Reading Group

Administrative Stuff

Machine Learning:

• We will be meeting in HRL every Wednesday at noon.
• Feel free to bring lunch and/or other snackies.

Force Control of Manipulators:

• We will meet on Mondays at 11:00.

Schedule

Machine Learning:

• 6/9/2010: Jan Peters, Sethu Vijayakumar, Stefan Schaal. Reinforcement Learning for Humanoid Robotics. International Conference on Humanoid Robots 2003. pdf
• 6/11/2010, 6/16/2010 Kober, J.; Peters, J. (2009). Learning Motor Primitives for Robotics, Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) pdf
  • Peter Pastor's slides on Dynamic Motor Primitives
  • Background paper on DMP (skip to page 435) pdf
  • Why DMP? Refer to bullets on page 10 & 11 of pdf
• 6/23/2010 Jens Kober, and Jan Peters. Policy Search for Motor Primitives in Robotics. NIPS 2008 pdf
• 6/30/2010 Thomas Ruckstieb, Martin Felder, Jurgen Schmidhuber. State-Dependent Exploration for Policy Gradient Methods. Machine Learning and Knowledge Discovery in Database (2008) pdf

Force Control of Manipulators:

Notes from JK Salisbury paper. June 21

• Jun 21, 2010: J.K. Salisbury, "Active stiffness control of a manipulator in Cartesian coordinates," Proc. 19th IEEE Conference on Decision and Control, 1980.
• Jun 25, 2010:
  • Look at the thumbnail, Notes from JK Salisbury paper.
  • Stuart Glaser's (Stu's) controller: There's no paper. For citations, please cite the wiki page for the teleop_controllers package and the stack version (pr2_cockpit 0.1). The best reference for how it works is the code (attached). The controller is a riff off of "Simplified Acceleration Based Control Variation 1" from this paper (Comparative experiments on task space control with redundancy resolution by Nakanishi, Cory, Mistry, Peters and Schaal, IROS 2005)

• Discussion on June 25, 2010
• 

  Equations from Stu's code

• 

  Our derivation

• July 1, 2010:
  • Read the PR1 paper (pdf)
  • Old paper that the PR1 paper cites for gravity compensation with springs. (pdf)(Not very helpful)
  • Continue discussion on Ken Salisbury paper and EPC.

• July 1, 2010
• 

  Starter (moving tip of spring along a line)

• 

  Simpler Case than the paper: Moving the tip in a circle but a == b

• 

  Elegant and simple, yet complete derivation for one link is in this paper (pdf)

• Multiple Contacts: July 1, 2010
• Multi contact 1.jpg

  starting to think about multiple contacts. Also, todos for next time.

Authors to Read

Machine Learning:

• Jan Peters: http://www-clmc.usc.edu/~jrpeters/
• Willow Peeps
• Fernando De la Torre
• Stefan Schaal: http://www-clmc.usc.edu/~sschaal/
• Chris Atkeson: http://www.cs.cmu.edu/~cga/
  • Martin Stolle and Christopher Atkeson. Finding and transferring policies using stored behaviors. Autonomous Robots pdf
• Chad Jenkins: http://www.cs.brown.edu/~cjenkins/
• Aude Billard: http://lasa.epfl.ch/people/member.php?SCIPER=115671
• Christian Ott: http://www.robotic.de/Christian.Ott/

Force Control of Manipulators:

For initial background

• Neville Hogan
• Ken Salisbury
• D.E. Whitney
• Oussama Khatib: http://cs.stanford.edu/groups/manips/publications

Suggested Papers

Machine Learning:

• Fernando De la Torre's component analysis paper.
• Choon Hui Teo, S. V. N. Vishwanathan, Alex J. Smola, and Quoc V. Le. Bundle Methods for Regularized Risk Minimization. Journal of Machine Learning Research, 11:311–365, January 2010. pdf
• Jan Peters, Stefan Schaal. Policy Gradient Methods for Robotics. IROS 2006. pdf
• Jan Peters, Stefan Schall. Learning to Control in Operational Space. IJRR 08. download from library website
• Todd Hester, Michael Quinlan, and Peter Stone. Generalized Model Learning for Reinforcement Learning on a Humanoid Robot. In IEEE International Conference on Robotics and Automation (ICRA), May 2010. pdf video related work
• Jonas Buchli, Evangelos Theodorou, Freek Stulp, Stefan Schaal. Variable Impedance Control A Reinforcement Learning Approac. Robotic Systems Science. pdf
• Detry,R.; Baseski, E.; Popovic, M.; Touati, Y.; Krueger, N.; Kroemer, O.; Peters, J.; Piater, J. (2010). Learning Continuous Grasp Affordances by Sensorimotor Exploration, From Motor Learning to Interaction Learning in Robots, Springer Verlag, 264. pdf

Force Control of Manipulators:

• Neville Hogan, Impedance control: an approach to manipulation: parts 1,2, 3

Skin Sensing

• Tactile Sensing—From Humans to Humanoids. Dahiya, R.S. Metta, G. Valle, M. Sandini, G., Feb 2010, Volume: 26 Issue: 1. On page(s): 1 - 20 link

Task-relevant Perception

• Kei Okada, Mitsuharu Kojima, Satoru Tokutsu, Yuto Mori, Toshiaki Maki, Masayuki Inaba : "Task Guided Attention Control and Visual Verification in Tea Serving by the Daily Assistive Humanoid HRP2JSK", In Proceedings of The 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2008), pp 1551-1557, 2008. ((The 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems Best Robocup Award)) pdf
• Kei Okada, Mitsuharu Kojima, Yuichi Sagawa, Toshiyuki Ichino, Kenji Sato, Masayuki Inaba : "Vision based behavior verification system of humanoid robot for daily environment tasks", 2006 6th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2006), pp 7-12, 2006. (2006 6th IEEE-RAS International Conference on Humanoid Robots Best Paper Award) pdf