Proseminar Robot Learning - WS 2014/15
Proseminar Robot Learning
Requirements & Information
- Organizer: Prof Dr. Wolfram Burgard
- Co-Organizers: Andreas Eitel, Nichola Abdo, Markus Kuderer, Ayush Dewan, Chau Do, Tim Welschehold.
- The Proseminar will be held as a "Blockseminar" in February 2015 (there will be a doodle with all participants).
- Please register via the online registration system.
- The first meeting was on Tuesday, October 28, 10.00 a.m. in room 02-017, building 52 .
- Students are requested to prepare a talk of 30 minutes and to write a summary. Both can be done in English or German.
- Topics will be assigned in the first meeting. Please contact your supervisor for details on literature.
- The summaries should be 7 pages long at maximum (latex, a4wide, 11pt) not counting the bibliography and figures. Significantly longer summaries will not be accepted. A LaTeX template can be downloaded here.
- Please fill out the assignment form and hand it to Andreas Eitel until Friday, October 31 in room 1006 (UG), building 79 .
Slides from the first meeting.
- Please contact your supervisor for details on literature.
- Wolfram Burgard will give a lecture on "How to give a presentation".
This lecture will take place on Wednesday, January 14, 10.00 s.t. in room 00-034, building 51.
- The Proseminar will take place on:
- February 2, 9.00 to 12.00.
- Location for the Proseminar: Room 00-014 , Building 078
- Students will be assigned to one meeting, a detailed schedule will be announced soon.
- The first version of the summary must be sent to the superviser on 13.Feb.2013. You can revise the summary once according to the comments of your supervisor. The final version has to be submitted by 20.Feb.2013.
- E. Klingbeil, B. Carpenter, O. Russakovsky, and A.Y. Ng.
Autonomous Operation of Novel Elevators for Robot Navigation
material: Markov models and hidden Markov models, introduction to hidden Markov models , EM algorithm
[Jannik Schoenartz, supervisor: Wolfram Burgard]
- E. Brunskill, T. Kollar and N. Roy.
Topological Mapping Using Spectral Clustering and Classification
material: spectral clustering, boosting tutorial
[Philipp Jund, supervisor: Nichola Abdo]
- M. Bennewitz, W. Burgard and S. Thrun.
Using EM to Learn Motion Behaviors of Persons with Mobile Robots
material: learning motion patterns of persons, EM algorithm
[Dustin Kunzelmann, supervisor: Wolfram Burgard]
- B. Ziebart et al.
Planning-based Prediction for Pedestrians
material: maximum entropy inverse reinforcement learning
[William Weigold, supervisor: Markus Kuderer]
- J.P. Mendoza, M. Veloso and R. Simmons.
Motion Interference Detection in Mobile Robots
material: hidden Markov models
[Didier Bissel, supervisor: Chau Do]
- M. Gemici and A. Saxena.
Learning Haptic Representation for Manipulating Deformable Food Objects
material: Dirichlet process, support vector regression
[Simon Geitliner, supervisor: Andreas Eitel]
- A. Boularias, O. Kroemer and J. Peters.
Learning Robot Grasping from 3-D Images with Markov Random Fields
material: learning associative Markov networks , discriminative learning of Markov random fields
[Michael Scherle, supervisor: Andreas Eitel]
- I. Lenz, H. Lee and A. Saxena.
Deep Learning for Detecting Robotic Grasps
material: UFLDL tutorial, section: sparse autoencoder
[Felix Goepfert, supervisor: Andreas Eitel]
- A. Ijspeert, J. Nakanishi and S. Schaal.
Movement Imitation with Nonlinear Dynamical Systems in Humanoid Robots
[material: locally weighted regression
[Joshua Marben, supervisor: Nichola Abdo]
- P. Pastor, H. Hoffmann, T. Asfour and S. Schaal.
Learning and Generalization of Motor Skills by Learning from Demonstration
material: least squares, dyanmic movement primitives
[Joshua Stork, supervisor: Tim Welschehold]
- S. Calinon, Z. Li, J.G. Rogers and H.I. Christensen.
A Conditional Random Field Model for Place and Object Classification
material: introduction to conditional random fields , relevance vector machine , bag of words
[Colin Seibel, supervisor: Ayush Dewan]
- L. Bo, X. Ren and D. Fox.
Unsupervised Feature Learning for RGB-D Based Object Recognition
material: hierarchical matching pursuit , orthogonal matching pursuit
[Natalie Prange, supervisor: Ayush Dewan]