CSCI 584 Control and Learning in Mobile Robots and Multi-Robot Systems
Course Basics Course Description Syllabus Project Grading Related Web Sites Related Readings

Taught: Spring 2000, Fall 2001, Fall 2003, Fall 2005

If you are enrolled in this class, please check this page regularly for updated information.

Course Basics

Tuesdays 2pm-4:50pm, SGM 601

Students requesting academic accomodations based on a disability are required to register with Disability Services and Programs (DSP) each semester. A letter of verification for approved accomodations can be obtained from DSP when adequate documentaion is filed. Please be sure the letter is delivered to the instructor (or TA) as early in the semester as possible. DSP is open Monday-Friday, 8:30-5:00. The office is in Student Union 301 and their phone number is (213) 740-0776.

This course counts toward the Intelligent Systems (formerly AI) track credit for PhD students in the IS track. It also counts toward MS credit for MS students enrolled in the Intelligent Robotics MS program (MSCS-IR) .

Undergraduate AI (e.g., CSCI 460) or graduate AI (CS 561) or Introduction to Robotics (CSCI 445) or Sensing and Planning in Robotics (CSCI 547) or permission of instructor.

Course Description

Survey of robot control and learning methods from technical papers. Control architectures, adaptation, learning, cooperation, distributed v. centralized approaches, cooperative and competitive systems. Prerequisite: CSCI 460 or 445 or 561 or 547.

This course is a seminar-style hands-on survey of issues in approaches to control and learning in single and multi-robot systems. Besides teaching about robotics, it is a specific goal of this course to advance the participating students' critical thinking and communication skills, through active discussions and regular presentations and report writing.

We will read original seminal papers that track the development of the field and overview the different state-of-the-art approaches to mobile robot control, including reactive, hybrid, and behavior-based based systems. The discussion will focus on the issues of resolving the fundamental conflict between thinking and acting, i.e., high-level deliberation and real-time control. Different approaches and robot control architectures for addressing this issue will be covered and discussed. In the second part of the course we will discuss scaling up robot control to multi-robot systems to human-robot interaction and robot teams. We will also address adaptation and learning in single and multi-robot systems, and deal with the many challenges those problems present. Several other relevant topics will be covered at least briefly, including biological inspirations for robot control and philosophical foundations. All topics will be illustrated with implemented systems and demonstrated with videos.

Each week, all students will read all of the assigned readings. Each of the assigned readings will be presented by a pair of students, and discussed and critiqued by all others. The students presenting a paper in a given class should prepare a clear 25-minute presentation. This presentation should assume that the audience has read the paper, and not spend more than about 5 minutes summarizing it. Most of the presentation should be spent on discussing the paper, its strengths, weaknesses, any points needing clarification, and addressing any questions the other students may have. A natural way to break up the work between the presenters is to have one do the summary and praise of the work, and have one play the "Devil's advocate" role and critique the paper.

For information on how to present a paper, look here. You are expected to prepare a PowerPoint/Foils presentation to show from your laptop. An LCD projector is available in the meeting classroom for the paper presentations; it is your responsibility to provide the presentation on a laptop that is compatible with the projector, and cables to connect to it. For any logistical questions, please contact the course TA ahead of time.

For each paper being covered on a given day, each student (whether presenting or not), will bring to class a report up to one page long (no more), consisting of the following parts:

1. a paragraph briefly summarizing the contributions of the paper (copies of the abstract and/or intro and/or conclusions will not do);
2. a paragraph critiquing the paper. The critique should take the form of addressing the strengths and weaknesses of the paper, comparing it briefly to other work, especially other papers read in class, as relevant, etc.

The reports should be written in the same formal tone as the papers read in class; this means on contractions, jokes, or otherwise inappropriate expressions for a technical report. Eloquent prose and literary style are encouraged, as is originality of content, but keep in mind that these reports are one type of practice for technical writing.

All summary reports should include: the student's name, and the title and authors of the paper being summarized and critiqued. Hand-written or late reports will not be accepted. Each paper report should be turned in on a separate piece of paper, i.e., do not bundle multiple reports due on a given day into a single report, turn them in as separate stand-alone reports.

An exemplary report written by one of your peers is available here. In summary, for each class, you should bring:

1. printouts or digital versions of the papers being discussed,
2. a printed summary report for each of the papers,
3. a presentation, if you are presenting one of the papers,
4. great enthusiasm for discussing all of the papers. :)

Syllabus

Note: please bring the readings to class on the assigned day, in digital or hardcopy format, so you can refer to specific sections, pages, and images.

"The Robotics Primer" by M. Mataric´ (heretofore referred to as RP) is the background textbook for this course. The book is draft form in preparation for publication by MIT Press. Electronic versions of the draft cannot be distributed; you can purchase a copy of the draft for $12 from Paperclip at the University Village (ask for CS584 materials) starting on Monday, Aug 22nd. The material in this textbook is assumed background for the course. You can read the textbook at the start of the semester or throughout (as indicated by the syllabus); if you have prior robotics background much of this material should be familiar to you already. In any case, you are expected to have read the textbook.

The course readings consist of published papers from the field, listed and downloadble below (any issues with downloading the papers should be reported to the TA). Papers marked with Roman numerals will be presented; you will be expected to also read (or view, if videos) the background material (marked with ) which supports the papers. For additional optional papers and resources, please refer to the list found here. Three optional background textbooks are on reserve at the library for your convenience:

• Artificial Intelligence, A Modern Approach by S. Russel & P. Norvig, Prentice Hall, 2nd edition, 2002.
• Cambrian Intelligence by R. Brooks, MIT Press, 1999.
• Behavior-Based Robotics by R. Arkin, MIT Press, 1998.

If you'll only be presenting three papers, then you need to write two additional reports (like the weekly hand-ins) on two papers of your choice that are not included in the syllabus list. The papers can come from the Relevant Readings section or may be otherwise uncovered chapters from any of the three textbooks above. Any other papers should be approved by the TA.

RP: chapters 1-9 RP: chapters 10-12

1. "Intelligence Without Reason", Rodney A. Brooks, Proceedings of 12th International Joint Conference on Artificial Intelligence (IJCAI-91), Sydney, Australia, pages 569-595, August 1991.
   Presenter: Prof. Mataric´
2. "Modeling Adaptive Autonomous Agents", Pattie Maes, Artificial Life, 1(1-2), MIT Press, pages 135-162, 1994.
   Presenters: Pro: Morgan Hendry / Con: Morgan Hendry
3. "What are Plans For", Philip Agre and David Chapman, Robotics and Autonomous Systems, vol. 6, Elsevier Science, pages 17-34, 1990.
   Presenters: Pro: David Stark / Con: William Yeoh

RP: chapter 14

1. "A Robust Layered Control System for a Mobile Robot", Rodney A. Brooks, IEEE Transactions on Robotics and Automation, 2(1), pages 14-23, April 1986.
   Presenters: Dylan Shell
2. "A Robot that Walks; Emergent Behavior from a Carefully Evolved Network", Rodney A. Brooks, Neural Computation, 1(2), MIT Press, pages 253-262, 1989.
   Presenters: Pro: Dylan Shell / Con: Joey Wozniak
3. "Universal Plans for Reactive Robots in Unpredictable Environments", Marcel Schoppers, Proceedings of the 10th International Joint Conference on Artificial Intelligence (IJCAI-87), Milan, Italy, pages 1039-1046, August 1987.
   Presenters: Pro: Nanjappan Muruganathan / Con: Emily Mower

Here is an inflammatory debate about the paper above:

• A critique of the paper by Matt Ginsberg
  A defense of the paper by the author, Marcel Schoppers
  A rebuttal of the defense, again by Matt Ginsberg
  

RP: chapters 13 and 15

1. "SSS: A Hybrid Architecture Applied to Robot Navigation", Jon Connell, Proceedings, IEEE International Conference on Robotics and Automation (ICRA-92), Nice, France, pages 2719-2724, May 12-14, 1992.
   Presenters: Pro: Charmy Chhichhia / Con: Jenny Chang
2. "On Three-Layer Architectures", Eran Gat, Artificial Intelligence and Mobile Robotics, in D. Kortenkamp, R. P. Bonnasso and R. Murphy (eds.), AAAI Press, pages 195-210, 1998.
   Presenters: Pro: Jenny Chang / Con: Morgan Hendry

   Background reading about Player/Stage: "Most Valuable Player: A Robot Device Server for Distributed Control" Brian P. Gerkey, Richard T. Vaughan, Kasper Stoy, Andrew Howard, Gaurav S Sukhatme, and Maja J Mataric'. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2001), pages 1226-1231, Wailea, Hawaii, October 29 - November 3, 2001.

   Background reading about Gazebo: "Design and Use Paradigms for Gazebo, An Open-Source Multi-Robot Simulator", Nathan Koenig and Andrew Howard. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2149-2154, Sendai, Japan, Sep 2004.

3. Tutorial on Player/Stage/Gazebo. Slides are available here.
   Presenter: Dylan Shell (TA)

RP: chapters 16 and 17
Here is a brief background article on control architectures and representation in behavior-based robotics:

1. "Integration of Representation Into Goal-Driven Behavior-Based Robots", Maja J Mataric´, IEEE Transactions on Robotics and Automation, 8(3), pages 304-312, June 1992.
   Presenters: Pro: Selina Chu / Con: Jonathan Pearce
2. "AuRA: Principles and Practice in Review", Ron Arkin and Tucker Balch, Journal of Experimental and Theoretical Artificial Intelligence, 9(2-3), pages 175-189, April 1997.
   Presenters: Pro: Jacob Madden / Con: Mark Kim
3. "Multiple objective behavior-based control", Paolo Pirjanian, Robotics and Autonomous Systems, 31:1-2, 30 April 2000, pages 53-60.
   Presenters: Pro: Nanjappan Muruganathan / Con: Morgan Hendry

RP: chapter 19

Project proposals due in class.

1. "Monte Carlo Localization: Efficient Position Estimation for Mobile Robots", D. Fox, W. Burgard, F. Dellaert, and S. Thrun, Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI'99), pages 208-216, July 1999.
   Presenters: Pro: Kevin Locklin / Con: Usha Guduri
2. "Estimating Uncertain Spatial Relationships in Robotics", Peter Cheeseman, Randall C. Smith, Matthew Self, n Autonomous Robot Vehicles, I. J. Cox and G. T. Wilfong, editors, pp. 167-193, Springer-Verlag, 1990.
   Presenters: Pro: Sanford Freedman / Con: Kevin Locklin
3. "The Distributed Architecture for Mobile Navigation", Julio Rosenblatt, Journal of Experimental and Theoretical Artificial Intelligence, 9(2-3), pages 339-360, April 1997.
   Presenters: Pro: Charles Su / Con: Selina Chu

1. "A Survey of Socially Interactive Robots", T. Fong, Illah Nourbakhsh and Kerstin Dautenhahn, Robotics and Autonomous Systems, 42(3-4), pages 143-166, 2003.
   Presenters: Pro: Jacob Madden / Con: Jacob Madden
2. "MINERVA: A second generation mobile tour-guide robot", Sebatian Thrun, Maren Bennewitz, Wolfram Burgard, Armin B. Cremers, Frank Dellaert, Dieter Fox, Dirk Haehnel, Charles Rosenberg, Nicholas Roy, Jamieson Schulte, and Dirk Schulz, Proceedings, IEEE International Conference on Robotics and Automation (ICRA), 10-15 May 1999.
   Presenters: Pro: Joey Wozniak / Con: Kyong Il Kang
3. "Roball, the rolling robot", Francois Michaud and Serge Caron, Autonomous Robots, 12(2), pages 211-222, 2002.
   Presenters: Pro: Josh Wainer / Con: Mark Kim

1. "Towards robotic assistants in nursing homes: challenges and results", Joelle Pineau, Micheal Montemerlo, Martha Pollack, Nicholas Roy and Sebastian Thrun. Robotics and Autonomous Systems, Volume 42, Issues 3-4, 31 March 2003, pages 271-281.
   Presenters: Pro: Kyong Il Kang / Con: Emily Mower
2. The following three short papers (four pages a piece) are grouped together
   1. "Defining Socially Assistive Robotics", David J. Feil-Seifer and Maja J. Mataric', Poster paper in International Conference on Rehabilitation Robotics, Chicago, Illinois, Jun 2005.
   2. "A Hands-Off Physical Therapy Assistance Robot for Cardiac Patients", Kyong Il Kang, Sanford Freedman, Maja J. Mataric', Mark J. Cunningham, and Becky Lopez. Poster paper in International Conference on Rehabilitation Robotics, Chicago, Illinois, Jun 2005.
   3. "Hands-off Assistive Robotics for Post-Stroke Arm Rehabilitation", Jon Eriksson, Maja J. Mataric' and Carolee J. Winstein. In International Conference on Rehabilitation Robotics, Chicago, Illinois, Jun 2005.
   Presenters: Pro: Josh Wainer / Con: Han-Nung Lin
3. "A motivation system for regulating human-robot interaction", Cynthia Breazeal, Proceedings of the fifteenth National Conference on Artificial Intelligence (AAAI 98). Madison, WI, 1998, pages 54-61.
   Presenters: Pro: Usha Guduri / Con: Sanford Freedman

1. "Wheelesley, A Robotic Wheelchair System: Indoor Navigation and User Interface.", Holly A. Yanco, In Lecture Notes in Artificial Intelligence: Assistive Technology and Artificial Intelligence,, edited by V.O. Mittal, H.A. Yanco, J. Aronis, and R. Simspon. Springer-Verlag, 1998, pp. 256-268.
   Presenters: Pro: Kerry Connor / Con: Josh Wainer
2. "Mixed-Initiative Control of Multiple Heterogeneous Robots for Urban Search and Rescue" Robin R. Murphy, Jennifer Casper, Mark Micire, Jeff Hyams. Center for Robot Assisted Search and Rescue Technical Report CRASAR-TR2000-11, 2000.
   Presenters: Pro: Charles Su / Con: Jacob Madden
3. "User-Adaptive Control of a Magnetorheological Prosthetic Knee", Hugh Herr and Ari Wilkenfeld, Industrial Robot: An International Journal 2003; 30: 42-55.
   Presenters: Pro: Kevin Locklin / Con: David Stark

RP: chapter 21

1. "Learning to Coordinate Behaviors", Pattie Maes and Rodney A. Brooks, Proceedings, 8th National Conference on Artificial Intelligence (AAAI-90), AAAI Press/MIT Press, pages 796-802, 1990.
   Presenters: Pro: Kerry Connor / Con: Sanford Freedman
2. "Automatic Programming of Behavior-Based Robots Using Reinforcement Learning", Sridhar Mahadevan and Jon Connell, Artificial Intelligence , 55(2-3), 311-365, 1991.
   Presenters: Pro: Selina Chu / Con: Shane Hoversten
3. Background reading: "Getting Reinforcement Learning to Work on Real Robots", William D. Smart and Leslie Pack Kaelbling, "Proceedings of the Conference on Automated Learning and Discovery (CONALD 98)", 1998.
   
   "Multiagent Reinforcement Learning for Multi-Robot Systems: A survey", Erfu Yang and Dongbing Gu, University of Essex Technical Report CSM-404.
   Presenters: Pro: Zeeshan Maqbool / Con: Usha Guduri

1. "Evolving Electronic Robot Controllers that Exploit Hardware Resources", Arian Thompson, F. Moran, A. Moreno, J. J. Merelo, and P. Chacon (eds.), Advances in Artificial Life: Proceedings of the Third European Conference on Artificial Life, 929, Springer-Verlag, pages 640-656, 1995.
   Presenters: Pro: Mark Kim / Con: David Stark
2. Background reading on coevolution
   Background reading: Sims' seminal '94 paper "Evolving 3D Morphology and Behavior by Competition", Karl Sims, Proceedings, Artificial Life IV, R. Brooks and P. Maes (eds.), MIT Press/Bradford Books, pages 28-39, 1994.
   Background reading on Karl Sims' Virtual Creatures
   
   "Generative Encodings for the Automated Design of Modular Physical Robots" Hornby G.S., Lipson H., Pollack. J.B., IEEE Transactions on Robotics and Automation, 19(4), pages 703-719, 2003.
   Presenters: Pro: Joey Wozniak / Con: Zeeshan Maqbool
3. Background reading on ALVINN
   Knowledge-based Training of Artificial Neural Networks for Autonomous Robot Driving", Dean Pomerleau, Robot Learning, Kluwer Academic Publishing, pages 19-43, 1993.
   Presenters: Pro: Kyong Il Kang / Con: Joey Wozniak

RP: chapter 18 and 20

1. A (partial but extensive) annotated bibliography of work on stigmergy.
   "Stigmergy, self-organization, and sorting in collective robotics", Owen Holland and Chris Melhuish, Artificial Life, 5(2), pages 173-202, 1999.
   Presenters: Pro: Mihir Sanghavi / Con: Zeeshan Maqbool
2. "Cooperation without deliberation: A minimal behavior-based approach to multi-robot teams", Barry Werger, Artificial Intelligence, 110, pages 293-320, 1999.
   Presenters: Pro: Jenny Chang / Con: Charles Su
3. A video of the box-pushing robots from the above paper.
   "Cooperative transport by ants and robots", C. Ronald Kube and Eric Bonabeau, Robotics and Autonomous Systems 30(1-2), pages 85-101, 2000.
   Presenters: Pro: Sanford Freedman / Con: Charmy Chhichhia

A video of the soccer playing process from the perspective of a Sony dog robot.

1. "Distributed Mobile Robotics by the Method of Dynamic Teams", Jim Jennings and C. Kirkwood-Watts, Proceedings, International Symposium on Distributed Autonomous Robotic Systems, Karlsruhe, Germany, May 1998.
   Presenters: Pro: Zeeshan Maqbool / Con: Han-Nung Lin
2. "Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork", Peter Stone and Manuela Veloso, Artificial Intelligence, 110(2), pages 241-273, 1998.
   Presenters: Pro: David Stark / Con: Kevin Locklin
3. "Dynamic Sensor Planning and Control for Optimally Tracking Targets" by J. Spletzer and C. J. Taylor, International Journal of Robotics Research,22(1), January 2003, pages 7-20.
   Presenters: Pro: Jonathan Pearce / Con: Han-Nung Lin

Note: course evaluations will be filled out in this class session.

1. "Minimalism + Distribution = Supermodularity", by B. Donald, J. Jennings, and D. Rus, Journal of Experimental and Theoretical AI, 9(20-3), 1997, pages 293-321.
   Presenters: Pro: Mihir Sanghavi / Con: Kerry Connor
2. "Mathematical Model of Foraging in a Group of Robots: Effect of Interference", by K. Lerman and A. Galstyan, Autonomous Robots, 13(2), 2002, pages 127-141.
   Presenters: Pro: Shane Hoversten / Con: Shane Hoversten
3. "A formal framework for the study of task allocation in multi-robot systems", by B. Gerkey and M. Mataric´, International Journal of Robotics Research, 23(9):939-954, September 2004.
   Presenters: Pro: Shane Hoversten/ Con: Jonathan Pearce

RP: chapter 22

Note: During this class we will take the special opportunity to attend the following presentation as part of our class material: "Neurobotics: An Interdisciplinary Approach to Understanding and Assisting Humans" by Prof. Yoky Matsuoka, Carnegie Mellon University. More information is found here. We will walk to the talk (3-4pm) and return to class afterwards.
1. Humanoid Robotics, G. A. Bekey, Autonomous Robots: From Biological Inspiration to Implementation and Control, MIT Press, 2005, pages 441-471 (the whole chapter 13).
   Presenters: Pro: Usha Guduri / Con: Mihir Sanghavi
2. "A Self-Reconfigurable Modular Robot : Reconfiguration Planning and Experiments", by Eiichi Yoshida, Satoshi Murata, Akiya Kamimura, Kohji Tomita, Haruhisa Kurokawa and Shigeru Kokaji, International Journal of Robotics Research, 21(10):903-916, October 2002.
   Presenters: Pro: Han-Nung Lin/ Con: Nanjappan Muruganathan
3. "Towards terrain-aided navigation for underwater robots", Stefan Willams, Gamini Dissanayake and Hugh Durrant-Whyte, Advanced Robotics. 15(5) pages 533-549, 2001.
   Presenters: Pro: Charmy Chhichhia / Con: Selina Chu

Project presentations:
1. David Stark
2. Kevin Locklin
3. Kerry Connor
4. Charmy Chhichhia & Mark K. Kim
5. Nanjappan Muruganathan
6. Morgan Hendry
7. Sanford Freedman
8. Zeeshan Maqbool
9. Josh Wainer
10. Shane Hoversten
11. Jenny Chang Ho

Project presentations:
1. Usha Guduri
2. Mihir Sanghavi
3. Jonathan Pearce & Joey Wozniak
4. Jacob Madden
5. Kyong Il Kang
6. Han-Nung Lin
7. Selina Chu
8. Charles Su

Project reports due! No late reports accepted.

Course Project

The principles learned in this class will be applied in a required course project. Individual and team projects are both welcome. Team projects must follow the following guidelines:

1. Teams must not exceed three students;
2. The project scope must be a sum of the individual projects (i.e., a 3-person team must have a project that is 3X the scope of an individual project);
3. The individual contribution of each team member must be clear;
4. Individual and original (i.e., relevantly different based on the author's contribution) final reports must be turned in by each of the team members.

Each project is expected to be either an implementation of complex single robot (e.g., human-robot interaction), or of coordinated social behavior (e.g., cooperation on a task, competition, and/or learning) implemented on two or more robots (i.e., a robot team). Any of the test-beds below are appropriate.

Work with physical robots is very strongly encouraged in this course. Since work with physical robots is highly challenging, validation in simulation is required before moving on to a physical platform. To faciliate the transition, as well as the real-robotics relevance of the projects, we will use the Player/Stage/Gazebo suite, a rapidly-accepted standard for robot programming, found at http://playerstage.sourceforge.net/. Player is a general purpose language-independent network server for robot control. Stage is a Player-compatible high-fidelity indoor multi-robot simulation test-bed. Gazebo is a Player-compatible high-fidelity 3D outdoor simulation testbed with dynamics. Stage and Gazebo are the accepted simulation test-testbeds for this course. Using Player/Stage/Gazebo allows for direct porting to Player-compatible physical robots. Note that the syllabus gives specific dates by which simulation results are required before transitioning to physical robot hardware.

Robot hardware will be made available for use in the course. Platforms include a ActivMedia Pioneer 1 AT research grade robot, and 4 Evolution Robotics ER1 platforms. Aiming for real robot experiments is required, but it requires a compelling demonstration of working code in Stage/Gazebo to the TA and Professor by Nov 15th. You need to include this milestone in your project proposal and plan to make it. Obviously the various platforms have different capablities, (e.g., The ER1's are equipped with a web cam as the primary sensor, while the pioneer has no vision but a gripper and sonar ring). You are strongly encouraged to take all these factors into account when selecting a project to propose. Other important factors in project selection include the state of other support software (for example, porting from a Stage/Gazebo simulation to a Pioneer will likely be easiler than to an ER1 because of the state of the Player driver for the ER; you could propose to improve this status quo as part of your project).

Students who have existing access to physical robots through their research may use those physical systems as their project test-beds after prior approval by the TA or Professor to ensure course relevance. All projects, software and robot use is contingent on project proposal approval, as are any necessary project revisions.

Project proposals describing specific project goals, implementation plan and platform, and evaluation metrics are due in the first half of the semester, as stated in the syllabus. Guidelines to be followed in writing the proposal are found here. You can see an example of a well-written project proposal here.

Look here for a list of topics you should use as the basis for your project proposal. You may adapt/combine these ideas in your proposal, creativity within the realm of what is doable in the course of the semester is encouraged.

Final projects will be presented to the class on scheduled end-of-semester presentation days. Project presentations will be allotted 15-20 minutes, followed by a Q&A session. Live robot demos are encouraged but not required; if real robots are used in the project, videos of performace are expected. Helpful information for preparing your project presentation can be found here.

A detailed final paper is a required part of the course project. Since technical writing is one of the skills you are expected to practice in this course, the final report is modeled on a journal paper, i.e., on a technical paper reporting research results to a peer review audience. The paper should be formatted using standard ACM specifications, found here: http://www.acm.org/sigs/pubs/proceed/template.html. You may use either the ACM SIGS or the ACM Alternate style; they are almost identical. Both MS Word and LaTex templates are provided.

A hard-copy of the report is due on the last day of project presentations. Please also provide a URL with an on-line version of the report. Helpful information for preparing your project report can be found here.

An example of a successful project and project report can be found here. For examples of past projects and final papers, visit the previous course Web page. Not surprisingly, the bar for projects has been rising with each semester this class is taught.

Prof. Mataric´'s home page
USC Robotics Lab home page
USC Computer Science Department
Back to top