View article

Robot knowledge of the world is created from discrete and asynchronous events received from its perception components. Proper representation and maintenance of robot knowledge is crucial to enable the use of robot knowledge for planning, user-interaction, etc. This paper identifies some of the main issues related to the representation, maintenance and querying of robot knowledge built upon discrete asynchronous events such as event-history management and synchronization, and introduces a language for simplifying the developers’ job at making a suitable representation of robot knowledge.

Autonomous robots with cognitive capabilities such as planning, knowledge intensive task execution and human interaction need to maintain and reason on knowledge about their environment (Beetz, Mosenlechner, and Tenorth 2010; Ziafati et al. 2013a; Tenorth and Beetz 2012; Lemaignan et al. 2011). Robot knowledge is collected by its perception components, which continuously process input sensory data and asynchronously output the results in the form of events representing various information types, such as recognized objects, faces and robot position (Heintz, Kvarnström, and Doherty 2010; Wrede 2009).