<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Lallée, Stephane</style></author><author><style face="normal" font="default" size="100%">Séverin Lemaignan</style></author><author><style face="normal" font="default" size="100%">Alexander Lenz</style></author><author><style face="normal" font="default" size="100%">Chris Melhuish</style></author><author><style face="normal" font="default" size="100%">Lorenzo Natale</style></author><author><style face="normal" font="default" size="100%">Sergey Skachek</style></author><author><style face="normal" font="default" size="100%">Tijn van Der Zant</style></author><author><style face="normal" font="default" size="100%">Felix Warneken</style></author><author><style face="normal" font="default" size="100%">Peter F. Dominey</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Towards a Platform-Independent Cooperative Human-Robot Interaction System: I. Perception</style></title><secondary-title><style face="normal" font="default" size="100%">IROS IEEE/RSJ International Conference on Intelligent Robots and Systems</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2010</style></year><pub-dates><date><style  face="normal" font="default" size="100%">10-2010</style></date></pub-dates></dates><urls><related-urls><url><style face="normal" font="default" size="100%">http://organic.elis.ugent.be/sites/organic.elis.ugent.be/files/0898.pdf</style></url></related-urls></urls><abstract><style face="normal" font="default" size="100%">&lt;p&gt;One of the long term objectives of robotics and&lt;br /&gt;
artificial cognitive systems is that robots will increasingly be&lt;br /&gt;
capable of interacting in a cooperative and adaptive manner&lt;br /&gt;
with their human counterparts in open-ended tasks that can&lt;br /&gt;
change in real-time. In such situations, an important aspect of&lt;br /&gt;
the robot behavior will be the ability to acquire new knowledge&lt;br /&gt;
of the cooperative tasks by observing humans. At least two&lt;br /&gt;
significant challenges can be identified in this context. The first&lt;br /&gt;
challenge concerns development of methods to allow the&lt;br /&gt;
characterization of human actions such that robotic systems can&lt;br /&gt;
observe and learn new actions, and more complex behaviors&lt;br /&gt;
made up of those actions. The second challenge is associated&lt;br /&gt;
with the immense heterogeneity and diversity of robots and&lt;br /&gt;
their perceptual and motor systems. The associated question is&lt;br /&gt;
whether the identified methods for action perception can be&lt;br /&gt;
generalized across the different perceptual systems inherent to&lt;br /&gt;
distinct robot platforms. The current research addresses these&lt;br /&gt;
two challenges. We present results from a cooperative human-&lt;br /&gt;
robot interaction system that has been specifically developed for&lt;br /&gt;
portability between different humanoid platforms. Within this&lt;br /&gt;
architecture, the physical details of the perceptual system (e.g.&lt;br /&gt;
video camera vs IR video with reflecting markers) are&lt;br /&gt;
encapsulated at the lowest level. Actions are then automatically&lt;br /&gt;
characterized in terms of perceptual primitives related to&lt;br /&gt;
motion, contact and visibility.&lt;br /&gt;
The resulting system is&lt;br /&gt;
demonstrated to perform robust object and action learning and&lt;br /&gt;
recognition on two distinct robotic platforms. Perhaps most&lt;br /&gt;
interestingly, we demonstrate that knowledge acquired about&lt;br /&gt;
action recognition with one robot can be directly imported and&lt;br /&gt;
successfully used on a second distinct robot platform for action&lt;br /&gt;
recognition. This will have interesting implications for the&lt;br /&gt;
accumulation of shared knowledge between distinct&lt;br /&gt;
heterogeneous robotic systems.&lt;/p&gt;</style></abstract></record></records></xml>