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

Robotic Learning from Successful and Failed Demonstration

Friedrich, Sissy (2021) Robotic Learning from Successful and Failed Demonstration. DLR-Interner Bericht. DLR-IB-RM-OP-2021-107. Master's. Munich University of Applied Sciences. 65 S.

[img] PDF - Only accessible within DLR
9MB

Abstract

In remote applications such as space exploration, intelligent assistance robots are supposed to work autonomously without human intervention. It is essential that such assistance robots provide a large skill catalog. However, programming new actions manually is cumbersome. Instead, it would be much more efficient to acquire new skills through learning from demonstration. When training new skills, errors may occur, as some tasks are challenging to execute - even for humans. From this, a fundamental question arises: Is it possible to leverage failed demonstrations for learning instead of discarding them? To answer this question, this thesis evaluates three algorithms toward this possibility. First Gaussian Mixture Regression (GMR), second Hidden Markov Model (HMM), and third Dynamic Movement Primitive (DMP). These algorithms are designed to generate the trajectory of a robot’s end-effector depending on the pose of a target object. Using this approach, successful and failed demonstrations are applicable to be used to learn a versatile policy. The methods are compared and used as a geometrical description of a task, where the target pose of the end-effector is optimized with respect to the best possible reachability. The on-line motion generation is then integrated into the cognitive reasoning framework on the humanoid robot Rollin’ Justin. The different motion generation methods are evaluated and experiments on the humanoid robot prove the successful application of the proposed method. In conclusion, this thesis shows that it is possible to learn explicitly from failed demonstrations if the symbolic information is known.

Item URL in elib:https://elib.dlr.de/144042/
Document Type:Monograph (DLR-Interner Bericht, Master's)
Title:Robotic Learning from Successful and Failed Demonstration
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Friedrich, Sissysissy.friedrich (at) dlr.deUNSPECIFIED
Date:September 2021
Refereed publication:No
Open Access:No
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Number of Pages:65
Status:Published
Keywords:Robtics, Learning from Demonstration, FUTURO
Institution:Munich University of Applied Sciences
Department:Computer Science and Mathematics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - On-Orbit Servicing [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Autonomy and Teleoperation
Deposited By: Leidner, Daniel
Deposited On:28 Sep 2021 09:13
Last Modified:28 Sep 2021 09:13

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.