Paper
6 August 2023 Study of flexible capacitive sensors applied to underdriven manipulators for grasping object recognition
Yonggeng Wei, Awen Xu
Author Affiliations +
Proceedings Volume 12781, International Conference on Optoelectronic Information and Functional Materials (OIFM 2023); 127810T (2023) https://doi.org/10.1117/12.2686701
Event: 2023 International Conference on Optoelectronic Information and Functional Materials (OIFM 2023), 2023, Guangzhou, JS, China
Abstract
To address the problem of how to recognize the grasped objects by underdriven manipulators, a new flexible capacitive sensor is proposed to improve the perceptual sensitivity of the manipulator and a grasping recognition method combined with machine learning methods to improve the recognition accuracy. The designed flexible sensor uses CB/Ecoflex as the conductive filler and Ecoflex as the substrate. The study optimizes the sensor design parameters by building a capacitance model; the test results show that the sensor has a good measurement sensitivity. The gripping test was performed by installing this sensor on each joint of the underdriven manipulator and analyzing the change of capacitance when gripping different surface contours to identify the shape of the object. The test system takes the collected capacitance signal and processes the collected data set. Two different machine learning algorithms are used to train the dataset for testing. Through experimental analysis, the object recognition accuracy is up to more than 90% in both cases, and the test verifies the effectiveness of the sensor and the recognition method.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yonggeng Wei and Awen Xu "Study of flexible capacitive sensors applied to underdriven manipulators for grasping object recognition", Proc. SPIE 12781, International Conference on Optoelectronic Information and Functional Materials (OIFM 2023), 127810T (6 August 2023); https://doi.org/10.1117/12.2686701
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Sensors

Capacitance

Object recognition

Machine learning

Haptic technology

Back to Top