A new differentiable architecture search method for optimizing convolutional neural networks in the digital twin of intelligent robotic grasping

Weifei Hu (), Jinyi Shao (), Qing Jiao (), Chuxuan Wang (), Jin Cheng (), Zhenyu Liu () and Jianrong Tan ()
Additional contact information
Weifei Hu: Zhejiang University
Jinyi Shao: Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province
Qing Jiao: Zhejiang University
Chuxuan Wang: Zhejiang University
Jin Cheng: Zhejiang University
Zhenyu Liu: Zhejiang University
Jianrong Tan: Zhejiang University

Journal of Intelligent Manufacturing, 2023, vol. 34, issue 7, No 5, 2943-2961

Abstract: Abstract Convolutional neural networks (CNNs) have been widely used for object recognition and grasping posture planning in intelligent robotic grasping (IRG). Compared with the traditional usage of CNNs in image recognition, IRGs require high recognition accuracy and computational efficiency. However, the existing methodologies for CNN architecture design often rely on human experience and numerous trial-and-error attempts, which make it a very challenging task to obtain an optimal CNN for IRGs. To tackle this challenge, this paper develops a new differentiable architecture search (DARTS) method considering the floating-point operations (FLOPs) of CNNs, named the DARTS-F method, which converts the discrete CNN architecture search to a gradient-based continuous optimization problem and considers both the prediction accuracy and the computational cost of the CNN during the optimization. To efficiently identify the optimal neural network, this paper adopts a bilevel optimization, which first trains the neural network weights in the inner level and then optimizes the neural network architecture by fine-tuning the operational variables in the outer level. In addition, a new digital twin (DT) of IRG is developed considering the physics of realistic robotic grasping in the DT’s virtual space, which could not only improve the IRG accuracy but also avoid the expensive training time. In the experiments, the proposed DARTS-F method could generate an optimized CNN with higher prediction accuracy and lower FLOPs than those obtained by the original DARTS method. The DT framework improves the accuracy of real robotic grasping from 61 to 71%.

Keywords: Intelligent robotic grasping; Digital twin; Convolutional neural network; Differentiable architecture search; Deep learning; Design optimization (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-022-01971-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:34:y:2023:i:7:d:10.1007_s10845-022-01971-8

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-022-01971-8

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().