Autonomous Learning of Object Models on a Mobile Robot
2016 (English)In: IEEE Robotics and Automation Letters, ISSN 2377-3766Article in journal (Refereed) Published
In this article we present and evaluate a system which allows a mobile robot to autonomously detect, model and re-recognize objects in everyday environments. Whilst other systems have demonstrated one of these elements, to our knowledge we present the first system which is capable of doing all of these things, all without human interaction, in normal indoor scenes. Our system detects objects to learn by modelling the static part of the environment and extracting dynamic elements. It then creates and executes a view plan around a dynamic element to gather additional views for learning. Finally these views are fused to create an object model. The performance of the system is evaluated on publicly available datasets as well as on data collected by the robot in both controlled and uncontrolled scenarios.
Place, publisher, year, edition, pages
IEEE , 2016.
Object Model, Robot
IdentifiersURN: urn:nbn:se:kth:diva-183494DOI: 10.1109/LRA.2016.2522086OAI: oai:DiVA.org:kth-183494DiVA: diva2:911777
FunderEU, FP7, Seventh Framework Programme, 600623
QC 201604112016-03-142016-03-142016-04-11Bibliographically approved