Ron Petrick's Webpages

Workshop paper

Object Action Complexes as an Interface for Planning and Robot Control, C. Geib, K. Mourão, R. Petrick, N. Pugeault, M. Steedman, N. Krueger, and F. Wörgötter, IEEE-RAS Humanoids-06 Workshop: Towards Cognitive Humanoid Robots, 2006.

[ bib | pdf ]

Abstract

Much prior work in integrating high-level artificial intelligence planning technology with low-level robotic control has foundered on the significant representational differences between these two areas of research. We discuss a proposed solution to this representational discontinuity in the form of object-action complexes (OACs). The pairing of actions and objects in a single interface representation captures the needs of both reasoning levels, and will enable machine learning of high-level action representations from low-level control representations.