Service robots usually share their workspace with people. Typically, a robot’s tasks require knowing when and where people are, to be able to schedule requested tasks. Therefore, there exists the need to take into account the presence of humans when planning their actions and it is indispensable to have knowledge of robots’ environments. It means in practice knowing when (time and events duration) and where (in workspace) a robot's tasks can be performed. This research paper takes steps towards obtaining of the spatial information required to execute software to plan tasks to be performed by a robot. With this aim, a program capable to define meaningful areas or zones in the robot workspace by the use of a clustering is created tied with statistically reasoned time slots when to perform each task. The software is tested using real data obtained from different cameras located along the corridors of CSE Department of University of Oulu.

Date Published: 3 February 2014
PDF: 8 pages
Proc. SPIE 9025, Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques, 902502 (3 February 2014); doi: 10.1117/12.2043164

Published in SPIE Proceedings Vol. 9025:
Intelligent Robots and Computer Vision XXXI: Algorithms and Techniques
Juha Röning; David Casasent, Editor(s)