Next Article in Journal / Special Issue
Intent Understanding Using an Activation Spreading Architecture
Previous Article in Journal / Special Issue
Learning Task Knowledge from Dialog and Web Access
Article

Leveraging Qualitative Reasoning to Learning Manipulation Tasks

1
Faculty of Information Systems and Applied Computer Sciences, University of Bamberg, Bamberg, D-96045, Germany
2
Department of Computer Science, Eberhard Karls Universität Tübingen, Tübingen, D-72074, Germany
*
Author to whom correspondence should be addressed.
Academic Editors: Nicola Bellotto, Nick Hawes, Mohan Sridharan and Daniele Nardi
Robotics 2015, 4(3), 253-283; https://doi.org/10.3390/robotics4030253
Received: 1 March 2015 / Revised: 26 June 2015 / Accepted: 7 July 2015 / Published: 13 July 2015
(This article belongs to the Special Issue Representations and Reasoning for Robotics)
Learning and planning are powerful AI methods that exhibit complementary strengths. While planning allows goal-directed actions to be computed when a reliable forward model is known, learning allows such models to be obtained autonomously. In this paper we describe how both methods can be combined using an expressive qualitative knowledge representation. We argue that the crucial step in this integration is to employ a representation based on a well-defined semantics. This article proposes the qualitative spatial logic QSL, a representation that combines qualitative abstraction with linear temporal logic, allowing us to represent relevant information about the learning task, possible actions, and their consequences. Doing so, we empower reasoning processes to enhance learning performance beyond the positive effects of learning in abstract state spaces. Proof-of-concept experiments in two simulation environments show that this approach can help to improve learning-based robotics by quicker convergence and leads to more reliable action planning. View Full-Text
Keywords: qualitative spatial reasoning; robot learning; AI robotics qualitative spatial reasoning; robot learning; AI robotics
Show Figures

Figure 1

MDPI and ACS Style

Wolter, D.; Kirsch, A. Leveraging Qualitative Reasoning to Learning Manipulation Tasks. Robotics 2015, 4, 253-283. https://doi.org/10.3390/robotics4030253

AMA Style

Wolter D, Kirsch A. Leveraging Qualitative Reasoning to Learning Manipulation Tasks. Robotics. 2015; 4(3):253-283. https://doi.org/10.3390/robotics4030253

Chicago/Turabian Style

Wolter, Diedrich; Kirsch, Alexandra. 2015. "Leveraging Qualitative Reasoning to Learning Manipulation Tasks" Robotics 4, no. 3: 253-283. https://doi.org/10.3390/robotics4030253

Find Other Styles

Article Access Map by Country/Region

1
Only visits after 24 November 2015 are recorded.
Search more from Scilit
 
Search
Back to TopTop