Search results

This paper aims to study the working principle of the capacitive pressure sensor and explore the distribution of pressure acting on the surface of the capacitor. Herein, a kind of high sensitivity capacitive pressure sensor was prepared by overlaying carbon fibers (CFs) on the surfaces of the thermoplastic elastomer (TPE), the TPE with high elasticity is a dielectric elastomer for the sensor and the CFs with excellent electrical conductivity were designed as the conductor.

Due to the excellent mechanical properties and electrical conductivity of CFs, it was designed as the conductor layer for the TPE/CFs capacitive pressure sensor via laminating CFs on the surfaces of the columnar TPE. Then, a ‘#' type structure of the capacitive pressure sensor was designed and fabricated.

The ‘#' type of capacitive pressure sensor of TPE/CFs composite was obtained in high sensitivity with a gauge factor of 2.77. Furthermore, the change of gauge factor values of the sensor under 10 per cent of applied strains was repeated for 1,000 cycles, indicating its outstanding sensing stability. Moreover, the ‘#' type capacitive pressure sensor of TPE/CFs was consisted of several capacitor arrays via laminating CFs, which could detect the distribution of pressure.

The TPE/CFs capacitive pressure sensor was easily fabricated with high sensitivity and quick responsiveness, which is desirably applied in wearable electronics, robots, medical devices, etc.

The outcome of this study will help to fabricate capacitive pressure sensors with high sensitivity and outstanding sensing stability.

Fire smoke detection in petrochemical plant can prevent fire and ensure production safety and life safety. The purpose of this paper is to solve the problem of missed detection and false detection in flame smoke detection under complex factory background.

This paper presents a flame smoke detection algorithm based on YOLOv5. The target regression loss function (CIoU) is used to improve the missed detection and false detection in target detection and improve the model detection performance. The improved activation function avoids gradient disappearance to maintain high real-time performance of the algorithm. Data enhancement technology is used to enhance the ability of the network to extract features and improve the accuracy of the model for small target detection.

Based on the actual situation of flame smoke, the loss function and activation function of YOLOv5 model are improved. Based on the improved YOLOv5 model, a flame smoke detection algorithm with generalization performance is established. The improved model is compared with SSD and YOLOv4-tiny. The accuracy of the improved YOLOv5 model can reach 99.5%, which achieves a more accurate detection effect on flame smoke. The improved network model is superior to the existing methods in running time and accuracy.

Aiming at the actual particularity of flame smoke detection, an improved flame smoke detection network model based on YOLOv5 is established. The purpose of optimizing the model is achieved by improving the loss function, and the activation function with stronger nonlinear ability is combined to avoid over-fitting of the network. This method is helpful to improve the problems of missed detection and false detection in flame smoke detection and can be further extended to pedestrian target detection and vehicle running recognition.

Virtual maintenance simulation is of great importance to help designers find and avoid design problems. During its simulation phase, besides the high precision requirement, collision detection must be suitable for all irregular objects in a virtual maintenance environment. Therefore, in this paper, a collision detection approach is proposed based on encapsulation for irregular objects in the virtual maintenance environment.

First, virtual maintenance simulation characteristics and several commonly used bounding boxes methods are analyzed, which motivates the application of encapsulation theory. Based on these, three different encapsulation methods are oriented to the needs of simulation, including encapsulation of rigid maintenance objects, flexible maintenance objects and maintenance personnel. In addition, to detecting collisions accurately, this paper divides the detection process into two stages. That is, in the first stage, a rough detection is carried out and then a tiny slice space is constructed to generate corresponding capsule groups, which will be redetected in the secondary stage. At last, several case studies are applied to illustrate the performance of the methodology.

The automatic construction algorithm for bounding boxes can be adapted to all forms of objects. The number of detection primitives are greatly reduced. It introduces the reachable space of the human body in maintainability as the collision search area.

The advantages of virtual maintenance simulation could also be advantageous in the industry with further studies. The paper believes this study is of particular interest to the readers of your journal.

This paper aims to present a novel embedded‐internet robot system based on an internet robot agent and the brain‐computer interface (BCI) scheme.

A highly flexible and well‐integrated embedded ethernet robot (eRobot) was designed with enhanced mobility. In the eRobot, a circuit core module called a tiny network bridge (TNB) is designed to reduce robotic system cost and increase its mobility and developmental flexibility. The TNB enables users to control eRobot motion via embedded ethernet technology. Through electroencephalogram (EEG) feedback training, the command translation unit (CTU) and alertness level detection unit (ADU) allow the eRobot to perform specific motions (for example, lying down or standing up) to reflect alertness levels of the user, and move forward, turn left or right following the user's command.

After a short training period, subjects could achieve at least 70 percent accuracy in the CTU game testing. And the error rate of ADU, estimated from the results of classifying 496 labeled EEG epochs, was approximately 10.7 percent. Combining an encoding procedure, the commands issued from the CTU could prevent the robot from performing undesired actions.

The eRobot could reflect some physiological human states and be controlled by users with our economical design and only two bipolar EEG channels adopted. Thus, users could make the EEG‐based eRobot agent his or her representative. Based on the proposed EEG‐based eRobot system, a robot with increased sophistication will be developed in the future for use by disabled patients.

The purpose of this study is to design, program and implement an intelligent robot for shelf-reading. an essential task in library maintenance is shelf-reading, which refers to the process of checking the disciplines of books based on their call numbers to ensure that they are correctly shelved. Shelf-reading is a routine yet challenging task for librarians, as it involves controlling call numbers on the scale of thousands of books promptly.

Leveraging the strength of autonomous robots in handling repetitive tasks, this paper introduces a novel vision-based shelf-reader robot, called \emph{Pars} and demonstrate its effectiveness in accomplishing shelf-reading tasks. Also, this paper proposes a novel supervised approach to power the vision system of \emph{Pars}, allowing it to handle motion blur on images captured while it moves. An approach based on Faster R-CNN is also incorporated into the vision system, allowing the robot to efficiently detect the region of interest for retrieving a book’s information.

This paper evaluated the robot’s performance in a library with $120,000 books and discovered problems such as missing and misplaced books. Besides, this paper introduces a new challenging data set of blurred barcodes free publicly available for similar research studies.

The robot is equipped with six parallel cameras, which enable it to check books and decide moving paths. Through its vision-based system, it is also capable of routing and tracking paths between bookcases in a library and it can also turn around bends. Moreover, \emph{Pars} addresses the blurred barcodes, which may appear because of its motion.

The purpose of this paper is to describe recent research into biomimetic imaging and vision systems.

Following an introduction, this paper discusses a range of biomimetic imaging and vision system research activities and their potential applications. Brief conclusions are drawn.

This shows that biomimetic design concepts, many based on insect vision, are being applied widely to prototype imaging systems. These exhibit features such as wide fields of view, hyperacuity and infra‐red detection and offer prospects to enhance the capabilities of such systems in a wide range of applications.

This paper provides details of recent biomimetic imaging research, which has potential in a range of robotic and other applications.

This paper aims to develop a new robotic ultrasound system for spine imaging with more anthropomorphic scanning manipulation in comparison with previously reported techniques.

The system evaluates the imaging quality of ultrasound (US) B-scans by detecting vertebral landmarks and groups the images with relatively low quality into several sub-optimal types. By imitating the scanning skills of sonographers, the authors defined a set of adjustment strategies for certain sub-optimal types. In this way, the robot can recollect the US images with high quality by adaptively adjusting the pose of the probe like a sonographer.

The results from phantom experiments and in vivo experiments showed that the proposed method could improve the quality of B-scans during the scanning. The 3 D US volume reconstruction has also verified the feasibility of the proposed method.

This paper demonstrates how to adapt a robotic spinal ultrasound scanning using a preliminary anthropomorphic approach.

This paper aims to improve the scene sense of a virtual scene, the welding model of a virtual reality system of riser automatic equipment was constructed using Unity3D and UG software, which mainly included a welding car, welding guide rail, welding power supply, virtual camera and other equipment and the model was rendered.

The human-computer interaction page and simulation test of the system was produced using the user interface GUI system for creating a human-computer interaction scene. The operator could capture the welding status of the physical equipment accurately and in real-time so the virtual reality technology was very suitable for the remote monitoring operation integrated with the welding system.

Human-computer interaction design and collision detection were realized. In addition, the system simulation experiment was accomplished. With the continuous improvement and development of virtual reality technology real-time virtual simulation and monitoring, technology will become the main development trend.

Based on virtual reality, the monitoring system can capture the operation status of physical welding equipment in real-time and accurately, which is very suitable for remote monitoring operation integrated with the welding system and also conducive to improving the monitoring level of the welding process.

This technology is time-saving and money-saving, for the operators do not have to be in a real welding environment and therefore they can get away from dangerous places. Consequently, it can avoid unnecessary injuries and problems.

This technology can replace people to enter the dangerous and extreme environment to carry out welding operation, so it becomes the most effective means of nuclear power plant maintenance, space structure construction and marine engineering construction. In addition, it is time-saving and money-saving.

With the rapid development of virtual reality technology in recent years, it is a new research direction to apply virtual reality technology to the remote welding operation. This technology is different from the traditional way of welding for the operators can stay away from the welding scene especially some dangerous places.

The purpose of this paper is to propose a multi-feature, multi-metric and multi-loop tightly coupled LiDAR-visual-inertial odometry, M³LVI, for high-accuracy and robust state estimation and mapping.

M³LVI is built atop a factor graph and composed of two subsystems, a LiDAR-inertial system (LIS) and a visual-inertial system (VIS). LIS implements multi-feature extraction on point cloud, and then multi-metric transformation estimation is implemented to realize LiDAR odometry. LiDAR-enhanced images and IMU pre-integration have been used in VIS to realize visual odometry, providing a reliable initial guess for LIS matching module. Location recognition is performed by a dual loop module combined with Bag of Words and LiDAR-Iris to correct accumulated drift. M³LVI also functions properly when one of the subsystems failed, which greatly increases the robustness in degraded environments.

Quantitative experiments were conducted on the KITTI data set and the campus data set to evaluate the M³LVI. The experimental results show the algorithm has higher pose estimation accuracy than existing methods.

The proposed method can greatly improve the positioning and mapping accuracy of AGV, and has an important impact on AGV material distribution, which is one of the most important applications of industrial robots.

M³LVI divides the original point cloud into six types, and uses multi-metric transformation estimation to estimate the state of robot and adopts factor graph optimization model to optimize the state estimation, which improves the accuracy of pose estimation. When one subsystem fails, the other system can complete the positioning work independently, which greatly increases the robustness in degraded environments.

The study proposed a human–robot interaction (HRI) framework to enable operators to communicate remotely with robots in a simple and intuitive way. The study focused on the situation when operators with no programming skills have to accomplish teleoperated tasks dealing with randomly localized different-sized objects in an unstructured environment. The purpose of this study is to reduce stress on operators, increase accuracy and reduce the time of task accomplishment. The special application of the proposed system is in the radioactive isotope production factories. The following approach combined the reactivity of the operator’s direct control with the powerful tools of vision-based object classification and localization.

Perceptive real-time gesture control predicated on a Kinect sensor is formulated by information fusion between human intuitiveness and an augmented reality-based vision algorithm. Objects are localized using a developed feature-based vision algorithm, where the homography is estimated and Perspective-n-Point problem is solved. The 3D object position and orientation are stored in the robot end-effector memory for the last mission adjusting and waiting for a gesture control signal to autonomously pick/place an object. Object classification process is done using a one-shot Siamese neural network (NN) to train a proposed deep NN; other well-known models are also used in a comparison. The system was contextualized in one of the nuclear industry applications: radioactive isotope production and its validation were performed through a user study where 10 participants of different backgrounds are involved.

The system was contextualized in one of the nuclear industry applications: radioactive isotope production and its validation were performed through a user study where 10 participants of different backgrounds are involved. The results revealed the effectiveness of the proposed teleoperation system and demonstrate its potential for use by robotics non-experienced users to effectively accomplish remote robot tasks.

The proposed system reduces risk and increases level of safety when applied in hazardous environment such as the nuclear one.

The contribution and uniqueness of the presented study are represented in the development of a well-integrated HRI system that can tackle the four aforementioned circumstances in an effective and user-friendly way. High operator–robot reactivity is kept by using the direct control method, while a lot of cognitive stress is removed using elective/flapped autonomous mode to manipulate randomly localized different configuration objects. This necessitates building an effective deep learning algorithm (in comparison to well-known methods) to recognize objects in different conditions: illumination levels, shadows and different postures.