Ron Petrick's Webpages


Knowledge-Level Planning for Robot Task Planning and Human-Robot Interaction, R. Petrick and A. Gaschler, extended abstract and poster from the RSS 2015 Workshop on Combining AI Reasoning and Cognitive Science with Robotics, 2015.

[ bib | pdf | poster | slides ]


In this poster, we present some of our recent applications of high-level knowledge-level planning with incomplete information and sensing actions to the problems of task planning and interaction in robotics domains. Our approach uses the PKS (Planning with Knowledge and Sensing) planner as the high-level reasoning and planning tool for robotics domains, which combines ideas from AI planning and knowledge representation. Examples are provided from a set of robot domains taken from two recent European Commission-funded projects, which illustrate the applicability of these techniques to a broad range of robot planning applications involving incomplete knowledge, real-world geometry, and human-robot interaction.