Call for papers


IROS 2017 The 2nd Workshop on Machine Learning Methods for
High-Level Cognitive Capabilities in Robotics


Special Issue in Advanced Robotics Journal: "Machine Learning Methods for High-Level Cognitive Capabilities in Robotics"

Submission deadline: August 12, 2017

Recent advances in machine learning techniques, including deep learning and hierarchical Bayesian modeling, are providing us with new possibilities to integrate high-level and low-level cognitive capabilities in robotics. It became clear that such learning methods are indispensable to create robots that can effectively deal with uncertainty while acting smart in the real world. On the other hand, no matter how powerful the method is, it cannot cope with the tremendous complexity of the learning space and problem.  In the last workshop at IROS 2016, we have launched this workshop to address these issues and attracted more than one hundred participants to the workshop.

In this workshop, we will extend the discussion scope how to accelerate the synergies of low and high-level cognitive capabilities to develop a robust intelligence that can deal with real-world problems. For this, we aim to share knowledge about the state-of-the-art machine learning methods that contribute to modeling sensory-motor and cognitive capabilities
in robotics, and to exchange views among cutting-edge robotics researchers with a special emphasis on adaptive high-level cognition.

We will have distinguished speakers who are the forerunners of this interdisciplinary research effort.

Yiannis Demiris, Imperial College
Olivier Mangin, Yale University
Michael Beetz, University of Bremen
Tomoaki Nakamura, The University of Electro-Communications
Dustin Tran, Columbia University
George Konidaris, Brown University, US
Tetsuya Ogata, Waseda University
Wataru Takano, Tokyo University
Erhan Oztop, Ozyegin University

Participants are required to submit a contribution in one of the categories:
  A) Extended abstract (maximum 2 pages in length)
  B) Full paper (maximum 6 pages in length), the paper automatically submitted to a special issue in Advanced Robotics.

All submissions will be peer-reviewed. Accepted papers will be presented during the workshop in a poster session. A number of selected papers will be presented as oral presentations or spotlight talks.
If you choose the category B), your paper will be automatically submitted to a special issue named “ Machine Learning Methods for High-Level Cognitive Capabilities in Robotics” in Advanced Robotics, which is a journal published by the Robotics Society of Japan. The review process for the journal is independent from the review for this workshop; however, you can receive the review result of the journal within about 90 days (average). It means that you might be able to state that the paper will be published in the journal later at the workshop. For this reason, the paper for the B) category should not be published in the workshop proceedings.

We invite contributions in the following topics that are
indicative but by no means exhaustive:
* Multimodal communication
* Emergence of communication
* Learning motor skills and segmentation of time-series information
* Concept formation
* Probabilistic programming and reasoning in robotics
* Language acquisition
* Human-robot communication and collaboration based on machine learning
* Deep learning for robotics
* Model of others
* Skill transfer between agents with different embodiment
* Bayesian modeling for high-level cognitive capabilities
* Sharing experiences through cloud computing
* Application in communicable service robots

Submission of abstracts:      August 12, 2017
Notification of acceptance:   August 31, 2017
Workshop:                      September 28, 2017

Special Issue in Advanced Robotics will be published around January in 2019.

* Tetsunari Inamura, National Institute of Informatics, Japan
* Hiroki Yokoyama, University of Tamagawa, Japan
* Emre Ugur, Bogazici University, Turkey
* Xavier Hinaut, INRIA (Bordeaux), France
* Michael Beetz, University of Bremen, Germany
* Tadahiro Taniguchi, Ritsumeikan University, Japan

- Submissions must be in PDF following the IEEE conference style in
- Send your PDF manuscript indicating [ML-HLCR 2017] in the
subject to the following email: mlhlcr2017[at]

Tetsunari Inamura,
National Institute of Informatics, Japan