Extending Knowledge-Level Contingent Planning for Robot Task Planning
Ronald P. A. Petrick, Andre Gaschler · mediaTUM (Technical University of Munich) · 2014
We present a set of extensions to the knowledge-level PKS (Planning with Knowledge and Sensing) planner, aimed at improving its ability to generate plans in real-world robotics domains. These extensions include a fa-cility for integrating externally-defined reasoning pro-cesses in PKS (e.g., invoking a motion planner), an interval-based fluent representation for capturing the ef-fects of noisy sensors and effectors, and an application programming interface (API) to facilitate software in-tegration on robot platforms. We demonstrate our tech-niques in three simple robot domains, which show their applicability to a broad range of robot planning applica-tions involving incomplete knowledge, real-world ge-ometry, and multiple robots and sensors.