In this paper, we propose a robust and accurate estimation method for the distance required for digital holography reconstruction using convolutional neural networks (CNN) in off-axis digital holography (Off-axis DH). This method applies adaptive spectral pooling to reflect distance-related optical characteristics and minimize information loss during the training phase. Simulations and experiments have confirmed that the proposed method is more robust and accurate than search-based or CNN-based distance estimation methods.

A compact electrohydraulic actuator (C-EHA) is an innovative hydraulic system with a wide range of applications, particularly in automation, robotics, and aerospace. The actuator provides the benefits of hydraulics without the expense and space requirements of full-sized hydraulic systems and in a much cleaner manner. However, this actuator is associated with some disadvantages, such as a high level of nonlinearity, uncertainty, and a lack of studies. The development of a robust controller requires a thorough understanding of the system behavior as well as an accurate dynamic model of the system; however, finding an accurate dynamic model of a system is not always straightforward, and it is considered a significant challenge for engineers, particularly for a C-EHA because the critical parameters inside cannot be accessed. Our research aims to evaluate and confirm the ability of genetic programming (GP) to model a nonlinear system for a C-EHA. In our paper, we present and develop a GP model for the C-EHA system. Furthermore, our study presents a dynamic model of the system for comparison with the GP model. As a result, by using this actuator in the 1-DOF arm system and conducting experiments, we confirmed that the GP model has a better performance with less positional error compared with the proposed dynamic model. The model can be used to conduct further studies, such as designing controllers or system simulations.

No abstract

Slip detection is an essential technology for robotic grippers to autonomously grasp unknown objects and can be achieved using a tactile sensor. In this paper, we propose a high-performance multilayer-perceptron-based slip detection algorithm that utilizes only normal force data obtained by frequency selective surface(FSS) sensor arrays. This is achieved in three stages in this study. First, slip and no-slip training data are aggregated such that the data closely resemble those of the real world. Second, the most suitable means of preprocessing the raw sensor output is identified. Third, the classification method with the highest performance is chosen on the basis of a performance comparison among various classification techniques. The online performance of the algorithm is evaluated by conducting two tasks: a simple pick and place task and a task of maintaining a stable grasp of an object whose weight is changing.

No abstract