Hauptseminar Topics in Robotics (SS 14)

Today’s robots are hardly intelligent. Why is that? What are the grand challenges of robotics — especially from the perspective of Artificial Intelligence and Machine Learning? In this seminar we cover topics from the state-of-the-art in robotics. The focus will be on current research that aims to bridge between robotics, AI and Machine Learning. The aim is to give students an impression on how research is done in robotics and train them in reading and presenting papers. Prior knowledge in Artificial Intelligence (e.g. the Bachelor’s course) and Robotics (e.g. the Master’s course) is required. This advanced seminar will be held completely in English. INFOTEC, cybernetics and other master students are welcome. Participants have to give a presentation and write a summary paper.

Talks

The talks will take place in room 0.463 and go from 15:45 to 17:15.

DateSpeakerTopic
17.06.2014Jan-Hendrik PaulsCakmak: Designing robot learners that ask good questions
Klaudius ScheufelePlatt: Non-gaussian belief space planning: correctness and complexity
24.06.2014Sascha MeuselWurm: OctoMap: a probabilistic, flexible, and compact 3D map representation for robotic systems
Duy Bien LeHenry: RGB-D mapping: using kinect-style depth cameras for dense 3D modeling of indoor environments
Jayashree AgatheswaranIkemoto: Physical human-robot interaction: mutual learning and adaptation

01.07.2014Jochen MohrmannVigoritto: Intrinsically motivated hierarchical skill learning in structured environments
Jaideep TiwariNiekum: Incremental semantically grounded learning from demonstration
Mohammed Bilal ButtBarry: Manipulation with multiple action types
08.07.2014Ehsan AbdiTellex: Toward learning perceptually grounded word meanings from unaligned parallel data
Hasan Mahmud ChowdhurySchulman: Motion planning with sequential convex optimization and convex collision checking
Suraj MishraPosa: A direct method for trajectory optimization of rigid bodies through contact

Presentation

  • 20 min presentation of the paper
  • 10 min Q&A
  • The other students should be able to grasp the paper afterwards!
  • The other students will give you feedback.

Summary paper

  • Do not plagiarize! Writing a summary paper means that your describe, in your own words, the paper’s motivation, contributions, limitations and relations to other work. When refering to the author’s work, say ``the authors propose…” or ``they developed…”.
  • Summary papers must be written in the style of ICRA (Int. Conf. on Robotics and Automation) using their style files (preferrably LaTex). Find these style files online.
  • The bibliography should follow scientific standards, preferrably using BibTeX as described in the ICRA style.
  • total of ~3500 words with the following content
  1. Motivation and problem: What was the authors’ motivation for this research. What is the problem they are trying to solve.
  2. State-of-the-art and contributions: What was the state-of-the-art BEFORE this paper and what do the authors aim and claim to contribute to the state-of-the-art with this work.
  3. Summarize the methods, techniques, theory, algorithms, etc, that they develop.
  4. Summarize their evaluation results.
  5. Research and discuss the impact that this paper had on later research (e.g. use Google Scholar to find citations of this paper).
  6. Add a personal assessment of the paper including critique and suggestions for improvements.

Papers

S. Tellex, P. Thaker, J. Joseph, M. R. Walter, and N. Roy: Toward learning perceptually grounded word meanings from unaligned parallel data. In Proceedings of the second workshop on semantic interpretation in an actionable context, 7–14, 2012. [Bibtex]

@inproceedings{tellex_toward_2012,
title = {Toward learning perceptually grounded word meanings from unaligned parallel data},
url = {http://dl.acm.org/citation.cfm?id=2390929},
urldate = {2013-07-11},
booktitle = {Proceedings of the Second Workshop on Semantic Interpretation in an Actionable Context},
author = {Tellex, Stefanie and Thaker, Pratiksha and Joseph, Josh and Walter, Matthew R. and Roy, Nicholas},
year = {2012},
pages = {7–14}
}
R. Platt, L. Kaelbling, T. Lozano-Perez, and R. Tedrake: Non-gaussian belief space planning: correctness and complexity. In Robotics and automation (ICRA), 2012 IEEE international conference on, 4711–4717, {IEEE}, 2012. [Bibtex]

@inproceedings{platt_non-gaussian_2012,
title = {Non-gaussian belief space planning: Correctness and complexity},
shorttitle = {Non-gaussian belief space planning},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6225223},
urldate = {2014-04-10},
booktitle = {Robotics and Automation ({ICRA)}, 2012 {IEEE} International Conference on},
publisher = {{IEEE}},
author = {Platt, Robert and Kaelbling, Leslie and Lozano-Perez, Tomas and Tedrake, Russ},
year = {2012},
pages = {4711–4717}
}
C. M. Vigorito and A. G. Barto: Intrinsically motivated hierarchical skill learning in structured environments. Autonomous mental development, IEEE transactions on, 2, 132–143, 2010. [Bibtex]

@article{vigorito_intrinsically_2010,
title = {Intrinsically motivated hierarchical skill learning in structured environments},
volume = {2},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5464347},
number = {2},
urldate = {2014-04-09},
journal = {Autonomous Mental Development, {IEEE} Transactions on},
author = {Vigorito, Christopher M. and Barto, Andrew G.},
year = {2010},
pages = {132–143}
}
S. Niekum, S. Chitta, B. Marthi, S. Osentoski, and A. G. Barto: Incremental semantically grounded learning from demonstration. In Robotics: science and systems, 9, 2013. [Bibtex]

@inproceedings{niekum_incremental_2013,
title = {Incremental semantically grounded learning from demonstration},
volume = {9},
url = {http://www.roboticsproceedings.org/rss09/p48.pdf},
urldate = {2013-07-11},
booktitle = {Robotics: Science and Systems},
author = {Niekum, Scott and Chitta, Sachin and Marthi, Bhaskara and Osentoski, Sarah and Barto, Andrew G.},
year = {2013}
}
K. M. Wurm, A. Hornung, M. Bennewitz, C. Stachniss, and W. Burgard: OctoMap: a probabilistic, flexible, and compact 3D map representation for robotic systems. In Proc. of the ICRA 2010 workshop on best practice in 3D perception and modeling for mobile manipulation, 2, 2010. [Bibtex]

@inproceedings{wurm_octomap:_2010,
title = {{OctoMap:} A probabilistic, flexible, and compact {3D} map representation for robotic systems},
volume = {2},
shorttitle = {{OctoMap}},
url = {http://ais.informatik.uni-freiburg.de/publications/papers/wurm10octomap.pdf},
urldate = {2014-04-22},
booktitle = {Proc. of the {ICRA} 2010 workshop on best practice in {3D} perception and modeling for mobile manipulation},
author = {Wurm, Kai M. and Hornung, Armin and Bennewitz, Maren and Stachniss, Cyrill and Burgard, Wolfram},
year = {2010}
}
E. A. Rückert, G. Neumann, M. Toussaint, and W. Maass: Learned graphical models for probabilistic planning provide a new class of movement primitives. Frontiers in computational neuroscience, 6, 2013. [Bibtex]

@article{ruckert_learned_2013,
title = {Learned graphical models for probabilistic planning provide a new class of movement primitives},
volume = {6},
issn = {1662-5188},
url = {http://www.frontiersin.org/Journal/10.3389/fncom.2012.00097/full},
doi = {10.3389/fncom.2012.00097},
urldate = {2014-04-22},
journal = {Frontiers in Computational Neuroscience},
author = {Rückert, Elmar A. and Neumann, Gerhard and Toussaint, Marc and Maass, Wolfgang},
year = {2013}
}
M. Cakmak and {A. L. }. Thomaz: Designing robot learners that ask good questions. In 2012 7th ACM/IEEE international conference on human-robot interaction (HRI), 17–24, Cited by 0014, 2012. [Bibtex]

@inproceedings{cakmak_designing_2012,
title = {Designing robot learners that ask good questions},
url = {ieeexplore.ieee.org/ielx5/6243995/6249474/06249515.pdf?tp=&arnumber=6249515&isnumber=6249474},
abstract = {Programming new skills on a robot should take minimal time and effort. One approach to achieve this goal is to allow the robot to ask questions. This idea, called Active Learning, has recently caught a lot of attention in the robotics community. However, it has not been explored from a human-robot interaction perspective. In this paper, we identify three types of questions (label, demonstration and feature queries) and discuss how a robot can use these while learning new skills. Then, we present an experiment on human question asking which characterizes the extent to which humans use these question types. Finally, we evaluate the three question types within a human-robot teaching interaction. We investigate the ease with which different types of questions are answered and whether or not there is a general preference of one type of question over another. Based on our findings from both experiments we provide guidelines for designing question asking behaviors on a robot learner.},
booktitle = {2012 7th {ACM/IEEE} International Conference on Human-Robot Interaction ({HRI)}},
author = {Cakmak, M. and Thomaz, {A.L.}},
year = {2012},
note = {Cited by 0014},
keywords = {Active Learning, demonstration type, feature query type, Green products, humanoid robots, human-robot interaction, human-robot teaching interaction, Humans, label type, learning (artificial intelligence), learning from demonstration, learning-from-demonstration, Programming, query processing, question asking behaviors, robotics community, robot learner design, robot programming, robots, student experiments, teaching, Trajectory, {USA} Councils, Videos},
pages = {17--24}
}
R. Platt, L. Kaelbling, T. Lozano-Perez, and R. Tedrake: Efficient planning in non-gaussian belief spaces and its application to robot grasping. In International symposium on robotics research, 2011. [Bibtex]

@inproceedings{platt_efficient_2011,
title = {Efficient planning in non-gaussian belief spaces and its application to robot grasping},
url = {http://www.cse.buffalo.edu/~robplatt/papers/platt_isrr2011_6.pdf},
urldate = {2014-04-22},
booktitle = {International Symposium on Robotics Research},
author = {Platt, Robert and Kaelbling, Leslie and Lozano-Perez, Tomas and Tedrake, Russ},
year = {2011}
}
Z. Jia, A. Gallagher, A. Saxena, and T. Chen: 3D-Based reasoning with blocks, support, and stability. 1–8, {IEEE}, 2013. [Bibtex]

@inproceedings{jia_3d-based_2013,
title = {{3D-Based} Reasoning with Blocks, Support, and Stability},
isbn = {978-0-7695-4989-7},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6618852},
doi = {10.1109/CVPR.2013.8},
urldate = {2014-04-22},
publisher = {{IEEE}},
author = {Jia, Zhaoyin and Gallagher, Andrew and Saxena, Ashutosh and Chen, Tsuhan},
month = jun,
year = {2013},
pages = {1--8}
}
P. Henry, M. Krainin, E. Herbst, X. Ren, and D. Fox: RGB-D mapping: using kinect-style depth cameras for dense 3D modeling of indoor environments. The international journal of robotics research, 31, 647–663, 2012. [Bibtex]

@article{henry_rgb-d_2012,
title = {{RGB-D} mapping: Using Kinect-style depth cameras for dense {3D} modeling of indoor environments},
volume = {31},
issn = {0278-3649, 1741-3176},
shorttitle = {{RGB-D} mapping},
url = {http://ijr.sagepub.com/cgi/doi/10.1177/0278364911434148},
doi = {10.1177/0278364911434148},
language = {en},
number = {5},
urldate = {2014-04-22},
journal = {The International Journal of Robotics Research},
author = {Henry, P. and Krainin, M. and Herbst, E. and Ren, X. and Fox, D.},
month = apr,
year = {2012},
pages = {647--663},
file = {647.full.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/UJTETM82/647.full.pdf:application/pdf}
}
M. Posa, C. Cantu, and R. Tedrake: A direct method for trajectory optimization of rigid bodies through contact. The international journal of robotics research, 33, 69–81, 2014. [Bibtex]

@article{posa_direct_2014,
title = {A direct method for trajectory optimization of rigid bodies through contact},
volume = {33},
issn = {0278-3649, 1741-3176},
url = {http://ijr.sagepub.com/cgi/doi/10.1177/0278364913506757},
doi = {10.1177/0278364913506757},
language = {en},
number = {1},
urldate = {2014-04-22},
journal = {The International Journal of Robotics Research},
author = {Posa, M. and Cantu, C. and Tedrake, R.},
month = jan,
year = {2014},
pages = {69--81},
file = {69.full.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/SV47WXKS/69.full.pdf:application/pdf}
}
R. Deits, S. Tellex, P. Thaker, D. Simeonov, T. Kollar, and N. Roy: Clarifying commands with information-theoretic human-robot dialog. Journal of human-robot interaction, 2, 2013. [Bibtex]

@article{deits_clarifying_2013,
title = {Clarifying Commands with Information-Theoretic Human-Robot Dialog},
volume = {2},
issn = {2163-0364},
url = {http://humanrobotinteraction.org/journal/index.php/HRI/article/view/112},
doi = {10.5898/JHRI.2.2.Deits},
number = {2},
urldate = {2014-04-22},
journal = {Journal of Human-Robot Interaction},
author = {Deits, Robin and Tellex, Stefanie and Thaker, Pratiksha and Simeonov, Dimitar and Kollar, Thomas and Roy, Nicholas},
month = jun,
year = {2013},
file = {97.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/TXNJZE4V/97.pdf:application/pdf}
}
J. Schulman: Motion planning with sequential convex optimization and convex collision checking. 2014. [Bibtex]

@article{schulman_motion_2014,
title = {Motion Planning with Sequential Convex Optimization and Convex Collision Checking},
url = {http://rll.berkeley.edu/~sachin/papers/Schulman-IJRR2014.pdf},
urldate = {2014-04-22},
author = {Schulman, John},
year = {2014}
}
I. Havoutis, C. Semini, J. Buchli, and D. G. Caldwell: Quadrupedal trotting with active compliance. In Mechatronics (ICM), 2013 IEEE international conference on, 610–616, {IEEE}, 2013. [Bibtex]

@inproceedings{havoutis_quadrupedal_2013,
title = {Quadrupedal trotting with active compliance},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6519112},
urldate = {2014-04-22},
booktitle = {Mechatronics ({ICM)}, 2013 {IEEE} International Conference on},
publisher = {{IEEE}},
author = {Havoutis, Ioannis and Semini, Claudio and Buchli, Jonas and Caldwell, Darwin G.},
year = {2013},
pages = {610–616}
}
F. Stulp and O. Sigaud: Robot skill learning: from reinforcement learning to evolution strategies. Journal of behavioral robotics, 2013. [Bibtex]

@article{stulp_robot_2013,
title = {Robot Skill Learning: From Reinforcement Learning to Evolution Strategies},
url = {http://www.degruyter.com/dg/viewarticle.fullcontentlink:pdfeventlink/$002fj$002fpjbr.2013.4.issue-1$002fpjbr-2013-0003$002fpjbr-2013-0003.pdf?t:ac=j$002fpjbr.2013.4.issue-1$002fpjbr-2013-0003$002fpjbr-2013-0003.xml},
urldate = {2014-04-22},
journal = {Journal of Behavioral Robotics},
author = {Stulp, Freek and Sigaud, Olivier},
year = {2013},
file = {$002fj$002fpjbr.2013.4.issue-1$002fpjbr-2013-0003$002fpjbr-2013-0003.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/5KIGR9GC/$002fj$002fpjbr.2013.4.issue-1$002fpjbr-2013-0003$002fpjbr-2013-0003.pdf:application/pdf}
}
Barry, Hsiao, Kaelbling, and Lozano-Pérez: Manipulation with multiple action types. Experimental robotics, 2013. [Bibtex]

@article{barry_manipulation_2013,
title = {Manipulation with Multiple Action Types},
url = {http://lis.csail.mit.edu/pubs/barry-iser12.pdf},
urldate = {2014-04-22},
journal = {Experimental Robotics},
author = {{Barry} and {Hsiao} and {Kaelbling} and {Lozano-Pérez}},
year = {2013},
file = {barry-iser12.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/ACU5W296/barry-iser12.pdf:application/pdf}
}
Dang and Allen: Stable grasping under pose uncertainty using tactile feedback. Autonomous robots, 2013. [Bibtex]

@article{dang_stable_2013,
title = {Stable grasping under pose uncertainty using tactile feedback},
url = {http://www.cs.columbia.edu/~dang/papers/dang_auro2013.pdf},
urldate = {2014-04-22},
journal = {Autonomous Robots},
author = {{Dang} and {Allen}},
year = {2013},
file = {dang_auro2013.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/7FMHQC36/dang_auro2013.pdf:application/pdf}
}
J. Bohg, A. Morales, T. Asfour, and D. Kragic: Data-driven grasp synthesis: a survey. IEEE transactions on robotics, 30, 289–309, 2014. [Bibtex]

@article{bohg_data-driven_2014,
title = {Data-Driven Grasp Synthesis: A Survey},
volume = {30},
issn = {1552-3098, 1941-0468},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6672028},
doi = {10.1109/TRO.2013.2289018},
number = {2},
urldate = {2014-04-22},
journal = {{IEEE} Transactions on Robotics},
author = {Bohg, Jeannette and Morales, Antonio and Asfour, Tamim and Kragic, Danica},
month = apr,
year = {2014},
pages = {289--309},
file = {06672028.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/VDHHCUI7/06672028.pdf:application/pdf}
}
S. Ikemoto, H. Amor, T. Minato, B. Jung, and H. Ishiguro: Physical human-robot interaction: mutual learning and adaptation. IEEE robotics & automation magazine, 19, 24–35, 2012. [Bibtex]

@article{ikemoto_physical_2012,
title = {Physical Human-Robot Interaction: Mutual Learning and Adaptation},
volume = {19},
issn = {1070-9932},
shorttitle = {Physical Human-Robot Interaction},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6161710},
doi = {10.1109/MRA.2011.2181676},
number = {4},
urldate = {2014-04-22},
journal = {{IEEE} Robotics \& Automation Magazine},
author = {Ikemoto, Shuhei and Amor, Heni and Minato, Takashi and Jung, Bernhard and Ishiguro, Hiroshi},
month = dec,
year = {2012},
pages = {24--35},
file = {06161710.pdf:/home/peter/.mozilla/firefox/6ufkgpfy.default/zotero/storage/C7MX3T8W/06161710.pdf:application/pdf}
}