Paper
27 March 2022 Flexible optical pressure sensor with high spatial resolution based on deep learning
Author Affiliations +
Proceedings Volume 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications; 121693C (2022) https://doi.org/10.1117/12.2623649
Event: Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 2021, Kunming, China
Abstract
Robot grasping and manipulating objects rely on sensors for force magnitude and spatial detection entirely. The pressure sensor is one of the most basic sensors. Most of the existing pressure sensors are composed of rigid materials, relying on resistance, piezoelectricity, and capacitance principles. The sensors are sensitive to electromagnetic fields, which limits their applications largely. Simultaneously, the resolution of pressure sensors plays an essential role in precise measurements. Hence, we designed a flexible optical pressure sensor with high spatial resolution using flexible silicone as substrate, optical fibers for transmitting light, and a camera as the receiver of images. This optical sensor is not affected by electromagnetic fields, while the flexible materials achieve soft properties of the sensor. Deep learning can decipher pictures. As a result, the better Root Mean Square Error (RMSE) for localization is about 0.1 mm order of magnitude, and the normal force (Fz) is around 0.67 N. This work has contributed to sensors for flexible electronics and robotics.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhengshuai Cao, Zhenyue Lu, Qi Zhang, Dong Luo, Jingtao Chen, Qiong Tian, Zhiyuan Liu, and Yuming Dong "Flexible optical pressure sensor with high spatial resolution based on deep learning", Proc. SPIE 12169, Eighth Symposium on Novel Photoelectronic Detection Technology and Applications, 121693C (27 March 2022); https://doi.org/10.1117/12.2623649
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Sensors

RGB color model

Convolution

Silicon

Spatial resolution

Cameras

Optical fibers

Back to Top