EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Bayesian-Assisted Keypoint Detection for Pose Estimation in Assembly Automation

Debo Shi, Alireza Rahimpour iD, Amin Ghafourian iD, Mohammad Mahdi Naddaf Shargh iD, Devesh Upadhyay iD, Ty A Lasky iD, Iman Soltani iD

Sensors · 02.07.2023 · 23 (13) · 6107

DOI: 10.3390/s23136107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.07.2023. Verfasst von Debo Shi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of California Davis, Davis, CA 95616, USA. Hauptthemen laut MEDLINE: Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ford Motor Company, Ford Greenfield Labs.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pose estimation is crucial for automating assembly tasks, yet achieving sufficient accuracy for assembly automation remains challenging and part-specific. This paper presents a novel, streamlined approach to pose estimation that facilitates automation of assembly tasks. Our proposed method employs deep learning on a limited number of annotated images to identify a set of keypoints on the parts of interest. To compensate for network shortcomings and enhance accuracy we incorporated a Bayesian updating stage that leverages our detailed knowledge of the assembly part design. This Bayesian updating step refines the network output, significantly improving pose estimation accuracy. For this purpose, we utilized a subset of network-generated keypoint positions with higher quality as measurements, while for the remaining keypoints, the network outputs only serve as priors. The geometry data aid in constructing likelihood functions, which in turn result in enhanced posterior distributions of keypoint pixel positions. We then employed the maximum a posteriori (MAP) estimates of keypoint locations to obtain a final pose, allowing for an update to the nominal assembly trajectory. We evaluated our method on a 14-point snap-fit dash trim assembly for a Ford Mustang dashboard, demonstrating promising results. Our approach does not require tailoring to new applications, nor does it rely on extensive machine learning expertise or large amounts of training data. This makes our method a scalable and adaptable solution for the production floors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBayes TheoremAutomation

Stichwörter der Autor:innen

AIassembly automationconvolutional neural networksdeep learningkeypoint detectionmanufacturing automationpose estimationrobot manipulationrobotics

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, University of California Davis, Davis, CA 95616, USA.
  • Greenfield Labs, Ford Motor Company, Palo Alto, CA 94304, USA.
  • Department of Mechanical and Aerospace Engineering, University of California Davis, Davis, CA 95616, USA.

ORCID-Profile: Alireza Rahimpour, Amin Ghafourian, Mohammad Mahdi Naddaf Shargh, Devesh Upadhyay, Ty A Lasky, Iman Soltani

Förderung

  • Ford Motor Company
  • Ford Greenfield Labs

Zitieren

APA

Shi, D., Rahimpour, A., Ghafourian, A., Naddaf Shargh, M. M., Upadhyay, D., Lasky, T. A., & Soltani, I. (2023). Deep Bayesian-Assisted Keypoint Detection for Pose Estimation in Assembly Automation. Sensors, 23(13), 6107. https://doi.org/10.3390/s23136107

Vancouver

Shi D, Rahimpour A, Ghafourian A, Naddaf Shargh MM, Upadhyay D, Lasky TA, et al. Deep Bayesian-Assisted Keypoint Detection for Pose Estimation in Assembly Automation. Sensors. 2023;23(13):6107. doi:10.3390/s23136107

BibTeX
@article{Shi2023,
  author = {Shi, Debo and Rahimpour, Alireza and Ghafourian, Amin and Naddaf Shargh, Mohammad Mahdi and Upadhyay, Devesh and Lasky, Ty A and Soltani, Iman},
  title = {Deep Bayesian-Assisted Keypoint Detection for Pose Estimation in Assembly Automation},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {13},
  pages = {6107},
  doi = {10.3390/s23136107}
}
Kostenlos starten →