Skip to Main content Skip to Navigation
Conference papers

Qualitative Spatial Reasoning for Boosting Learning-Based Robotics

Abstract : Learning and motion planning are powerful 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 outline how both methods can be combined using an expressive qualitative knowledge representation as a link. We argue that the crucial step in this integration is to employ a representation based on a well-defined semantics which empowers reasoning to boost performance of learning as well as of the resulting action plans. We present an architecture for learning based robotics that exploits qualitative reasoning. Expected beneficiaries of this approach are discussed, some of which are already demonstrated in proof-of-concept experiments.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01693628
Contributor : Alexandra Kirsch <>
Submitted on : Friday, January 26, 2018 - 1:43:39 PM
Last modification on : Monday, January 29, 2018 - 1:43:34 PM
Document(s) archivé(s) le : Friday, May 25, 2018 - 6:10:13 AM

File

wolter15qualitative-ws-preprin...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01693628, version 1

Citation

Diedrich Wolter, Alexandra Kirsch. Qualitative Spatial Reasoning for Boosting Learning-Based Robotics. IROS Workshop Machine Learning in Planning and Control of Robot Motion, 2015, Hamburg, Germany. ⟨hal-01693628⟩

Share

Metrics

Record views

85

Files downloads

57