A sensorimotor learning framework for object categorization
2016 (English)In: IEEE Transactions on Cognitive and Developmental Systems, ISSN 2379-8920, Vol. 8, no 1, 15-25 p.Article in journal (Refereed) Published
This paper presents a framework that enables a robot to discover various object categories through interaction. The categories are described using action-effect relations, i.e. sensorimotor contingencies rather than more static shape or appearance representation. The framework provides a functionality to classify objects and the resulting categories, associating a class with a specific module. We demonstrate the performance of the framework by studying a pushing behavior in robots, encoding the sensorimotor contingencies and their predictability with Gaussian Processes. We show how entropy-based action selection can improve object classification and how functional categories emerge from the similarities of effects observed among the objects. We also show how a multidimensional action space can be realized by parameterizing pushing using both position and velocity.
Place, publisher, year, edition, pages
IEEE , 2016. Vol. 8, no 1, 15-25 p.
sensorimotor learning, object classification, categorization, cognitive robotics, active perception, learning and adaptive system, embodiment, developmental robotics
Research subject Computer Science
IdentifiersURN: urn:nbn:se:kth:diva-172143DOI: 10.1109/TAMD.2015.2463728OAI: oai:DiVA.org:kth-172143DiVA: diva2:922036
FunderSwedish Research CouncilEU, European Research Council, H2020-FETPROACT-2014 641321
QC 201604222016-04-212015-08-132016-06-03Bibliographically approved