	Christopher Rasmussen, 446 Smith Hall, cer@cis.udel.edu
Office hours	Tuesdays and Thursdays, 11 am-12 pm (until October 15: in office; after October 15, in Smith 211)
Grading	16% 3 assignments worth 16% each. Each homework will be due 2 weeks after being assigned. 20% Presentation. 20-minute tutorial or demo of advanced features in ROS and/or PCL (that were not presented in lecture). You can talk about platforms (walking, flying), sensors, planners, perception algorithms, etc. using slides, images, and movies or live code. 32% Project Programming assignments will be graded on the basis of correctness, efficiency, and originality. This is not an introductory programming class, so coding style is not critical. However, if you want partial credit for something that doesn't quite work, it needs to be well-commented and easy to follow. For the overall course grade, a preliminary absolute mark will be assigned to each student based on the percentage of the total possible points they earn according to the standard formula: A = 90-100, B = 80-90, C = 70-80, etc., with +'s and -'s given for the upper and lower third of each range, respectively. Based on the distribution of preliminary grades for all students (i.e., "the curve"), the instructor may increase these grades monotonically to calculate final grades. This means that your final grade can't be lower than your preliminary grade, and your final grade won't be higher than that of anyone who had a higher preliminary grade. I will try to keep you informed about your standing throughout the semester. If you have any questions about grading or expectations at any time, please feel free to ask me.
Piazza	We will be using Piazza for discussion, questions, and help, both from me to you and student-to-student. To enroll: http://www.piazza.com/udel/fall2012/cisc829 After you enroll: http://piazza.com/class#fall2012/cisc829
Academic policies	Programming projects are due by midnight of the deadline day (with a grace period of a few hours afterward...after sunrise is definitely late). A late homework is a 0 without a valid prior excuse. To give you a little flexibility, you have 6 "late days" to use on homeworks to extend the deadline by one day each without penalty. No more than three late days may be used per assignment. Late days will automatically be subtracted, but as a courtesy please notify the instructor in an e-mail of your intention to use late days before the deadline. Assignment submissions should consist of a directory containing all code (your .cpp files, makefile, etc.), any output data generated (e.g., images, movies, etc.), and an explanation of your approach, what worked and didn't work, etc. contained in a separate text or HTML file. Do not submit executables or .o files, please! The directory you submit for each assignment should be packaged by tar'ing and gzip'ing it or just zip'ing it. The resulting file should be e-mailed to the instructor (cer@cis.udel.edu). Students can discuss problems with one another in general terms, but must work independently on programming assignments. This also applies to online and printed resources: you may consult them as references (as long as you cite them), but the words and source code you turn in must be yours alone. The University's policies on academic dishonesty are set forth in the student code of conduct here.

Instructions

Operating system	If you don't have a Linux distribution running currently, it's not hard to add one to your machine. The Ubuntu website has comprehensive instructions on installing it from different sources (CD-ROM, USB stick, etc.) on a separate partition (aka "dual booting"). I recommend version 12.04. Other free options are VirtualBox and VMWare Player, which let you run Ubuntu from within Windows. I found these instructions helpful when setting up my virtual machine Ubuntu can be run from within Mac OSX using VirtualBox or VMWare Fusion (which costs $50)
ROS	Installation instructions (Fuerte, Ubuntu 12.04) "Cheatsheet" Tutorial videos Rviz user guide
TurtleBot	Installing TurtleBot with Fuerte and 12.04 Also run this: sudo apt-get install ros-fuerte-turtlebot-simulator Turtlebot simulator tutorials Further changes to make are detailed in 8/30 lecture notes, but here they are in one place
Gazebo	The Gazebo 3-D simulator is included in the full desktop install of ROS Wiki Basic tutorials ROSCon 2012 talk To run "headless" (i.e. with no display), in launch file add -r to beginning of gazebo node's args string and comment out gazebo_gui node line DON'T INSTALL ANYTHING BELOW THIS LINE YET
Hector quadrotor	Use svn to checkout the following stacks (at least) from here: hector_quadrotor hector_quadrotor_apps hector_common hector_gazebo hector_models hector_slam Do sudo -i, go into hector_quadrotor, and do rosmake. roslaunch hector_quadrotor_demo outdoor_flight_gazebo.launch, then rosrun hector_quadrotor_controller test_trajectory. You should see the quadrotor do a little circuit.
PR2	WARNING: executing the next line will overwrite some of the turtlebot changes described in lecture sudo apt-get install ros-fuerte-pr2-simulator sudo apt-get install ros-fuerte-pr2-navigation (this brings down pr2_teleop)
OpenNI Kinect/ASUS drivers	Note: install these before OpenCV Installing on 12.04 (details/links in [1], [2]) OpenNI unstable, PrimeSense NITE unstable, and avin2 hardware driver. Make sure you choose the 32-bit or 64-bit version to match your Ubuntu install Possible fix for openni_launch not working Instructions for libfreenect (an alternative to OpenNI) on 12.04
OpenCV	Install guide
PCL	Installation: Pre-built binaries on Ubuntu PCL and ROS

Links

• Thrun probabilistic robotics slides
• Lavalle planning textbook
• WillowGarage videos (see ROSCon ones especially)
• Courses
  • ROS teaching resources and course links (overlaps some listed below)
  • Brown course (Jenkins)
  • Stanford TurtleBot course (Konolige)
  • hands-on CMU course (Veloso)
  • HMC robot lab (Dodds)
  • Visual Navigation for Flying Robots (Sturm)
  • Probabilistic robotics course at UW (Fox)
  • Washington U. course (Smart)
  • USC course (Mataric)
• Recording Gazebo/rviz (my shorter version)

Schedule

Note: The blue squares in the "#" column below indicate Tuesdays.

#	Date	Topic	Notes	Readings	Assignments/slides
1	Aug. 28	Introduction	Background, course information		slides
2	Aug. 30	ROS/Gazebo	Installation, hello ROS, hello Gazebo	Bohren's ROS intro slides	slides
3	Sep. 4	ROS/Gazebo	Writing simple ROS programs		HW #1 (see slides) slides
4	Sep. 6	ROS/Gazebo	Odometry, ground truth positions		slides
5	Sep. 11	Motion planning	Background, kinematics, PID control	Thrun et al. wheeled locomotion slides LaValle, Chap. 13.1.2	slides
6	Sep. 13	Motion planning	Homing controllers, occupancy grid and grid-based planning	Stanford Stanley paper (section 9.2) LaValle Chaps. 1 (skip 1.5), 15.3-15.3.2	slides
7	Sep. 18	Motion planning	Explanation of nav code (ROS costmap_2d and navfn, trajectory following, replanning), putting moving objects in Gazebo world		HW #1 due slides
8	Sep. 20	Motion planning	Bug variants, search-based planning	Choset's Bug slides ROSCon MP talk	slides
9	Sep. 25	Perception	Point clouds, estimation (least squares, RANSAC)		HW #2 (see slides) slides
10	Sep. 27	Perception	Kinect tilt controller, plane segmentation in PCL		slides
11	Oct. 2	Perception	Point cloud matching, registration	RSS 2011 tutorials on keypoints, range images	slides
12	Oct. 4	Perception	More details on registration and associated PCL functions
	Oct. 9	NO CLASS Instructor away
13	Oct. 11	Localization	Inference/tracking, Markov localization	ETH localization 1 (through slide 31), ETH localization 2 (through slide 41),	HW #2 due
14	Oct. 16	Localization	Particle filtering, Monte Carlo localization (ROS amcl)	Thrun particle filtering slides, U. Tennessee Monte Carlo Localization, Fox et al. AAAI 1999 paper, Nao localization at U. Freiburg
15	Oct. 18	Mapping	SLAM (ROS gmapping)	Thrun FastSLAM slides, gmapping demo, Darmstadt mapping	HW #3
16	Oct. 23	Mapping	gmapping details	UC Berkeley notes on gmapping, scan-matching	Instructions for running gmapping/amcl
17	Oct. 25	Mapping	RGB-D SLAM (ROS rgbdslam)	RGBD SLAM slides, ICRA 2012 RGBD SLAM paper, U. Texas slides on SIFT features 1, 2
18	Oct. 30	NO CLASS HW #3 Lab	Sign up page
19	Nov. 1	NO CLASS HW #3 Lab	Sign up page		HW #3 due
	Nov. 6	NO CLASS Election day
20	Nov. 8	Student presentations	Sign up page
21	Nov. 13	Student presentations	Sign up page
22	Nov. 15	Student presentations	Sign up page
23	Nov. 20	Miscellaneous	Finish lecture on SIFT features, go over project ideas
	Nov. 22	NO CLASS Thanksgiving
24	Nov. 27	Project lab
25	Nov. 29	Project lab
26	Dec. 4	Project presentations (extra-long class)
		NO FINAL EXAM