CS393R: Autonomous Robots -- Resources

Naos and UT Austin Villa

Week 0: Class Overview

Week 1: Vision basics

• Intro slides.
• Slides on physical cameras.
• Slides from CMU.
• Slides on autonomous color learning and illumination invariance.
• Slides on the RoboCup 2016 paper.
• The videos shown in class:
  Raw video
  Segmented video
  Segmented video over raw video
  Vision objects video
• The CMVision page.
• CMUcam
• Research pages on UT Austin Villa color mapping, autonomous color learning, and follow-ups: basic vision; autonomous color learning; illumination invariance; learning with illumination invariance; hybrid representations;
• Work by Dan Stronger on Model-based vision.
• The UT Austin Villa 2003 Four-Legged Team, Extended version
  The University of Texas at Austin, Department of Computer Sciences, AI Laboratory Tech report UT-AI-TR-03-304.
  Read Sections 4, 4.1-4.3, 14.
• The UT Austin Villa 2004 RoboCup Four-Legged Team: Coming of Age
  Read Sections 3, 3.1,3.2,3.3,3.4 (and the first couple of appendices if you're interested)
• Using Layered Color Precision for a Self-Calibrating Vision System
  Matthias Jungel
  Robocup 2004
• Bayesian Color Estimation for Adaptive Vision-based Robot Localization.
  D. Schulz and D. Fox
  Proceedings of IROS, 2004.
• B-Human Team Report and Code Release.
  Thomas Röfer et al.
• Vision Calibration and Processing on a Humanoid Soccer Robot.
  Piyush Khandelwal, Matthew Hausknecht, Juhyun Lee, Aibo Tian, and Peter Stone.
  Humanoids 2010 workshop on Humanoid Soccer Robots.
• Color Learning on a Mobile Robot: Towards Full Autonomy under Changing Illumination
  Mohan Sridharan and Peter Stone.
  In The 20th International Joint Conference on Artificial Intelligence, pp. 2212
• Autonomous Color Learning on a Mobile Robot
  Mohan Sridharan and Peter Stone
  In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.
• UT Austin Villa 2013 - Advances in Vision, Kinematics, and Strategy: Paper, Slides
  Jacob Menashe et al.
• Some vision-related papers from the 2018 RoboCup Symposium:
  A Deep Learning Approach for Object Recognition with NAO Soccer Robots.
  D. Albani, A. Youssef, V. Suriani, D. Nardi, and D.D. Bloisi
  Deep Learning for Semantic Segmentation on Minimal Hardware.
  Sander G. van Dijk and Marcus M. Scheunemann
  Designing Convolutional Neural Networks Using a Genetic Approach for Ball Detection..
  Georg Christian Felbinger, Patrick Gottsch, Pascal Loth, Lasse Peters, Felix Wege

Week 2: Introduction to motion control

• Slides on control: (pdf, ppt).
• I showed some slides (pdf) from lecture 2 of the 2008 class at CMU.
• Another tutorial on control by Thomas Dean and Michael Wellman.
• Some videos on control
  • closed loop control
  • PID control - a brief introduction
  • Simple Examples of PID control
  • Effects of different gains for P, PI, PD, and PID
  • Some PID tuning heuristics
• A page to play with some control parameters.
• PID control on a quadrotor
• A Braitenberg simulator.
• The whole Braitenberg book
• A video of a Braitenberg vehicle #2
• A video of the CMUnited team that used the Braitenberg love vehicle.
• The UT Austin Villa 2003 Four-Legged Team, Extended version
  The University of Texas at Austin, Department of Computer Sciences, AI Laboratory Tech report UT-AI-TR-03-304.
  Sections 5.1.1-5.1.3.
• A Model-Based Approach to Robot Joint Control
  Daniel Stronger and Peter Stone.
  In Daniele Nardi, Martin Riedmiller, and Claude Sammut, editors, RoboCup-2004: Robot Soccer World Cup VIII, pp. 297
• Learning and Using Models of Kicking Motions for Legged Robots.
  Sonia Chernova and Manuela Veloso
  In Proceedings of International Conference on Robotics and Automation (ICRA'04), May 2004.

Week 3: Walking

• Slides on ZMP: (pdf)
• Slides on the learned Aibo walk (starting at slide 57): (pdf)
• Slides on the stable version: (pdf)
• A Closed-loop 3D-LIPM Gait for the RoboCup Standard Platform League
  Graf and Rofer
  RoboCup 2010 Symposium
• A Robust Closed-Loop Gait for the Standard Platform League Humanoid
  Graf, Hartle, Rofer, and Laue
  RoboCup 2009 Symposium
• Omnidirectional Walking using ZMP and Preview Control for the NAO Humanoid robot
  Strom, Slavov, and Chown
  RoboCup 2009 Symposium
• Applying Dynamic Walking Control for Biped Robots
  Stefan Czarnetzki, Sören Kerner, Oliver Urbann
  RoboCup 2009 Symposium
• A Center of Mass Observing 3D-LIPM Gait for the RoboCup Standard Platform League Humanoid
  Graf and Rofer
  RoboCup 2011 Symposium
• Zero-Moment Point - Thirty Five Years of Its Life
  Vukobratovic, M. and Borovac, B.
  International Journal of Humanoid Robotics, Vol.1, No. 1, pp.157-173, 2004.
• Biped Walking Pattern Generation by using Preview Control of Zero-Moment Point
  Kajita, S., Kanehiro, F., Kaneko, K., Fujiwara, K., Harada, K., Yokoi, K. and Hirukawa, H.
  ICRA 2003.
• The Nao Devil's walking paper that uses ZMP and preview control
• Observer based biped walking control, a sensor fusion approach
  Oliver Urbann and Stefan Tasse
  Autonomous Robots, July 2013
  The video of the evaluation for this paper
  a walking video from RoboCup 2015
• Machine Learning for Fast Quadrupedal Locomotion
  Nate Kohl and Peter Stone
  In The Nineteenth National Conference on Artificial Intelligence, pp. 611-616, July 2004.
• A paper on also optimizing for stability.
• A paper on optimizing ball capturing.
• A reference on Nelder-Mead (aka Amoeba).
• A reference on Powell's method
• Videos from the omni-directional walk learning paper
• Earlier work on transfering what was learned in simulation back to the real robots
• Big dog in action.
• A 2-legged follow-up to big dog, Petman
• Their latest quadruped: Wildcat
• Asimo videos. Here's one where it walks up and down stairs. Here's some additional information on the walk.
• Asimo playing soccer with Pres. Obama in 2014
• A Nao climbing stairs
• Kuka balancing robot
• Luis Sentis' Human Centered Robotics Lab in the ME department here at UT does some cool research on biped locomotion.
• RoboCup 2009 humanoid league videos.
• RoboCup 2010 humanoid league videos.
• Russ Tedrake's videos.
• Chris Atkeson's course on Legged Locomotion
• The development of Honda humanoid robot
  Hirai, K. and Hirose, M. and Haikawa, Y. and Takenaka, T.
  ICRA 1998.
• Legged robots that balance.
  Raibert, M. H.
  
• Virtual Model Control of a Bipedal Walking Robot
  Pratt, J., Dilworth, P. and Pratt, G.
  ICRA 1997.
• Hybrid Zero Dynamics of Planar Biped Walkers
  Westervelt, E.R., Grizzle, J.W. and Koditschek, D.E.
  IEEE Trans. on Automatic Control, Vol.48, No.1, pp.42-56, 2003.
• Modeling and Control of Multi-Contact Centers of Pressure and Internal Forces in Humanoid Robots
  Luis Sentis, Jaeheung Park, and Oussama Khatib.
  IROS 2009.
• The 2010 rUNSWift team report has more details on their walk in Chapter 6.
• Their 2011 Humanoids paper on using RL to control a biped's feet.
• Boston Dynamics and Agility Robotics use Raibert-like methods. The Simbicon algorithm extends those kind of controllers and also summarizes Raibert-like methods.
• The capture point method for quasi static locomotion.
• A paper on a whole-body walking controller (posted on Piazza).
• A good explanation of CoP vs. ZMP
• Creation of a Fine Controlled Action for a Robot.
  Ellie Lin, 2003
  

Week 4: Probability/Sensing

Week 5: Kalman Filters

Week 6: Localization

• Slides from chapter 4 of the book: (ppt).
• Slides about the legged localization paper below: (pdf).
• Slides about the Hester and Stone paper below: (pdf).
• Some videos from the textbook authors.

Additional readings:

• Practical Vision-Based Monte Carlo Localization on a Legged Robot.
  Mohan Sridharan, Gregory Kuhlmann, and Peter Stone.
  In IEEE International Conference on Robotics and Automation, April 2005.
• Negative Information and Line Observations for Monte Carlo Localization.
  Todd Hester and Peter Stone.
  In IEEE International Conference on Robotics and Automation, May 2008.
• Adapting the Particle Size in Particle Filters Through KLD-Sampling
  Dieter Fox.
  In the International Journal of Robotic Research, IJRR, 2003.
  (An excellent description of robot localization - has some overlap with the textbook)
• Vision-Based Fast and Reactive Monte-Carlo Localization
  Thomas Roefer and Matthias Jungel.
  In the IEEE International Conference on Robotics and Automation, ICRA, 2003.
  (Another team's implementation details are in Sections III and IV)
• Fast and Robust Edge-Based Localization in the Sony Four-Legged Robot League
  Thomas Roefer and Matthias Jungel.
  In the Seventh International RoboCup Symposium, 2003.
  (On using field edges in localization)
• Making Use Of What You Don't see: Negative Information in Markov Localization
  Jan Hoffmann, Michael Spranger, Daniel Gohring and Matthias Jungel.
  In the IEEE International Conference on Intelligent Robots and Systems, IROS, 2005.
  (Recent article on using negative information in localization)
• Multiple Model Kalman Filters: A Localization Technique for RoboCup Soccer
  Quinlan and Middleton.
  

Week 7: Action and sensor models

• Maximum Likelihood Estimation of Sensor and Action Model Functions on a Mobile Robot.
  Daniel Stronger and Peter Stone.
  IROS 2008.
  This is essentially ASAMI in 2 dimensions.
• A paper on learning the degree of a polynomial autonomously.
• A Model-Based Approach to Robot Joint Control
  Daniel Stronger and Peter Stone.
  In Daniele Nardi, Martin Riedmiller, and Claude Sammut, editors, RoboCup-2004: Robot Soccer World Cup VIII, pp. 297
  Slides on the paper: (pdf).
• A paper that was based on a class project in the 2005 class that extended the above joint modeling paper:
  A Neural Network-Based Approach to Robot Motion Control.
  Uli Grasemann, Daniel Stronger, and Peter Stone.
  In Ubbo Visser, Fernando Ribeiro, Takeshi Ohashi, and Frank Dellaert, editors, RoboCup-2007: Robot Soccer World Cup XI, Lecture Notes in Artificial Intelligence, pp. 480
• Learning and Using Models of Kicking Motions for Legged Robots
  Sonia Chernova and Manuela Veloso
  In Proceedings of International Conference on Robotics and Automation (ICRA'04), May 2004.
• Instance-Based Action Models for Fast Action Planning.
  Mazda Ahmadi and Peter Stone.
  In Ubbo Visser, Fernando Ribeiro, Takeshi Ohashi, and Frank Dellaert, editors, RoboCup-2007: Robot Soccer World Cup XI, Lecture Notes in Artificial Intelligence, pp. 1-16.
• The Spatial Semantic Hierarchy.
  Ben Kuipers
  AIJ, 2000.

Week 8: Path Planning

Week 9: Behavior Architectures

Week 10: Robot Learning

Week 11: Applications

Week 12: Social Implications

Week 13: Multi-Robot Coordination