Object–Action Complexes: Grounded abstractions of sensory–motor processes

• Published in: Robotics and autonomous systems Vol. 59; no. 10; pp. 740 - 757
• Main Authors: Krüger, Norbert, Geib, Christopher, Piater, Justus, Petrick, Ronald, Steedman, Mark, Wörgötter, Florentin, Ude, Aleš, Asfour, Tamim, Kraft, Dirk, Omrčen, Damir, Agostini, Alejandro, Dillmann, Rüdiger
• Format: Journal Article Publication
• Language: English
• Published: Elsevier B.V 01.10.2011
• Subjects: Aprenentatge automàtic; Artificial intelligence; Autonomous; Classificació INSPEC; Cybernetics; Execution monitoring; Grounding; Informàtica; Intel·ligència artificial; Learning; Learning (artificial intelligence); Machine learning; Reasoning about action and change; Representations; Robotics; Robots; Àrees temàtiques de la UPC; Execution monitoring; Grounding; Reasoning about action and change; Robotics; Machine learning
• ISSN: 0921-8890; 1872-793X
• DOI: 10.1016/j.robot.2011.05.009

This paper formalises Object–Action Complexes (OACs) as a basis for symbolic representations of sensory–motor experience and behaviours. OACs are designed to capture the interaction between objects and associated actions in artificial cognitive systems. This paper gives a formal definition of OACs, provides examples of their use for autonomous cognitive robots, and enumerates a number of critical learning problems in terms of OACs. ► A formal definition of Object–Action Complexes (OACs) is given. ► OACs capture the interaction between objects and associated actions. ► OACs provide a framework for grounded symbolic representations of behaviours. ► OACs enumerate a number of critical learning problems in artificial cognitive systems. ► OACs realise a paradigm of ‘ongoing learning at all levels at all times’.