Loading [MathJax]/extensions/tex2jax.js

Leveraging human expert knowledge to automate forklift truck driving

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autorschaft

  • Phil Köhne
  • Mirko Schaper
  • Justus Lübbehusen
  • Benjamin Küster
  • Ludger Overmeyer

Externe Organisationen

  • Institut für integrierte Produktion Hannover (IPH) gGmbH

Details

Titel in ÜbersetzungNutzung des menschlichen Expertenwissens zur Automatisierung des Gabelstaplerfahrens
OriginalspracheEnglisch
Seitenumfang11
FachzeitschriftLogistics Journal
Jahrgang2024
Ausgabenummer20
PublikationsstatusVeröffentlicht - 30 Okt. 2024
Veranstaltung20. WGTL-Kolloquium 2024 - Dresden, Deutschland
Dauer: 26 Sept. 202427 Sept. 2024

Abstract

This work explores the challenges of fully automating in-house goods transport in environments where industrial trucks like forklift trucks remain necessary due to undefined load carrier positions and shapes. Imitation Learning (IL) is identified as a promising solution for vehicle control in repetitive tasks, yet its application in intralogistics is challenging by the dynamic complexity of industrial trucks and the large dimensional space involved. A Robot Operating System 2 (ROS2) framework is introduced, enabling the acquisition of driving data from both simulation environments and real-world demonstrators. The study also presents a network architecture combining a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network, facilitating end-to-end learning from spatial and temporal image data. The framework's effectiveness is evaluated using a dataset of expert driving maneuvers to assess the generalization potential of the IL-trained network in vehicle control in different scenarios. The research aims to demonstrate the utility of the proposed framework for data acquisition and validate IL as a control approach for industrial trucks that require generalization.

ASJC Scopus Sachgebiete

Zitieren

Leveraging human expert knowledge to automate forklift truck driving. / Köhne, Phil; Schaper, Mirko; Lübbehusen, Justus et al.
in: Logistics Journal, Jahrgang 2024, Nr. 20, 30.10.2024.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Köhne, P, Schaper, M, Lübbehusen, J, Küster, B, Stonis, M & Overmeyer, L 2024, 'Leveraging human expert knowledge to automate forklift truck driving', Logistics Journal, Jg. 2024, Nr. 20. https://doi.org/10.2195/lj_proc_koehne_en_202410_01
Köhne, P., Schaper, M., Lübbehusen, J., Küster, B., Stonis, M., & Overmeyer, L. (2024). Leveraging human expert knowledge to automate forklift truck driving. Logistics Journal, 2024(20). https://doi.org/10.2195/lj_proc_koehne_en_202410_01
Köhne P, Schaper M, Lübbehusen J, Küster B, Stonis M, Overmeyer L. Leveraging human expert knowledge to automate forklift truck driving. Logistics Journal. 2024 Okt 30;2024(20). doi: 10.2195/lj_proc_koehne_en_202410_01
Köhne, Phil ; Schaper, Mirko ; Lübbehusen, Justus et al. / Leveraging human expert knowledge to automate forklift truck driving. in: Logistics Journal. 2024 ; Jahrgang 2024, Nr. 20.
Download
@article{2ba3bfac1cbc4a5f9f3c9ef25931f422,
title = "Leveraging human expert knowledge to automate forklift truck driving",
abstract = "This work explores the challenges of fully automating in-house goods transport in environments where industrial trucks like forklift trucks remain necessary due to undefined load carrier positions and shapes. Imitation Learning (IL) is identified as a promising solution for vehicle control in repetitive tasks, yet its application in intralogistics is challenging by the dynamic complexity of industrial trucks and the large dimensional space involved. A Robot Operating System 2 (ROS2) framework is introduced, enabling the acquisition of driving data from both simulation environments and real-world demonstrators. The study also presents a network architecture combining a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network, facilitating end-to-end learning from spatial and temporal image data. The framework's effectiveness is evaluated using a dataset of expert driving maneuvers to assess the generalization potential of the IL-trained network in vehicle control in different scenarios. The research aims to demonstrate the utility of the proposed framework for data acquisition and validate IL as a control approach for industrial trucks that require generalization.",
keywords = "Imitation Learning (IL), industrial truck automation, intralogistics, load handling, ROS2",
author = "Phil K{\"o}hne and Mirko Schaper and Justus L{\"u}bbehusen and Benjamin K{\"u}ster and Malte Stonis and Ludger Overmeyer",
note = "Publisher Copyright: {\textcopyright} 2024 Logistics Journal: Proceedings.; 20. WGTL-Kolloquium 2024 ; Conference date: 26-09-2024 Through 27-09-2024",
year = "2024",
month = oct,
day = "30",
doi = "10.2195/lj_proc_koehne_en_202410_01",
language = "English",
volume = "2024",
number = "20",

}

Download

TY - JOUR

T1 - Leveraging human expert knowledge to automate forklift truck driving

AU - Köhne, Phil

AU - Schaper, Mirko

AU - Lübbehusen, Justus

AU - Küster, Benjamin

AU - Stonis, Malte

AU - Overmeyer, Ludger

N1 - Publisher Copyright: © 2024 Logistics Journal: Proceedings.

PY - 2024/10/30

Y1 - 2024/10/30

N2 - This work explores the challenges of fully automating in-house goods transport in environments where industrial trucks like forklift trucks remain necessary due to undefined load carrier positions and shapes. Imitation Learning (IL) is identified as a promising solution for vehicle control in repetitive tasks, yet its application in intralogistics is challenging by the dynamic complexity of industrial trucks and the large dimensional space involved. A Robot Operating System 2 (ROS2) framework is introduced, enabling the acquisition of driving data from both simulation environments and real-world demonstrators. The study also presents a network architecture combining a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network, facilitating end-to-end learning from spatial and temporal image data. The framework's effectiveness is evaluated using a dataset of expert driving maneuvers to assess the generalization potential of the IL-trained network in vehicle control in different scenarios. The research aims to demonstrate the utility of the proposed framework for data acquisition and validate IL as a control approach for industrial trucks that require generalization.

AB - This work explores the challenges of fully automating in-house goods transport in environments where industrial trucks like forklift trucks remain necessary due to undefined load carrier positions and shapes. Imitation Learning (IL) is identified as a promising solution for vehicle control in repetitive tasks, yet its application in intralogistics is challenging by the dynamic complexity of industrial trucks and the large dimensional space involved. A Robot Operating System 2 (ROS2) framework is introduced, enabling the acquisition of driving data from both simulation environments and real-world demonstrators. The study also presents a network architecture combining a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network, facilitating end-to-end learning from spatial and temporal image data. The framework's effectiveness is evaluated using a dataset of expert driving maneuvers to assess the generalization potential of the IL-trained network in vehicle control in different scenarios. The research aims to demonstrate the utility of the proposed framework for data acquisition and validate IL as a control approach for industrial trucks that require generalization.

KW - Imitation Learning (IL)

KW - industrial truck automation

KW - intralogistics

KW - load handling

KW - ROS2

UR - http://www.scopus.com/inward/record.url?scp=85214521971&partnerID=8YFLogxK

U2 - 10.2195/lj_proc_koehne_en_202410_01

DO - 10.2195/lj_proc_koehne_en_202410_01

M3 - Conference article

AN - SCOPUS:85214521971

VL - 2024

JO - Logistics Journal

JF - Logistics Journal

SN - 1860-7977

IS - 20

T2 - 20. WGTL-Kolloquium 2024

Y2 - 26 September 2024 through 27 September 2024

ER -