Biomimetic Intelligence and Robotics最新文献

People who have trouble communicating verbally are often dependent on sign language, which can be difficult for most people to understand, making interaction with them a difficult endeavor. The Sign Language Recognition (SLR) system takes an input expression from a hearing or speaking-impaired person and outputs it in the form of text or voice to a normal person. The existing study related to the Sign Language Recognition system has some drawbacks, such as a lack of large datasets and datasets with a range of backgrounds, skin tones, and ages. This research efficiently focuses on Sign Language Recognition to overcome previous limitations. Most importantly, we use our proposed Convolutional Neural Network (CNN) model, “ConvNeural”, in order to train our dataset. Additionally, we develop our own datasets, “BdSL_OPSA22_STATIC1” and “BdSL_OPSA22_STATIC2”, both of which have ambiguous backgrounds. “BdSL_OPSA22_STATIC1” and “BdSL_OPSA22_STATIC2” both include images of Bangla characters and numerals, a total of 24,615 and 8437 images, respectively. The “ConvNeural” model outperforms the pre-trained models with accuracy of 98.38% for “BdSL_OPSA22_STATIC1” and 92.78% for “BdSL_OPSA22_STATIC2”. For “BdSL_OPSA22_STATIC1” dataset, we get precision, recall, F1-score, sensitivity and specificity of 96%, 95%, 95%, 99.31% , and 95.78% respectively. Moreover, in case of “BdSL_OPSA22_STATIC2” dataset, we achieve precision, recall, F1-score, sensitivity and specificity of 90%, 88%, 88%, 100%, and 100% respectively.

In this study, we proposed a recognition method based on deep artificial neural networks to identify various elements in pipelines and instrumentation diagrams (P&ID) in image formats, such as symbols, texts, and pipelines. Presently, the P&ID image format is recognized manually, and there is a problem with a high recognition error rate; therefore, automation of the above process is an important issue in the processing plant industry. The China National Offshore Petrochemical Engineering Co. provided the image set used in this study, which contains 51 P&ID drawings in the PDF. We converted the PDF P&ID drawings to PNG P&IDs with an image size of 8410 × 5940. In addition, we used labeling software to annotate the images, divided the dataset into training and test sets in a 3:1 ratio, and deployed a deep neural network for recognition. The method proposed in this study is divided into three steps. The first step segments the images and recognizes symbols using YOLOv5 + SE. The second step determines text regions using character region awareness for text detection, and performs character recognition within the text region using the optical character recognition technique. The third step is pipeline recognition using YOLOv5 + SE. The symbol recognition accuracy was 94.52%, and the recall rate was 93.27%. The recognition accuracy in the text positioning stage was 97.26% and the recall rate was 90.27%. The recognition accuracy in the character recognition stage was 90.03% and the recall rate was 91.87%. The pipeline identification accuracy was 92.9%, and the recall rate was 90.36%.

Camera-based object tracking systems in a given closed environment lack privacy and confidentiality. In this study, light detection and ranging (LiDAR) was applied to track objects similar to the camera tracking in a closed environment, guaranteeing privacy and confidentiality. The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios. In Scenario I, the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface, achieved by analyzing LiDAR data collected from several locations within the closed environment. Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single, fixed location. Real-time experiments are conducted with human subjects navigating predefined paths. Three individuals move within an environment, while LiDAR, fixed at the center, dynamically tracks and identifies their locations at multiple instances. Results demonstrate that a single, strategically positioned LiDAR can adeptly detect objects in motion around it. Furthermore, this study provides a comparison of various regression techniques for predicting bounding box coordinates. Gaussian process regression (GPR), combined with particle swarm optimization (PSO) for prediction, achieves the lowest prediction mean square error of all the regression techniques examined at 0.01. Hyperparameter tuning of GPR using PSO significantly minimizes the regression error. Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls, surveillance systems, and various Internet of Things scenarios.

Soft robotics is a breakthrough technology to support human–robot interactions. The soft structure of a soft robot can increase safety during human and robot interactions. One of the promising soft actuators for soft robotics is dielectric elastomer actuators (DEAs). DEAs can operate silently and have an excellent energy density. The simple structure of DEAs leads to the easy fabrication of soft actuators. The simplicity combined with silent operation and high energy density make DEAs interesting for soft robotics researchers. DEAs actuation follows the Maxwell-pressure principle. The pressure produced in the DEAs actuation depends much on the voltage applied. Common DEAs requires high voltage to gain an actuation. Since the power consumption of DEAs is in the milli-Watt range, the current needed to operate the DEAs can be neglected. Several commercially available DC-DC converters can convert the volt range to the kV range. In order to get a voltage in the 2–3 kV range, the reliable DC-DC converter can be pricy for each device. This problem hinders the education of soft actuators, especially for a newcomer laboratory that works in soft electric actuators. This paper introduces an entirely do-it-yourself (DIY) Ultrahigh voltage amplifier (UHV-Amp) for education in soft robotics. UHV-Amp can amplify 12 V to at a maximum of 4 kV DC. As a demonstration, we used this UHV-Amp to test a single layer of powdered-based DEAs. The strategy to build this educational type UHV-Amp was utilizing a Cockcroft-Walton circuit structure to amplify the voltage range to the kV range. In its current state, the UHV-Amp has the potential to achieve approximately 4 kV. We created a simple platform to control the UHV-Amp from a personal computer. In near future, we expect this easy control of the UHV-Amp can contribute to the education of soft electric actuators.

The aye-aye (Daubentonia madagascariensis) is a nocturnal lemur native to the island of Madagascar with a unique thin middle finger. Its slender third digit has a remarkably specific adaptation, allowing them to perform tap-scanning to locate small cavities beneath tree bark and extract wood-boring larvae from it. As an exceptional active acoustic actuator, this finger makes an aye-aye’s biological system an attractive model for pioneering Nondestructive Evaluation (NDE) methods and robotic systems. Despite the important aspects of the topic in the aye-aye’s unique foraging and its potential contribution to the engineering sensory, little is known about the mechanism and dynamics of this unique finger. This paper used a motion-tracking approach for the aye-aye’s middle finger using simultaneous video graphic capture. To mimic the motion, a two-link robot arm model is designed to reproduce the trajectory. Kinematics formulations were proposed to derive the motion of the middle finger using the Lagrangian method. In addition, a hardware model was developed to simulate the aye-aye’s finger motion. To validate the model, different motion states such as trajectory paths and joint angles, were compared. The simulation results indicate the kinematics of the model were consistent with the actual finger movement. This model is used to understand the aye-aye’s unique tap-scanning process for pioneering new tap-testing NDE strategies for various inspection applications.

This article has the objective of presenting our method to develop and test a motion control system for a heavy-duty hydraulically actuated manipulator, which is part of a newly developed prototype featuring a fully-autonomous unmanned forestry machine. This control algorithm is based on functional analysis and differential algebra, under the concepts of a new type of approach known as model-free intelligent PID control (iPID). As it can be unsafe to test this form of control directly on real hardware, our main contribution is to introduce a framework for developing and testing control software. This framework incorporates a desktop-size mockup crane equipped with comparable hardware as the real one, which we design and manufactured using 3D-printing. This downscaled mechatronic system allows to safely test the implementation of control software in real-time hardware directly on our desks, prior to the actual testing on the real machine. The results demonstrate that this development framework is useful to safely test control software for heavy-duty systems, and it helped us present the first experiments with the world’s first unmanned forestry machine capable of performing fully autonomous forestry tasks.

With the aim of addressing the visual positioning problem of board-to-board (BTB) jacks during the automatic assembly of flexible printed circuit (FPC) in mobile phones, an FPC-BTB jack detection method based on the optimized You Only Look Once, version 5 (YOLOv5) deep learning algorithm was proposed in this study. An FPC-BTB jack real-time detection and positioning system was developed for the real-time target detection and pose output synchronization of the BTB jack. On that basis, a visual positioning experimental platform that integrated a UR5e manipulator arm and Hikvision industrial camera was built for BTB jack detection and positioning experiments. As indicated by the experimental results, the developed FPC-BTB jack detection and positioning system for BTB target recognition and positioning achieved a success rate of 99.677%. Its average detection accuracy reached 99.341%, the average confidence of the detected target was 91%, the detection and positioning speed reached 31.25 frames per second, and the positioning deviation was less than 0.93 mm, which conforms to the practical application requirements of the FPC assembly process.