[robotics-worldwide] [meetings] CFP: IROS Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics

Emre Ugur emre.ugur at boun.edu.tr
Sun Aug 7 20:57:35 PDT 2016


IROS 2016 Workshop on Machine Learning Methods for High-Level Cognitive
Capabilities in Robotics,
October 14, 2016
Daejeon, Korea


Submission deadline: August 12, 2016

Integrating multi-level sensory-motor and cognitive capabilities is
essential for developing robotic systems that can adaptively act in our
daily environment in active collaboration with humans. In this workshop,
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

Our daily environment is full of uncertainties with complex objects and
challenging tasks. A robot is not only required to deal with things
appropriately in a physical manner but also required to perform logical
and/or linguistic tasks in the real world. Conventionally, symbol-based
and/or rule-based approaches have been employed to model high-level
cognitive capabilities in robotics. However, it has been pointed out
that such conventional methods could not deal with the uncertainty that
is inevitably found in the physical environment and natural human-robot

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.

In this workshop, we will investigate how to create synergies so that
advanced learning of sensorimotor and cognitive capabilities can
interact to create a bootstrapping effect in different levels of skill

- Multimodal machine learning for robotics
- Deep learning for robotics
- Computational approaches to the study of development and learning
- Bayesian modeling for high-level cognitive capabilities
- Emergence of communication
- Segmentation of time-series information
- Probabilistic programming and reasoning
- Language acquisition
- Symbol grounding
- Human-robot communication and collaboration based on machine learning
- Human-assisted learning
- Imitation learning and Skill acquisition
- Cognitive and perceptual development
- Exploration and learning in animals and robots
- Social and emotional learning in humans and robots
- Curiosity and intrinsic motivation
- Affordance learning

The topics of the contributed papers are not limited to the topics shown

- Jun Tani, KAIST
- Komei Sugiura, NICT
- Xavier Hinaut, INRIA
- Justus Piater, University of Innsbruck
- Tadahiro Taniguchi, Ritsumeikan University
- Kuniaki Noda, Nissan North America

Participants are required to submit a contribution as:

- Extended abstract (maximum 2 pages in length)

All submissions will be reviewed on the basis of relevance, novelty,
originality, significance, soundness and clarity. At least two referees
will review each submission independently. Accepted papers will be
presented during the workshop in a poster session. A small number of
selected papers will be presented as oral presentations or spotlight talks.

- Submissions must be in PDF following the IEEE conference style in
- Send your PDF manuscript indicating [ML-HLCR 2016] in the subject to
the following email:

August 12, 2016 - Contributions submission deadline
August 31, 2016 - Notification of acceptance
October 14, 2016 - Workshop

- Takayuki Nagai, The University of Electro-Communications
- Tetsuya Ogata, Waseda University
- Emre Ugur, Bogazici University
- Yiannis Demiris, Imperial College London
- Tadahiro Taniguchi, Ritsumeikan University, Japan,

See more details in:

-- Emre Ugur, Ph.D. Assistant Professor, Bogazici University

More information about the robotics-worldwide mailing list