Symbolic reasoning about unseen objects from multimodal sensory feedback for manipulation

Title

Symbolic reasoning about unseen objects from multimodal sensory feedback for manipulation

 Author

Helsloot, Arthur (TU Delft Mechanical, Maritime and Materials Engineering; TU Delft Biomechanical Engineering; TU Delft Delft Center for Systems and Control; TU Delft Cognitive Robotics)

Contributor

Imre, M. (mentor) ORCID 0000-0003-1749-9365
Hernández, Carlos (mentor) ORCID 0000-0001-6094-4917
Kober, J. (mentor) ORCID 0000-0001-7257-5434
Sijs, Joris (graduation committee)

Degree granting institution

Delft University of Technology

 Date

2020-12-11

 Abstract

Robotically manipulating objects can be very challenging when not all of the environment can be fully observed, e.g. in environments which are physically and visually accessible from only a single side. By using multimodal sensory feedback and symbolic reasoning, conclusions can be drawn about the presence of objects that cannot be observed directly. This paper presents the Symbolic Reasoning for Partially Observable Environments (SyRePOE) system, which uses an ontology to maintain its world model and a reasoner to infer information about unobservable objects. SyRePOE is demonstrated in simulation and on a real robot, where it is tasked with stocking a retail shelf.

 Subject

knowledge representation and reasoning
Cognitive architecture
task planning
Robot arm control

 To reference this document use:

http://resolver.tudelft.nl/uuid:f60b9403-f2ab-45a3-929c-a6dbd067dea7

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2020 Arthur Helsloot
Files
PDF MSc_Thesis_Arthur_Helsloot.pdf 16.43 MB
MP4 submission_video.mp4 18.1 MB
Close viewer