Action-By-Detection: Efficient Forklift Action Detection for Autonomous Mobile Robots in Warehouses

Alexander Prutsch*, Horst Possegger, Horst Bischof

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

Understanding actions of other agents increases the efficiency of autonomous mobile robots (AMRs) since they encompass intention and indicate future movements. We propose a new method that allows us to infer vehicle actions using a shallow image-based classification model. The actions are classified via bird's-eye view scene crops, where we project the detections of a 3D object detection model onto a context map. We learn map context information and aggregate temporal sequence information without requiring object tracking. This results in a highly efficient classification model that can easily be deployed on embedded AMR hardware. To evaluate our approach, we create new large-scale synthetic datasets showing warehouse traffic based on real vehicle models and geometry.

Originalspracheenglisch
Titel2024 IEEE International Conference on Robotics and Automation (ICRA)
Herausgeber (Verlag)IEEE
Seiten10757-10763
Seitenumfang7
ISBN (elektronisch)9798350384574
DOIs
PublikationsstatusVeröffentlicht - 8 Aug. 2024
Veranstaltung2024 IEEE International Conference on Robotics and Automation: ICRA 2024 - Yokohama, Japan
Dauer: 13 Mai 202417 Mai 2024

Konferenz

Konferenz2024 IEEE International Conference on Robotics and Automation
Land/GebietJapan
OrtYokohama
Zeitraum13/05/2417/05/24

ASJC Scopus subject areas

  • Software
  • Steuerungs- und Systemtechnik
  • Elektrotechnik und Elektronik
  • Artificial intelligence

Fingerprint

Untersuchen Sie die Forschungsthemen von „Action-By-Detection: Efficient Forklift Action Detection for Autonomous Mobile Robots in Warehouses“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren