elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Development of an interactive robot programming method

Willibald, Christoph (2020) Development of an interactive robot programming method. DLR-Interner Bericht. DLR-IB-RM-OP-2020-19. Master's. Technische Universität München. 86 S.

[img] PDF - Only accessible within DLR
18MB

Abstract

Today's robot programming methods are not suitable for intuitively teaching robots new tasks. For this reason, the potential of new generations of collaborative robots for production cannot yet be fully exploited. In this work, we propose an active learning framework, in which the robot and the user collaborate in order to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. An on-line anomaly detection algorithm therefore automatically identifies new situations during task execution by monitoring the deviation between measured- and commanded sensor values. The robot then triggers a teaching phase, in which the user decides to either refine an existing- or demonstrate a new skill. The different skills of a task are encoded in separate probabilistic models and structured in a high-level graph, guaranteeing a robust execution and a successful transition between skills. The graph is used as visual feedback for the user, to verify the effects of his demonstrations on the robot's task knowledge. In a user study, our approach is compared to two state of the art Programming by Demonstration frameworks on a real system. An increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program conditional tasks for the production with our framework.

Item URL in elib:https://elib.dlr.de/134018/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Development of an interactive robot programming method
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Willibald, ChristophTechnische Universität MünchenUNSPECIFIEDUNSPECIFIED
Date:1 February 2020
Refereed publication:No
Open Access:No
Number of Pages:86
Status:Published
Keywords:Learning from Demonstration; Programming by Demonstration; intuitive programming; interactive teaching; interactive task learning; robot learning; decision states; conditional tasks; anomaly detection; novelty detection; user study; interactive programming; graph-based tasks; graph learning; graph generation; refinement; incremental motion learning; incremental task refinement
Institution:Technische Universität München
Department:Associate Professorship of Human-centered Assistive Robotics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space System Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Space System Technology
DLR - Research theme (Project):Vorhaben Intuitive Mensch-Roboter Schnittstelle (old), Vorhaben Interagierende Robotersteuerung (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Deposited By: Eiband, Thomas
Deposited On:10 Feb 2020 12:46
Last Modified:10 Feb 2020 12:46

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.