Next Article in Journal
Self-Assembled TiN-Metal Nanocomposites Integrated on Flexible Mica Substrates towards Flexible Devices
Previous Article in Journal
Linguistic-Driven Partial Semantic Relevance Learning for Skeleton-Based Action Recognition
Previous Article in Special Issue
Research on the Collision Risk of Fusion Operation of Manned Aircraft and Unmanned Aircraft at Zigong Airport
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Robotic Grasping of Novel Objects Based on Deep-Learning Based Feature Detection

by
Kai Sherng Khor
1,
Chao Liu
2 and
Chien Chern Cheah
1,*
1
School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore 639798, Singapore
2
Department of Robotics, Laboratory of Computer Science, Robotics and Microelectronics of Montpellier, Centre National de la Recherche Scientifique, University of Montpellier, 34095 Montpellier, France
*
Author to whom correspondence should be addressed.
Sensors 2024, 24(15), 4861; https://doi.org/10.3390/s24154861
Submission received: 29 June 2024 / Revised: 23 July 2024 / Accepted: 24 July 2024 / Published: 26 July 2024

Abstract

In recent years, the integration of deep learning into robotic grasping algorithms has led to significant advancements in this field. However, one of the challenges faced by many existing deep learning-based grasping algorithms is their reliance on extensive training data, which makes them less effective when encountering unknown objects not present in the training dataset. This paper presents a simple and effective grasping algorithm that addresses this challenge through the utilization of a deep learning-based object detector, focusing on oriented detection of key features shared among most objects, namely straight edges and corners. By integrating these features with information obtained through image segmentation, the proposed algorithm can logically deduce a grasping pose without being limited by the size of the training dataset. Experimental results on actual robotic grasping of unknown objects over 400 trials show that the proposed method can achieve a higher grasp success rate of 98.25% compared to existing methods.
Keywords: robotics; robotic grasping; unknown objects robotics; robotic grasping; unknown objects

Share and Cite

MDPI and ACS Style

Khor, K.S.; Liu, C.; Cheah, C.C. Robotic Grasping of Novel Objects Based on Deep-Learning Based Feature Detection. Sensors 2024, 24, 4861. https://doi.org/10.3390/s24154861

AMA Style

Khor KS, Liu C, Cheah CC. Robotic Grasping of Novel Objects Based on Deep-Learning Based Feature Detection. Sensors. 2024; 24(15):4861. https://doi.org/10.3390/s24154861

Chicago/Turabian Style

Khor, Kai Sherng, Chao Liu, and Chien Chern Cheah. 2024. "Robotic Grasping of Novel Objects Based on Deep-Learning Based Feature Detection" Sensors 24, no. 15: 4861. https://doi.org/10.3390/s24154861

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop