Representation and Integration: Combining Robot Control, High-Level Planning, and Action Learning

Ronald Petrick, Dirk Kraft, Kira Mourao, Christopher Geib, Nicolas Pugeault, Norbert Krüger, Mark Steedman

Publikation: Konferencebidrag uden forlag/tidsskriftPaperForskningpeer review

Abstrakt

We describe an approach to integrated robot control, high-level planning, and action effect learning that attempts to overcome the representational difficulties that exist between these diverse areas. Our approach combines ideas from robot vision, knowledgelevel planning, and connectionist machine learning, and focuses on the representational needs of these components.We also make use of a simple representational unit called an instantiated state transition fragment (ISTF) and a related structure called an object-action complex (OAC). The goal of this work is a general approach for inducing high-level action specifications, suitable for planning, from a robot’s interactions with the world. We present a detailed overview of our approach and show how it supports the learning of certain aspects of a high-level lepresentation from low-level world state information.
OriginalsprogEngelsk
Publikationsdato2008
StatusUdgivet - 2008
BegivenhedThe 6th International Cognitive Robotics Workshop (CogRob 2008) - Patras, Grækenland
Varighed: 21. jul. 200822. jul. 2008
Konferencens nummer: 6

Konference

KonferenceThe 6th International Cognitive Robotics Workshop (CogRob 2008)
Nummer6
Land/OmrådeGrækenland
ByPatras
Periode21/07/200822/07/2008

Fingeraftryk

Dyk ned i forskningsemnerne om 'Representation and Integration: Combining Robot Control, High-Level Planning, and Action Learning'. Sammen danner de et unikt fingeraftryk.

Citationsformater