Autonomous learning of object models on a mobile robot

Thomas Fäulhammer, Rares Ambrus, Chris Burbridge, Michael Zillich, John Folkesson, Nick Hawes, Patric Jensfelt, Markus Vincze

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)
301 Downloads (Pure)


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. While 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 modeling 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.
Original languageEnglish
Pages (from-to)26-33
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number1
Early online date26 Jan 2016
Publication statusPublished - Jan 2017


Dive into the research topics of 'Autonomous learning of object models on a mobile robot'. Together they form a unique fingerprint.

Cite this