Search Contact
bild
School of
Computer Science
and Communication
KTH / CSC / CVAP / Yasemin Bekiroğlu

Yasemin Bekiroğlu


About me



I completed my Ph.D. in the Computer Vision and Active Perception Lab (CVAP), in the School of Computer Science and Communication, at the Royal Institute of Technology (KTH), in Stockholm, Sweden, in November 2012. My supervisor was Prof. Danica Kragic. I was involved in the EU project CogX. I was a postdoctoral researcher at CVAP until Feb 2016 and involved in the EU project RoboHow and eSMCs. My research interests include robotics, computer vision and machine learning. More specifically, I am interested in learning-based approaches for robot grasping and manipulation using multisensory data.

Publications




A Database for Reproducible Manipulation Research: CapriDB - Capture, Print, Innovate
Y. Bekiroglu*, F. T. Pokorny*, K. Pauwels, J. Butepage, C. Scherer, D. Kragic
Data in Brief, 2017, accepted

Grasp Quality Evaluation Done Right: How Assumed Contact Force Bounds Affect Wrench-Based Quality Metrics
R. Krug, Y. Bekiroglu, M. A. Roa
IEEE International Conference on Robotics and Automation, 2017, Singapore, accepted

Towards Robotic Manipulation for Nuclear Decommissioning: A Pilot Study on Tele-operation and Autonomy
N. Marturi, A. Rastegarpanah, C. Takahashi, J. Kuo, R. Stolkin, Y. Bekiroglu
IEEE International Conference on Robotics and Automation for Humanitarian Applications (RAHA), 2016, Kerala, India, Best Paper Award

Active Exploration Using Gaussian Random Fields and Gaussian Process Implicit Surfaces
S. Caccamo, Y. Bekiroglu, C. H. Ek, D. Kragic
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016, Daejeon, Korea

Hierarchical Fingertip Space: A Unified Framework for Grasp Planning and In-Hand Grasp Adaptation
K. Hang, M. Li, J. A. Stork, Y. Bekiroglu, F. T. Pokorny, A. Billard, D. Kragic
IEEE Transactions on Robotics 2016

CapriDB - Capture, Print, Innovate: A Low-Cost Pipeline and Database for Reproducible Manipulation Research
F. T. Pokorny*, Y. Bekiroglu*, K. Pauwels, J. Butepage, C. Scherer, D. Kragic
IEEE ICRA 2016 Workshop: Grasping and Manipulation Datasets, Stockholm, Sweden

Analytic Grasp Success Prediction with Tactile Feedback
R. Krug, A. J. Lilienthal, D. Kragic, Y. Bekiroglu
IEEE International Conference on Robotics and Automation 2016, Stockholm, Sweden

Probabilistic Consolidation of Grasp Experience
Y. Bekiroglu, A. Damianou, R. Detry, J. A. Stork, D. Kragic, C. H. Ek
IEEE International Conference on Robotics and Automation 2016, Stockholm, Sweden

Learning Predictive State Representation for In-Hand Manipulation
J. A. Stork, C. H. Ek, Y. Bekiroglu and D. Kragic
IEEE International Conference on Robotics and Automation 2015, Seattle, Washington, USA

Learning to Disambiguate Object Hypotheses through Self-Exploration
M. Bjorkman and Y. Bekiroglu
IEEE-RAS International Conference on Humanoid Robots 2014, Madrid, Spain

Learning of Grasp Adaptation through Experience and Tactile Sensing
M. Li, Y. Bekiroglu, D. Kragic and A. Billard
IEEE/RSJ International Conference on Intelligent Robots and Systems 2014, Chicago, USA

What's in the Container? Classifying Object Contents from Vision and Touch
P. Guler, Y. Bekiroglu, X. Gratal, K. Pauwels and D. Kragic
IEEE/RSJ International Conference on Intelligent Robots and Systems 2014, Chicago, USA

Grasp Moduli Spaces, Gaussian Processes and Multimodal Sensor Data
F. T. Pokorny, Y. Bekiroglu, M. Bjorkman, J. Exner and D. Kragic
RSS 2014 Workshop: Information-based Grasp and Manipulation Planning, Berkeley, USA

Hierarchical Fingertip Space for Synthesizing Adaptable Fingertip Grasps
K. Hang, M. Li, J. A. Stork, Y. Bekiroglu, A. Billard and D. Kragic
ICRA 2014 Workshop: Autonomous Grasping and Manipulation: An Open Challenge, Hong Kong, China

Grasp Moduli Spaces and Spherical Harmonics
F. T. Pokorny, Y. Bekiroglu and D. Kragic
IEEE International Conference on Robotics and Automation 2014, Hong Kong, China

Predicting Slippage and Learning Manipulation Affordances through Gaussian Process Regression
F. Vina, Y. Bekiroglu, C. Smith, Y. Karayiannidis and D. Kragic
IEEE-RAS International Conference on Humanoid Robots 2013, Atlanta, USA

Enhancing Visual Perception of Shape through Tactile Glances
M. Bjorkman, Y. Bekiroglu, V. Hogman and D. Kragic
IEEE/RSJ International Conference on Intelligent Robots and Systems 2013, Tokyo, Japan, IROS CoTeSys Cognitive Robotics Best Paper Award Finalist

A Probabilistic Framework for Task-Oriented Grasp Stability Assessment
Y. Bekiroglu, D. Song, L. Wang and D. Kragic
IEEE International Conference on Robotics and Automation 2013, Karlsruhe, Germany, Best Manipulation Paper Award

Grasp Stability from Vision and Touch
Y. Bekiroglu, R. Detry and D. Kragic
IEEE IROS 2012 Workshop: Advances in Tactile Sensing and Touch-based Human Robot Interaction, Vilamoura, Portugal

Learning Task- and Touch-based Grasping
Y. Bekiroglu, D. Song, L. Wang and D. Kragic
IEEE IROS 2012 Workshop: Beyond Robot Grasping - Modern Approaches for Learning Dynamic Manipulation, Vilamoura, Portugal

Learning Tactile Characterizations Of Object- And Pose-specific Grasps
Y. Bekiroglu, R. Detry and D. Kragic
IEEE/RSJ International Conference on Intelligent Robots and Systems 2011, San Francisco, USA

Assessing grasp stability based on learning and haptic data
Y. Bekiroglu, J. Laaksonen, J.A. Jorgensen, V. Kyrki and D. Kragic
IEEE Transactions on Robotics, 27(3):616-629, 2011

Integrating Grasp Planning with Online Stability Assessment using Tactile Sensing
Y. Bekiroglu, K. Huebner and D. Kragic
IEEE International Conference on Robotics and Automation 2011, Shanghai, China

Joint Observation of Object Pose and Tactile Imprints for Online Grasp Stability Assessment
Y. Bekiroglu, R. Detry and D. Kragic
IEEE ICRA 2011 workshop: Manipulation Under Uncertainty, Shanghai, China

Learning grasp stability with tactile data and HMMs
Y. Bekiroglu, V. Kyrki and D. Kragic
IEEE International Symposium on Robot and Human Interactive Communication 2010, Viareggio, Italy

Learning grasp stability based on haptic data
Y. Bekiroglu, J. Laaksonen, J. A. Jorgensen, V. Kyrki and D. Kragic
RSS 2010 workshop: Representations for object grasping and manipulation in single and dual arm tasks, Zaragoza, Spain

Learning to Assess Grasp Stability from Vision, Touch and Proprioception
Y. Bekiroglu
PhD Thesis, 2012

News




I organize two workshops at ERF 2017.
I gave a talk at an IROS 2016 workshop: See, Touch, and Hear: 2nd Workshop on multimodal sensor-based robot control for HRI and soft manipulation.
I organized a workshop collaborating with EPFL and Orebro University at IROS 2016: Closed-loop Grasping and Manipulation: Challenges and Progress.
I gave a talk at ICRA '16 Workshop on "Grasping and Manipulation Datasets".
Two submissions for ICRA 2016 were accepted.
I gave a tutorial on stability and shape estimation based on visual and tactile data at SQUIRREL/3rdHand Winter School, Feb, 2016.
I gave a talk at the workshop of the British Machine Vision Association (BMVA) "Visual, tactile and force sensing for robot manipulation" in December.
I attended the Dagstuhl seminar "Multimodal Manipulation Under Uncertainty" in October.
I organized a workshop together with my colleagues: RSS 2015 Workshop Bridging the Gap between Data-driven and Analytical Physics-based Grasping and Manipulation I presented our paper: "Learning to Disambiguate Object Hypotheses through Self-Exploration" at Humanoids 2014.
I presented our paper: "Learning of Grasp Adaptation through Experience and Tactile Sensing" at IROS 2014.
I presented our paper: "Grasp Moduli Spaces, Gaussian Processes and Multimodal Sensor Data " at ICRA 2014.
I was at Bremen University to integrate grasp stability estimation package with the CRAM: Cognitive Robot Abstract Machine in March 2014.
I attended the Gaussian Process Winter School, 2014

Links



CapriDB - Capture, Print, Innovate: A Low-Cost Pipeline and Database for Reproducible Manipulation Research
Master (Exjobb) Project Positions at CVAP
Datasets with real and simulated tactile data from the Schunk Dexterous hand

Contact



Comp.Vision & Active Perception Lab (CVAP)
Royal Institute of Technology (KTH)
Teknikringen 14, plan 5
SE - 100 44 Stockholm, SWEDEN
+46 (0) 8 790 6242
Published by: Yasemin Bekiroğlu <yaseminb@kth.se>
http://www.yaseminbekiroglu.com/