CS393R: Autonomous Robots -- Resources

CS393R: Autonomous Robots -- Resources

Naos and UT Austin Villa

  • UT Austin Villa
  • Softbank Robotics
  • Softbank Nao H25 Datasheet
  • Codebase on GitHub
  • Lab/Robot Setup
  • Tutorial
  • Lab intro slides

  • Week 0: Class Overview

  • Slides from Thursday: (pptx).
  • RoboCup 2018 Final Match (NAO HTWK vs. B-Human)
  • RoboCup 2018 League Play Match (UT Austin Villa vs. RunSwift)
  • RoboCup 2016 Final Match (UT Austin Villa vs. B-Human)
  • RoboCup 2012 Final match (UT Austin Villa vs. B-Human)

  • Week 1: Vision basics

    Week 2: Introduction to motion control

    Week 3: Walking

    Week 4: Probability/Sensing

  • A Bayes' Theorem explanation.
  • Another (with a calculator).
  • Andrew Moore's tutorial on probability density functions, including variance/covariance.
  • A Udacity course that covers some of this material.
  • Some videos from Matt Mason's group on actions that reduce uncertainty

  • Week 5: Kalman Filters

  • Slides from Tuesday on Kalman filters: (ppt, pdf).
  • Slides from the book: (ppt, pdf).
  • wikipedia has a good 2D example.
  • More details from Welch and Bishop
  • A youtube tutorial endorsed by a student in the previous class.
  • Three other resources endorsed by students:
  • http://greg.czerniak.info/guides/kalman1/
  • https://www.udacity.com/wiki/cs373/kalman_filter_matrices
  • Kalman filter for dummies
  • A paper about the unscented Kalman Filter(UKF) and how it improves upon the EKF for estimation of non-linear systems.
  • A RoboCup application of Kalman filters (see Section 2.3).
  • A description of the use of a Kalman Filter for ball tracking in RoboCup: Han and Veloso, 1997.
  • Newcastle RoboCup Team Report describing the Kalman Filter for localization and ball tracking. (See section 4). Quinlan et al, 2005.
  • CWMtx C++ Matrix library.
  • A list of applications
  • An informal description of the UT Austin Villa state tracking method as of 2018, courtesy of Jake Menashe.

  • Week 6: Localization

    Additional readings:

    Week 7: Action and sensor models

  • Slides on ASAMI: (pdf)
  • Some slides (pdf) from lecture 2 of the 2008 class at CMU.
  • Additional readings:

    Week 8: Path Planning

  • Slides from the intro lecture of Howie Choset's motion planning course. See also his slides on A*, D* lite, and sampling based methods.
  • Another presentation on D* lite.
  • UTSeaSim, which uses RRT for path planning. The slides.
  • Slides from Pieter Abbeel on motion planning that include information on PRMs and RRT*.
  • Urban challenge path planning paper:
    Practical Search Techniques in Path Planning for Autonomous Driving
  • Video of a holonomic robot
  • A* visualization
  • RRT page
  • An extension of RRT that interleaves execution
    Real-Time Randomized Path Planning for Robot Navigation
    James Bruce, Manuela Veloso
  • Karaman and Frazzoli introduce an algorithm that's asymptotically optimal called RRT*.
  • A paper on RRT with dynamic obstacles: Multipartite RRTs for Rapid Replanning in Dynamic Environments. Zucker et al.
  • A page on Voronoi planning
  • Sensor-Based Exploration: The Hierarchical Generalized Voronoi Graph
    Choset and Burdick
  • Voronoi page with applet
  • Three papers on the potential field approach: Borenstein, 1991; Konolige, 2000;
    Numerical Potential Field Techniques for Robot Path Planning: Barraquand, Langlois, Latombe
  • Craig Reynolds' boids (especially click on "steering")
  • Andrew Ng's A* search notes
  • Slides from Johns Hopkins and CMU on bug algorithms
  • Sven Koenig's site on LPA* and D* lite
  • Pieter Abbeel's paper on Environmentally Guided RRT's (a video of the talk is available from his homepage)
  • A paper by Lo, Zhang, and Stone on integrating task and motion plannning:
    PETLON: Planning Efficiently for Task-Level Optimal Navigation.
    In Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), July 2018.
    (Winner of the Best Robotics Paper Award at AAMAS 2018)
    the slides.
  • A paper by Robert C. Holte, Ariel Felner, Guni Sharon, Nathan R. Sturtevant on bidirectional heuristic search:
    Bidirectional Search That Is Guaranteed to Meet in the Middle
    (Winner of the Outstanding Paper Award at AAAI 2016)

  • Week 9: Behavior Architectures

  • Some planning slides (postscript).
  • A journal article with more details on the initial subsumption implementation:
    Brooks, R. A. "A Robust Layered Control System for a Mobile Robot", IEEE Journal of Robotics and Automation, Vol. 2, No. 1, March 1986, pp. 1423; also MIT AI Memo 864, September 1985. The detail slides from that article.
  • A radio interview with Rodney Brooks.
  • A journal article extending subsumption to multi-robot systems:
    Designing and Understanding Adaptive Group Behavior.
    Maja J Mataric.
    Adaptive Behavior 4:1, Dec 1995, 51-80.
  • Intelligence without Robots (A Reply to Brooks) by Oren Etzioni. AI Magazine, 14(4), December 1993.
  • Pengo
  • Experiences with an Architecture for Intelligent, Reactive Agents.
    R. Peter Bonasso, R. James Firby, Erann Gat, David Kortenkamp, David P. Miller, and Marc G. Slack.
    JETAI 9(2/3):237-256, 1997.
  • A paper on an architecture for action selection using value functions that was applied in simulated soccer. The accompanying slides.

  • Week 10: Robot Learning

  • Learning Multi-Modal Grounded Linguistic Semantics by Playing "I Spy"
    Language learning on a robot.
    Thomason, Sinapov, Svetlik, Stone, and Mooney, 2017
  • Generalized Model Learning for Reinforcement Learning on a Humanoid Robot
  • Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection"
    Multiple robots learning in parallel.
    Levine, Pastor, Krizhevsky, Quillen, 2017
    Google's blog with videos
  • Learning and generalization of motor skills by learning from demonstration
    Dynamic motion primitives for representation and learning.
    Pastor, Hoffmann, Asfour, Schaal, 2009
  • Keyframe-based learning from demonstration
    Learning from human demonstrations.
    Akgun, Cakmak, Jiang, Thomaz, 2011
  • End-to-end Training of Deep Visuomotor Policies
    Guided policy search on a robot using images as input.
    Levine, Finn, Darrell, Abbeel, 2016
  • Policy search for motor primitives in robotics
    Kober and Peters, 2008
  • My RL course
  • Scott Niekum's course
  • Anca Dragan's course at UC Berkeley
  • Learning parameterized motor skills on a humanoid robot
    da Silva, Baldassarre, Konidaris, Barto, 2014
  • Sergey Levine's Deep RL course at Berkeley (model-based slides relevant to GPS)
  • An explanation of iLQR.

  • Week 11: Applications

  • Kurt Dresner's slides on AIM. (keynote version)
  • More recent AIM slides (ppt version)
  • JoFR 2008 Special Issue on the 2007 DARPA Urban Challenge, Part I
  • JoFR 2008 Special Issue on the 2007 DARPA Urban Challenge, Part II
  • JoFR 2008 Special Issue on the 2007 DARPA Urban Challenge, Part III
  • Festo flying/swimming robots
  • A very fast robot hand
  • Anytime D*
  • The 2016 report from the 100 Year Study on AI
  • Applications papers and related resources from a previous version of this course
  • Cloth Grasp Point Detection based on Multiple-View Geometric Cues with Application to Robotic Towel Folding.
    Jeremy Maitin-Shepard, Marco Cusumano-Towner, Jinna Lei and Pieter Abbeel.
    In the proceedings of the International Conference on Robotics and Automation (ICRA), 2010.
  • Autonomous helicopter control, Ng et al., 2004.
  • PEGASUS: A policy search method for large MDPs and POMDPs, Andrew Y. Ng and Michael Jordan. In Uncertainty in Artificial Intelligence, Proceedings of the Sixteenth Conference, 2000.
  • Andrew Ng's robot videos.
  • Robot air hockey, Bentivegna and Atkeson, 2002.
  • A paper about the Nursebot project.
  • HERB 2.0: Lessons Learned from Developing a Mobile Manipulator for the Home.
    Siddhartha S. Srinivasa, Dmitry Berenson, Maya Cakmak, Alvaro Collet, Mehmet R. Dogar, Anca D. Dragan, Ross A. Knepper, Tim Niemueller, Kyle Strabala, Mike Vande Weghe, Julius Ziegler
    Proceedings of the IEEE, Vol. 100, No. 8, JULY 2012.

  • Week 12: Social Implications

  • Bill Joy's TED talk from 2006.
  • Illah Nourbakhsh's course on ethics and robotics
  • Ron Arkin's tech report on embedding ethics in robots.
  • Some writings on the singularity: a resesarch institute, and Ray Kurzweil's page.
  • Jordan Pollack's GOLEM project: evolving physical robots.
  • The Lifeboat Foundation is dedicated to assessing and protecting against threats to humanity.
  • Stephen Goose on The Case for Banning Killer Robots: Point in CACM, Dec. 2015.
  • Ron Arkin on The Case for Banning Killer Robots: Counterpoint in CACM, Dec. 2015.
  • An arms-control advocacy video on slaughterbots put out by Future of Life Institute.

  • Week 13: Multi-Robot Coordination

  • Slides on ACLs and joint intentions: (pdf)
  • Slides on MAS and pursuit domain: (pdf)
  • Swarmanoid: a novel concept for the study of heterogeneous robotic swarms.
    Marco Dorigo et al.
    IEEE Robotics and Automation
  • Robot surveillance, Ahmadi and Stone, 2005.
  • Slides on continual area sweeping (pdf)
  • Videos of continual area sweeping.
  • Current Research in Multi-robot Systems.
    Lynne Parker
    ALife Robotics, 2003.
  • Theoretical Analysis of the Multi-agent Patrolling Problem.
    Yann Chevaleyre.
    IAT '04.
  • A fault-tolerant modular control approach to multi-robot perimeter patrol.
    Alessandro Marino, Lynne E. Parker, Gianluca Antonelli, Fabrizio Caccavale and Stefano Chiaverini.
    ROBIO '09.
  • Flexible Teamwork in Behavior-Based Robots.
    Gal A. Kaminka and Inna Frenkel.
    In Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI-05) , 2005.
  • A Realistic Model of Frequency-Based Multi-Robot Fence Patrolling.
    Yehuda Elmaliach, Asaf Shiloni, and Gal A. Kaminka.
    In Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-08)
    It's OK to skim sections 3.2 and 3.3. Make sure to understand what they analyze and how. It's OK not to follow the full details of the analysis (though it all should be accessible).
  • Follow-up and other interesting papers from Gal Kaminka's lab
  • Swarmanoid, winner of the 2011 AAAI video competition. And another video.
  • James McLurkin's work on multi-robot systems.
  • Collision avoidance with ClearPath and ORCA.
  • Video: Swarm robotics -- from local rules to global behaviors, Magnus Egerstedt, TEDxEmory
  • A video from his lab.
  • Kiva systems demo
  • Interview with Mick Mountz, Kiva CEO.
  • Kiva homepage.
  • Video about Kiva from a founder of the company.
  • Video about a Kiva robot.
  • Video of Kiva warehouse robots at work.
  • Video about Kiva robots at Zappos.
  • Video showing a teddy bear being shipped at Amazon using Kiva robots.
  • Video of Kiva dancing nut cracker robots.
  • Amazon Picking Challenge.
  • A recent TED talk by Raff D'andrea on his quadrotors research.
  • Trail-Laying Robots for Robust Terrain Coverage.
    J. Svennebring and S. Koenig.
    In Proceedings of the International Conference on Robotics and Automation (ICRA), 2003.
  • Sven Koenig's Ant Robotics page, including a video from the paper.
  • The Generation of Bidding Rules for Auction-Based Robot Coordination.
    C. Tovey, M. Lagoudakis, S. Jain and S. Koenig.
    In Multi-Robot Systems: From Swarms to Intelligent Automata, L. Parker, F. Schneider and A. Schultz (editor), 3-14. Springer, 2005.
  • Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork.
    Stone and Veloso.
    AIJ, 1999.
    See sections 1-4, 6.1 and 7.1.
  • Slides on PTS domains, locker-room agreements (ps)
  • Slides on MAS in pursuit domains (ps)
  • self-configuring robots from USC.
  • On Team Formation.
    Cohen, P. R., Levesque, H. R., and Smith, I.
    in Hintikka, J. and Tuomela, R. (Eds.) Contemporary Action Theory. Synthese, 1997.
  • Ad Hoc Teamwork for Leading a Flock.
    Katie Genter, Noa Agmon, and Peter Stone.
    In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2013), May 2013.
  • Reciprocal n-body collision avoidance
    Jur van den Berg, Stephen J. Guy, Ming Lin, and Dinesh Manocha
    in Cedric Pradalier, Roland Siegwart, and Gerhard Hirzinger (eds.)
    Robotics Research: The 14th International Symposium ISRR, Springer Tracts in Advanced Robotics, vol. 70, Springer-Verlag, May 2011, pp. 3-19.
  • Lifelong Path Planning with Kinematic Constraints for Multi-Agent Pickup and Delivery.
    Hang Ma, Wolfgang Honig, T. K. Satish Kumar, Nora Ayanian, Sven Koenig.
    AAAI Conference on Artificial Intelligence (AAAI), Honolulu, Hawaii, Jan 2019.
  • SCRAM for role assignment in robot soccer.
  • Peter Stone and Manuela Veloso.
    Multiagent Systems: A survey from a machine learning perspective
    Autonomous Robots, 8(3):345

  • [Back to Department Homepage]

    Page maintained by Peter Stone
    Questions? Send me mail