Autonomous Multirobot Systems Course

Autonomous Multirobot Systems 2015

Important Announcements

New:

• Be sure to bring laptop to class
• Please sign up with piazza for this course: [piazza.com]
• Project 1A description 2015_Project_1A due Friday January 23 at 11:55PM
• Project 1B description 2015_Project_1B due Friday February 6 at 11:55PM
• Research Presentation Overview 2015_Research_Presentation
• Example presentation: Media:Example-presentation.pptx
• Project 2 description 2015_Project_2 due Friday February 27 at 11:55PM
• Project 3 description 2015_Project_3 due Tuesday March 10 at 11:55PM
• Project Final description 2015_Project_Final due Thursday March 12 at 11:55PM
• Project 4 description 2015_Project_4 due Friday April 17 at 11:55PM

Course Overview

We will survey the inspiration and motivation for multirobot systems, the unique challenges in this field and the wide range of solutions developed thus far. Students will learn about the theoretical and algorithmic aspects of multi-agent and multi-robot systems, including communication, coordination and cooperation. This is a "hands-on" class requiring the students to develop and evaluate their own simulated multirobot system. Autonomous MultiRobot Systems is a graduate course, but undergraduate students with strong programming skills and a background in robotics or AI are welcome.

Topics to be covered:

• Multiagent architectures.
• Communication, cooperation and coordination in mulitrobot systems.
• Diversity.
• Taxonomies of multirobot systems and tasks.
• Adversarial domains including robot soccer.
• Example biological multiagent systems.
• Multirobot learning.

Who the Course is For

The course is open to and intended for graduate and upper level undergraduate students in Computer Science and Engineering

Prerequisites: Students should have strong programming skills and some familiarity with Linux. Here's a short test to check if you have strong programming skills: quiz. If you don't do well on that quiz, you should either drop the course, or be sure to plan so that you can devote extra time to the course.

Student Responsibilities

• Read the emails sent to the course email list. Check at least daily.
• Participate in class and via the piazza site.
• Don't plagiarize.

Course Logistics

• Instructor: Associate Professor Tucker Balch
  • Office hours: Tu/Th 1:30-2:30 (after class) or by appointment
  • firstname at cc.gatech.edu
  • phone 678-523-8685
• TA for Python issues:
  • Arindam Bose,
  • Office hours: 1.30-3.30 Tuesday outside class.
• TA for C and other issues:
  • Jayita Bhattacharya
  • Office hours: Wednesday 4:00-5:00 at CCB commons

Research Presentations

Visit this page for details on the research presentation component of this course: Multirobotics Course Research Presentations

Grading

• 70%: Projects
  • 10%: Project 1: Drunken Sailor
  • 10%: Project 2: ASCII Soccer
  • 10%: Project 3: Herds and flocks
  • 10%: Project 4: Predator / Prey
  • 30%: Final Project
• 20%: Presentations
  • 15% Best one
  • 5% Other one
• 10%: Class participation/pop quizzes
  • Drop worst 2

Late policy: -5% per day late

Plagiarism

Unless specifically stated otherwise I expect all code that you submit was written by you. I will present some libraries in class that you are allowed to use. Otherwise, all source code, images and write ups you provide should have been created by you alone.

What is allowed:

• Meeting with other students to discuss implementations. You should talk about solutions at the pseudo code level.
• Sharing snippets of code to solve specific (small) problems such as examples of how to address sections of arrays in Python. In this case the shared code should not be more than 5 lines.
• Searching the web for other solution outlines that you may draw on (but not copy directly). If you are inspired by a solution on the web, you MUST cite that code with comments in your code.

What is not allowed:

• Copying sections of code longer than 5 lines. Note that merely changing variable names does not suffice.
• Copying code from the web.
• Use of ideas from the web that are not cited in comments.

Week 1

Tuesday, 6 January, 2015
Course overview and intro
Definition of autonomy (NASA Video)
Example of multi agent coordination (Harvard Video)
Drunken Sailor description

Thursday 8 January 2015
Intro and discussion of ASCII Soccer
How does sensing affect necessity for diversity?

Week 2

Tuesday, 13 January, 2015
Introduction to the deliberative/reactive dichotomy
AI winter
Gray Walter
First intro to reactive robotics

Thursday 15 January
Class cancelled

Week 3

Tuesday 20 Jan
Overview and discussion of sailor project (no memory)
Bug algorithms: [by Howie Choset]

Thursday 22 Jan
Overview and discussion of sailor project (memory)
Build a map

Week 4

Tuesday 27 Jan
Lecture by Brian Hrolenok. Slides here
Slides on Reynold's Boids here

Thursday 29 Jan
Motor Schema Based Navigation (Arkin)
See especially section 4: AuRA: Principles and Practice in Review

Week 5

Tuesday 3 Feb
Motor Schemas Case Study: See Chapter 6 Balch Thesis
Motor Schema Formulations: See Appendix Balch Thesis

Thursday 5 Feb
Reinforcement Learning: Section 1, 3.1, 4.2, 5.2 Kaelbling Littman Moore

Week 6

Tuesday 10 Feb
Balch presents example presentation

• LaValle, Steven M. "Rapidly-Exploring Random Trees A Цew Tool for Path Planning." (1998). [[1]]
  
• Bruce, James, and Manuela Veloso. "Real-time randomized path planning for robot navigation." Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on. Vol. 3. IEEE, 2002. [[2]]

Thursday 12 Feb

• Arindam presents Python framework
  

Week 7

Tuesday 17 Feb
Team 1: Robot Soccer +5

• Primary paper: Biswas, Joydeep, et al. "Opponent-driven planning and execution for pass, attack, and defense in a multi-robot soccer team." Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems. International Foundation for Autonomous Agents and Multiagent Systems, 2014. http://www.cs.cmu.edu/~mmv/papers/14aamas-cmdragons.pdf
• Veloso, Manuela, Peter Stone, and Kwun Han. "The CMUnited-97 robotic soccer team: Perception and multi-agent control." Robotics and Autonomous Systems 29.2 (1999): 133-143. https://www.cs.utexas.edu/~pstone/Papers/bib2html-links/RAS99.pdf
• Wu, Shih-Lin, et al. "A Multi-agent Algorithm for Robot Soccer Games in Fira Simulation League." FIRA RoboWorld Congress USA. 2007. http://robogames.net/symposium/2007/07-118-Wu-ChangGungUniv-Multi-agentAlgorithmforRobotSocce.pdf
  

Team 2: Flocking, Herding Swarming +5

• Primary paper: Reynolds, Craig W. "Flocks, herds and schools: A distributed behavioral model." ACM Siggraph Computer Graphics 21.4 (1987): 25-34. http://www.cs.toronto.edu/~dt/siggraph97-course/cwr87/
  
• Moeslinger, Christoph, Thomas Schmickl, and Karl Crailsheim. "A minimalist flocking algorithm for swarm robots." Advances in Artificial Life. Darwin Meets von Neumann. Springer Berlin Heidelberg, 2011. 375-382. http://www.researchgate.net/profile/Thomas_Schmickl/publication/221531179_A_Minimalist_Flocking_Algorithm_for_Swarm_Robots/links/09e41507eadaa2b0cd000000.pdf
  
• Couzin, Iain D., et al. "Effective leadership and decision-making in animal groups on the move." Nature 433.7025 (2005): 513-516. http://www.uvm.edu/~pdodds/files/papers/others/2005/couzin2005.pdf
  

Check out this video: https://www.facebook.com/video.php?v=1087180774641291&fref=nf

Thursday 19 Feb
Team 6: Ant Navigation & Stigmergy +5

• Primary Paper: Beckers, Ralph, O. E. Holland, and Jean-Louis Deneubourg. "From local actions to global tasks: Stigmergy and collective robotics." Artificial life IV. Vol. 181. 1994. http://www.eecs.harvard.edu/~rad/courses/cs266-fall04/papers/beckers-alife94.pdf
  
• Beckers, Ralph, Jean-Louis Deneubourg, and Simon Goss. "Trails and U-turns in the selection of a path by the ant Lasius niger." Journal of theoretical biology 159.4 (1992): 397-415. http://www.eecs.harvard.edu/~rad/courses/cs266/papers/beckers-uturns.pdf
  
• Wehner, Rudiger. "Desert ant navigation: how miniature brains solve complex tasks." Journal of Comparative Physiology A 189.8 (2003): 579-588. http://www.mnf.uni-greifswald.de/fileadmin/Zoologisches_Museum/Hildebrandt/Dokumente/wehner03.pdf
  

Team 10: Honeybee Communication +5

• Primary paper: C. Grüter and W. Farina, The honeybee waggle dance: can we follow the steps?, Trends in Ecology & Evolution, vol. 24, no. 5, pp. 242-247, 2009.
• Bartholdi, T. Seeley, C. Tovey and J. Vate, The Pattern and Effectiveness of Forager Allocation Among Flower Patches by Honey Bee Colonies, Journal of Theoretical Biology, vol. 160, no. 1, pp. 23-40, 1993. http://www.sciencedirect.com/science/article/pii/S0022519383710027
  
• S. Nakrani and C. Tovey, From honeybees to Internet servers: biomimicry for distributed management of Internet hosting centers, Bioinspir. Biomim., vol. 2, no. 4, pp. S182-S197, 2007. http://iopscience.iop.org/1748-3190/2/4/S07
  
• M. Beekman, G. Sword and S. Simpson, Biological Foundations of Swarm Intelligence, in Swarm Intelligence, 1st ed., C. Blum and D. Merkle, Ed. Berlin: Springer-Verlag, 2008, pp. 3-42.
  

Week 8

Tuesday 24 Feb

• Recap of Project 2: Communication in Robot Soccer
  
• Overview of Project 3: Flocking and Herding
  

Team 9: Robot Formation Control

• Balch, Tucker, and Ronald C. Arkin. "Behavior-based formation control for multirobot teams." Robotics and Automation, IEEE Transactions on 14.6 (1998): 926-939. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=736776
• Ji, Meng, Abubakr Muhammad, and Magnus Egerstedt. "Leader-based multi-agent coordination: Controllability and optimal control." American control conference. 2006. http://users.ece.gatech.edu/~magnus/Papers/JiEgerstedtMuhammadACC06.pdf
• Lewis, M. Anthony, and Kar-Han Tan. "High precision formation control of mobile robots using virtual structures." Autonomous Robots 4.4 (1997): 387-403. http://link.springer.com/article/10.1023/A:1008814708459

Thursday 26 Feb
Team 3: Self Assembly and Modular Robotics 1

• White, P. J., Kris Kopanski, and Hod Lipson. "Stochastic self-reconfigurable cellular robotics." Robotics and Automation, 2004. Proceedings. ICRA'04. 2004 IEEE International Conference on. Vol. 3. IEEE, 2004. http://creativemachines.cornell.edu/papers/ICRA04_White.pdf
• Tolley, Michael T., et al. "Stochastic modular robotic systems: a study of fluidic assembly strategies." Robotics, IEEE Transactions on 26.3 (2010): 518-530. http://creativemachines.cornell.edu/sites/default/files/T-RO_2010_Tolley.pdf
• Tolley, Michael T., Jonathan D. Hiller, and Hod Lipson. "Evolutionary design and assembly planning for stochastic modular robots." New Horizons in Evolutionary Robotics. Springer Berlin Heidelberg, 2011. 211-225. http://www.michaeltolley.com/publications/IROS_2009_Tolley.pdf

Team 4: Self Assembly and Modular Robotics 2

• Yim, Mark, et al. "Modular self-reconfigurable robot systems [grand challenges of robotics]." Robotics & Automation Magazine, IEEE 14.1 (2007): 43-52. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4141032&tag=1
• J.W. Romanishin, K. Gilpin, and D. Rus, “M-Blocks: Momentum Driven, Magnetic, Modular Robots,” in 2013 IEEE/RSJ Conference on Intelligent Robots and Systems (IROS)., Tokyo, Japan, 2013, pp. 4288 - 4295 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6696971
• Felton et al., “Robotic Self – Assembly by Folding: A Printed Inchworm Robot,” in 2013 IEEE/RSJ Conference on Robotics and Automation (ICRA)., Karlsruhe, Germany, 2013, pp. 277 - 282 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6630588
  

Friday 27 Feb
Drop day

Week 9

Tuesday 3 March
Team 11: Path planning for robot teams: Cooperative/Deliberative

• Otte, Michael, and Nikolaus Correll. "Any-com multi-robot path-planning with dynamic teams: Multi-robot coordination under communication constraints."Experimental Robotics. Springer Berlin Tracts in Advanced Robotics, pp. 743-757, New Delhi, India, 2010. http://tinyurl.com/oygn8a4
• Luna, Ryan, and Kostas E. Bekris. "Efficient and complete centralized multi-robot path planning." Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on. IEEE, 2011. http://tinyurl.com/lt52szf
• Desaraju, Vishnu R., and Jonathan P. How. "Decentralized path planning for multi-agent teams with complex constraints." Autonomous Robots 32.4 (2012): 385-403. http://tinyurl.com/n6fo7pz

Team 8: Optimal Task Allocation

• Dias, M.B.; Zlot, Robert; Kalra, N.; Stentz, A., "Market-Based Multirobot Coordination: A Survey and Analysis," Proceedings of the IEEE , vol.94, no.7, pp.1257,1270, July 2006 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1677943&isnumber=35292
• Lagoudakis, Michail G., et al. "Simple auctions with performance guarantees for multi-robot task allocation." Intelligent Robots and Systems, 2004.(IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on. Vol. 1. IEEE, 2004. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1389434&isnumber=30275
• Petersen, K.; Kleiner, A.; von Stryk, O., "Fast task-sequence allocation for heterogeneous robot teams with a human in the loop," Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on , vol., no., pp.1648,1655, 3-7 Nov. 2013 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6696570&isnumber=6696319

Thursday 5 March
Team 7: Multi-robot team learning

• J. Hu and M. Wellman, ‘‘Multiagent reinforcement learning: Theoretical framework and an algorithm,’’ in Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann: San Francisco, CA, pp. 242–250, 1998. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.138.2589&rep=rep1&type=pdf
• M. Littman, ‘‘Friend-or-foe Q-learning in general-sum games,’’ in Proceedings of the Eighteenth International Conference on Machine Learning, Morgan Kaufmann, pp. 322–328, 2001. http://www.cs.rutgers.edu/~mlittman/papers/icml01-ffq.pdf
• A. Greenwald and K. Hall, ‘‘Correlated Q-learning,’’ in Proceedings of the Twentieth International Conference on Machine Learning, 2003. http://www.aaai.org/Papers/Symposia/Spring/2002/SS-02-02/SS02-02-012.pdf

Team 5: Coordinated control for sensing

• Simmons, Reid, et al. "Coordination for multi-robot exploration and mapping." AAAI/IAAI. 2000. http://www.aaai.org/Papers/AAAI/2000/AAAI00-131.pdf
• Pereira, Tiago, António Paulo Moreira, and Manuela Veloso. "Coordination for Multi-robot Exploration Using Topological Maps." CONTROLO’2014–Proceedings of the 11th Portuguese Conference on Automatic Control. Springer International Publishing, 2015. http://link.springer.com/chapter/10.1007/978-3-319-10380-8_49
• Dames, Philip, and Vijay Kumar. "Cooperative multi-target localization with noisy sensors." Robotics and Automation (ICRA), 2013 IEEE International Conference on. IEEE, 2013. http://www.seas.upenn.edu/~pdames/media/DamesKumarICRA2013TechnicalReport.pdf
• Marjovi, Ali, and Lino Marques. "Multi-robot topological exploration using olfactory cues." Distributed Autonomous Robotic Systems. Springer Berlin Heidelberg, 2013. 47-60. http://infoscience.epfl.ch/record/197455/files/chp3A10.10072F978-3-642-32723-0_4.pdf

Week 10

Tuesday 10 March
Class cancelled due to POTUS visit

Thursday 12 March
Team 2 Presentation 2

• Haque, Musad, Amirreza Rahmani, and Magnus Egerstedt. "Geometric foraging strategies in multi-agent systems based on biological models." Decision and Control (CDC), 2010 49th IEEE Conference on. IEEE, 2010

Spring Break

Monday 16 March - Friday 20 March

Week 11

Tuesday 24 March
Brian Hrolenok: Learning Models of Executable Behavior

Topic 2

Thursday 26 March
Misha Novitzky: Learning Recognizable Behaviors
Prof. Magnus Egerstedt

Week 12

Tuesday 31 March
Team 1 Presentation 2

• Wawerla, Jens, Gaurav S. Sukhatme, and Maja J. Mataric. "Collective construction with multiple robots." Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on. Vol. 3. IEEE, 2002. (Found at: http://www.sfu.ca/~jwawerla/papers/wawerla02construction.pdf)

Team 3 Presentation 2

• Werfel, Justin K., Kirsten Petersen, and Radhika Nagpal. "Distributed multi-robot algorithms for the TERMES 3D collective construction system." Institute of Electrical and Electronics Engineers, 2011. http://www.eecs.harvard.edu/ssr/papers/iros11wksp-werfel.pdf​

Thursday 2 April
Team 4 Presentation 2

• Wei, Hongxing, et al. "Sambot: A self-assembly modular robot for swarm robot." Robotics and Automation (ICRA), 2010 IEEE International Conference on. IEEE, 2010. http://sambot.buaa.edu.cn/webadmin/htmledit/UploadFile/201266193955593.pdf

Team 5 Presentation 2

• Lindsey, Quentin, Daniel Mellinger, and Vijay Kumar. "Construction with quadrotor teams." Autonomous Robots 33.3 (2012): 323-336. http://link.springer.com/article/10.1007/s10514-012-9305-0/fulltext.html

Week 13

Tuesday 7 April
Team 6 Presentation 2

• Ranjbar-Sahraei, B., Weiss, G., & Nakisaee, A. (2012). A multi-robot coverage approach based on stigmergic communication. In Multiagent System Technologies (pp. 126-138). Springer Berlin Heidelberg. http://www.weiss-gerhard.info/publications/MATES2012_RS_W_N.pdf

Team 7 Presentation 2

• Gregoire, Jean. Priority-based Coordination of Mobile Robots. Thesis. MINES Paristech, 2014. http://arxiv.org/pdf/1410.0879.pdf

Thursday 9 April
Team 8 Presentation 2

• Albin, A.; Weinberg, G.; Egerstedt, M., "Musical abstractions in distributed multi-robot systems," Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on , vol., no., pp.451,458, 7-12 Oct. 2012 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6385688&isnumber=6385431

Team 9 Presentation 2

• Coordination strategies for multi-robot exploration and mapping http://ijr.sagepub.com/content/early/2014/02/20/0278364913515309.full.pdf

Week 14

Tuesday 14 April
Team 10 Presentation 2
Team 11 Presentation 2

Thursday 16 April

ASCII Soccer Championship

Week 15

Tuesday 21 April
Professor Greg Turk
Topic 2

Thursday 23 April
Topic 1
Topic 2

Finals Week

27 April - 1 May