EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning

Bin Zhao iD, Chengdong Wu, Fengshan Zou, Xuejiao Zhang, Ruohuai Sun, Yang Jiang

Sensors · 2023

DOI: 10.3390/s23135826 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Bin Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Northeastern University, Shenyang 110819, China. Hauptthemen laut MEDLINE: Learning, Algorithms. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China under Grants, the Provincial Key Research and Development for Liaoning under Grant.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningAlgorithmsTechnologyMachine Learning

Stichwörter der Autor:innen

SqueezeNetattention mechanismdeep learninggrab detectionmulti-object detection

Autor:innen und Institutionen

  • College of Information Science and Engineering, Northeastern University, Shenyang 110819, China.
  • SIASUN Robot & Automation Co., Ltd., Shenyang 110168, China.
  • Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110169, China.

ORCID-Profile: Bin Zhao

Förderung

  • the National Natural Science Foundation of China under Grants
  • the Provincial Key Research and Development for Liaoning under Grant

Zitieren

APA

Zhao, B., Wu, C., Zou, F., Zhang, X., Sun, R., & Jiang, Y. (2023). Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning. Sensors. https://doi.org/10.3390/s23135826

Vancouver

Zhao B, Wu C, Zou F, Zhang X, Sun R, Jiang Y. Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning. Sensors. 2023. doi:10.3390/s23135826

BibTeX
@article{Zhao2023,
  author = {Zhao, Bin and Wu, Chengdong and Zou, Fengshan and Zhang, Xuejiao and Sun, Ruohuai and Jiang, Yang},
  title = {Research on Small Sample Multi-Target Grasping Technology Based on Transfer Learning},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23135826}
}
Kostenlos starten →