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

Towards efficient and scalable visual homing

Stelzer, Annett and Vayugundla, Mallikarjuna and Mair, Elmar and Suppa, Michael and Burgard, Wolfram (2018) Towards efficient and scalable visual homing. The International Journal of Robotics Research, 37 (2-3), pp. 225-248. SAGE Publications. DOI: 10.1177/0278364918761115 ISSN 0278-3649

[img] PDF
5MB

Abstract

Visual homing describes the ability of a robot to autonomously return to its starting position along a previously traversed path using visual information. In this paper, we propose a method for visual homing that is solely based on bearing angles to landmarks. During the first traversal of a path, the robot creates a sequence of viewframes, which are rotationally aligned landmark angle configurations at certain locations. During homing, the robot calculates homing vectors which subsequently lead it in the direction to align the currently perceived set of landmark observations with the reference viewframe until the home location is reached. This paper discusses methods for homing vector calculation and proposes new methods which are more robust and yield straighter homing paths in case of non-isotropic landmark distributions and false landmark matches. Furthermore, we present the Trail-Map, which is a novel data structure for storing a sequence of viewframes in a non-redundant and scalable way. The Trail-Map exploits the fact that the bearing angles to distant landmarks and landmarks in the direction of movement hardly change when the robot moves, whereas close landmarks change their bearing angles quickly. Thus, the Trail-Map allows easy downscaling by deleting observations that correspond to nearby, quickly-changing landmarks and, thus, retaining the stable, translation invariant landmark information. We show the memory efficiency and scalability of the data structure in simulations and in real-world indoor and outdoor experiments. This makes the proposed method for visual homing suitable for mobile robots with limited computational and memory resources.

Item URL in elib:https://elib.dlr.de/119587/
Document Type:Article
Title:Towards efficient and scalable visual homing
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Stelzer, AnnettAnnett.Stelzer (at) dlr.deUNSPECIFIED
Vayugundla, MallikarjunaMallikarjuna.Vayugundla (at) dlr.dehttps://orcid.org/0000-0002-9277-0461
Mair, ElmarUNSPECIFIEDUNSPECIFIED
Suppa, MichaelMichael.Suppa (at) roboception.deUNSPECIFIED
Burgard, WolframUniversität FreiburgUNSPECIFIED
Date:1 February 2018
Journal or Publication Title:The International Journal of Robotics Research
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:37
DOI :10.1177/0278364918761115
Page Range:pp. 225-248
Publisher:SAGE Publications
ISSN:0278-3649
Status:Published
Keywords:visual homing, range-free navigation, omnidirectional vision
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Technology
DLR - Research area:Raumfahrt
DLR - Program:R SY - Technik für Raumfahrtsysteme
DLR - Research theme (Project):R - Vorhaben Multisensorielle Weltmodellierung
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013)
Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Deposited By: Vayugundla, Mallikarjuna
Deposited On:16 Apr 2018 03:48
Last Modified:06 Sep 2019 15:30

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.