In this paper, we propose a novel shape-sensing method based on deep learning with a multi-core optical fiber for the accurate shape-sensing of catheters and guidewires. Firstly, we designed a catheter with embedded multi-core fiber containing three sensing outer cores and one temperature compensation middle core. Then, we analyzed the relationship between the central wavelength shift, the curvature of the multi-core Fiber Bragg Grating (FBG), and temperature compensation methods to establish a Particle Swarm Optimization (PSO) BP neural network-based catheter shape sensing method. Finally, experiments were conducted in both constant and variable temperature environments to validate the method. The average and maximum distance errors of the PSO-BP neural network were 0.57 and 1.33 mm, respectively, under constant temperature conditions, and 0.36 and 0.96 mm, respectively, under variable temperature conditions. This well-sensed catheter shape demonstrates the effectiveness of the shape-sensing method proposed in this paper and its potential applications in real surgical catheters and guidewire.
To meet the practical application requirements of cardiac fixation during off-pump coronary artery bypass surgery, a soft cardiac fixator with a flexible arm was previously designed. To enable the soft cardiac fixator to adapt to uncertain external forces, this study evaluates the variable-stiffness performance of the flexible arm. First, the flexible arm was simplified as a soft silicone manipulator measuring 60 mm × 90 mm × 120 mm, which can actuate, soften, or stiffen independently along the length of the arm by combining granular jamming with input pressure. Then, the soft manipulator was modelled as a cantilever beam to analyse its variable-stiffness performance with granular jamming. Next, based on theoretical analysis and calculations, many experiments were conducted to evaluate the variable-stiffness performance of the soft manipulator. The experimental results demonstrated that the variable-stiffness performance is influenced by the flexible arm length, the size of the granules, and the input pressure.
Fiber-optic sensors are highly promising within soft robot sensing applications, but sensing methods based on geometry-based reconstruction limit the sensing capability and range. In this study, a fiber-optic sensor with a different deployment strategy for indirect sensing to monitor the outside posture of a soft manipulator is presented. The internal support structure’s curvature was measured using the FBG sensor, and its mapping to the external pose was then modelled using a modified LSTM network. The error was assumed to follow the Gaussian distribution in the LSTM neural network and was rectified by maximum likelihood estimation to address the issue of noise generated during the deformation transfer and curvature sensing of the soft structure. For the soft manipulator, the network model’s sensing performance was demonstrated. The proposed method’s average absolute error for posture sensing was 63.3% lower than the error before optimization, and the root mean square error was 56.9% lower than the error before optimization. The comparison results between the experiment and the simulation demonstrate the viability of the indirect measurement of the soft structure posture using FBG sensors based on the data-driven method, as well as the significant impact of the error optimization method based on the Gaussian distribution assumption.
22 April 2024 in IEEE Photonics Technology Letters
This letter proposes a novel algorithm for three-dimensional shape reconstruction and torsion compensation using a spun multi-core optic fiber (SMOF). The torsion-compensation Bishop algorithm (TCBA) addresses torsion in SMOFs and enables accurate coordinate correction. Experimental validation is conducted by arranging the SMOF sensor in controlled helical shapes. The reconstruction accuracy is increased by 10.87%. Additionally, the mean error is reduced from 7.21 mm to 2.50 mm. The algorithm can be used for navigation in flexible robotics and minimally invasive surgery, where precise positioning and manipulation are crucial.
In fields such as polarization navigation and imaging, there is a demand for polarizers to simultaneously possess a high transmittance and extinction ratio. However, most studies focus solely on a single metric for polarizer design. To address this issue, this paper proposed a metasurface polarizer with a transition layer and its efficient design method, aiming to enhance the polarizers’ transmittance and extinction ratio performance simultaneously. An all-dielectric metasurface polarizer with a TiO2 transition layer was designed, and a tandem neural network was constructed by combining forward prediction and inverse design networks. The network is successfully trained by utilizing structural parameters and spectral response Tx and Ty datasets collected through simulation software. A high-performance metasurface polarizer was designed under the desired metrics with a transmittance of 90% and an extinction ratio of 40 dB. The proposed method in this paper made progress in the comprehensive optimization of polarizer performance. It is more accurate and efficient compared to other design methods and is better suited for practical applications.