Change search
ReferencesLink to record
Permanent link

Direct link
Unsupervised object exploration using context
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0003-2314-2880
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0002-5750-9655
2014 (English)In: The 23rd IEEE International Symposium on Robot and Human Interactive Communication, 2014 RO-MAN, IEEE conference proceedings, 2014, -506 p.Conference paper (Refereed)
Abstract [en]

In order for robots to function in unstructured environments in interaction with humans, they must be able to reason about the world in a semantic meaningful way. An essential capability is to segment the world into semantic plausible object hypotheses. In this paper we propose a general framework which can be used for reasoning about objects and their functionality in manipulation activities. Our system employs a hierarchical segmentation framework that extracts object hypotheses from RGB-D video. Motivated by cognitive studies on humans, our work leverages on contextual information, e.g., that objects obey the laws of physics, to formulate object hypotheses from regions in a mathematically principled manner.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2014. -506 p.
National Category
Computer Vision and Robotics (Autonomous Systems)
URN: urn:nbn:se:kth:diva-158006DOI: 10.1109/ROMAN.2014.6926302ISBN: 978-1-4799-6763-6OAI: diva2:773359
International Symposium on Robot and Human Interactive Communication,25-29th August, Edinburgh, Scotland, UK

Qc 20150122

Available from: 2014-12-18 Created: 2014-12-18 Last updated: 2015-05-04Bibliographically approved
In thesis
1. Action Recognition for Robot Learning
Open this publication in new window or tab >>Action Recognition for Robot Learning
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

This thesis builds on the observation that robots cannot be programmed to handle any possible situation in the world. Like humans, they need mechanisms to deal with previously unseen situations and unknown objects. One of the skills humans rely on to deal with the unknown is the ability to learn by observing others. This thesis addresses the challenge of enabling a robot to learn from a human instructor. In particular, it is focused on objects. How can a robot find previously unseen objects? How can it track the object with its gaze? How can the object be employed in activities? Throughout this thesis, these questions are addressed with the end goal of allowing a robot to observe a human instructor and learn how to perform an activity. The robot is assumed to know very little about the world and it is supposed to discover objects autonomously. Given a visual input, object hypotheses are formulated by leveraging on common contextual knowledge often used by humans (e.g. gravity, compactness, convexity). Moreover, unknown objects are tracked and their appearance is updated over time since only a small fraction of the object is visible from the robot initially. Finally, object functionality is inferred by looking how the human instructor is manipulating objects and how objects are used in relation to others. All the methods included in this thesis have been evaluated on datasets that are publicly available or that we collected, showing the importance of these learning abilities.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2015. v, 38 p.
TRITA-CSC-A, ISSN 1653-5723 ; 2015:09
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science
urn:nbn:se:kth:diva-165680 (URN)
Public defence
2015-05-21, F3, Lindstedtsvägen 26, KTH, Stockholm, 10:00 (English)

QC 20150504

Available from: 2015-05-04 Created: 2015-04-29 Last updated: 2015-05-04Bibliographically approved

Open Access in DiVA

fulltext(1056 kB)58 downloads
File information
File name FULLTEXT01.pdfFile size 1056 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textConference websiteIEEEXplore

Search in DiVA

By author/editor
Pieropan, AlessandroKjellström, Hedvig
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 58 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 766 hits
ReferencesLink to record
Permanent link

Direct link