Robot anticipation of human intentions through continuous gesture recognition
2013 (English)In: Proceedings of the 2013 International Conference on Collaboration Technologies and Systems, CTS 2013, IEEE , 2013, 218-225 p.Conference paper (Refereed)
In this paper, we propose a method to recognize human body movements and we combine it with the contextual knowledge of human-robot collaboration scenarios provided by an object affordances framework that associates actions with its effects and the objects involved in them. The aim is to equip humanoid robots with action prediction capabilities, allowing them to anticipate effects as soon as a human partner starts performing a physical action, thus enabling interactions between man and robot to be fast and natural. We consider simple actions that characterize a human-robot collaboration scenario with objects being manipulated on a table: inspired from automatic speech recognition techniques, we train a statistical gesture model in order to recognize those physical gestures in real time. Analogies and differences between the two domains are discussed, highlighting the requirements of an automatic gesture recognizer for robots in order to perform robustly and in real time.
Place, publisher, year, edition, pages
IEEE , 2013. 218-225 p.
Action prediction, Automatic speech recognition, Contextual knowledge, Human body movement, Human intentions, Human-robot collaboration, Humanoid robot, Physical action
Engineering and Technology
IdentifiersURN: urn:nbn:se:kth:diva-133411DOI: 10.1109/CTS.2013.6567232ScopusID: 2-s2.0-84883302848ISBN: 978-146736402-7OAI: oai:DiVA.org:kth-133411DiVA: diva2:661042
2013 International Conference on Collaboration Technologies and Systems, CTS 2013; San Diego, CA; United States; 20 May 2013 through 24 May 2013
QC 201310312013-10-312013-10-312013-10-31Bibliographically approved