Publications

Adaptive Neural Fuzzy Inference System Disturbance Observer-Based Control for Reaching Movement of Musculoskeletal Arm Model

Traditional disturbance observer techniques have limitations for multi-input multi-output-coupled systems, time-varying systems with large parameters, and complex systems which are difficult to obtain accurate model, such as the human musculoskeletal arm system. The neural network has advantages of generalized approximation ability, learning ability, and self-adaptive ability. Therefore, this paper develops an adaptive neural fuzzy inference system disturbance observer-based control to achieve the point-to-point control and the path tracking control of the end point of the musculoskeletal arm model. The adaptivity is improved by adjusting the learning algorithm of neural network parameters and the network structure in real time. The uncertainty of the inverse model of the system is solved by constructing a pseudo-system. The adaptive neural fuzzy inference system is used to identify the inverse model of the pseudo-system and to design a compound controller based on feedback control method. The stability is analyzed by Lyapunov function in detail. Furthermore, internal disturbances are suppressed by the learning algorithm of the adaptive neural fuzzy inference system network while external disturbances may be estimated by the multi-input multi-output disturbance observer at the same time. Simulations are performed to verify the point-to-point control and the path tracking control. Results demonstrate that both of the adaptivity and the accuracy are enhanced so that the system can achieve accurate tracking control of any arbitrary trajectory.

Development of an Integrated Haptic Sensor System for Multimodal Human–Computer Interaction Using Ultrasonic Array and Cable Robot

This paper presents the design and development of a novel haptic sensor system. It integrates cable-driven force and ultrasonic tactile feedback, which can produce multimodal haptic stimuli. The sensing element includes a Leapmotion, an ultrasonic transducer array, tension sensors, and rotary encoders, which are used to capture hand posture, project tactile points, measure cable force and length, respectively. Firstly, a 6-DOF cable-driven force feedback apparatus based on parallel mechanism is designed and ultrasonic phased array is combined to form a multimodal haptic feedback system. Secondly, a multimodal haptic fusion method for cable-driven force and ultrasonic tactile is firstly proposed to invoke realistic compound haptic sensations. To enhance the rendering effects of each subsystem, admittance control is developed for a cable robot, and a new perceived magnitude model is established for ultrasound tactile rendering. A psychophysical experiment is conducted to study the perceived characteristics of multimodal haptic stimuli. To verify the proposed system, a series of experiments were carried out, whose results indicated that the system performs well at multi-property haptic rendering and confirm the accuracy and sensitive advantage of our system in virtual reality applications. The results of our study indicate that this device has great application potential in human-computer interaction.

A Graph Embedding Method Based on Sparse Representation for Wireless Sensor Network Localization

In accordance with the problem that the traditional trilateral or multilateral estimation localization method is highly dependent on the proportion of beacon nodes and the measurement accuracy, an algorithm based on kernel sparse preserve projection (KSPP) is proposed in this dissertation. The Gaussian kernel function is used to evaluate the similarity between nodes, and the location of the unknown nodes will be commonly decided by all the nodes within communication radius through selection of sparse preserve projection self-adaptation and maintaining of the topological structure between adjacent nodes. Therefore, the algorithm can effectively solve the nonlinear problem while ranging, and it becomes less affected by the measuring error and beacon nodes quantity.

Development and Evaluation of Refreshable Braille Display and Active Touch-Reading System for Digital Reading of the Visually Impaired

The traditional way of reading through Braille books is constraining the reading experience of blind or visually impaired (BVI) in the digital age. In order to improve the reading convenience of BVI, this paper proposes a low-cost and refreshable Braille display device, and solves the problems of high energy consumption and low latching force existing in existing devices. Further, the Braille display device was combined with the 3D Systems Touch device to develop an active Braille touch-reading system for digital reading of BVI with the help of the CHAI3D virtual environment. Firstly, according to the actual needs of BVI to touch and read the Braille dots, this paper utilizes the beam structure to provide a full latching function for the raised Braille dot without energy consumption. Through theoretical derivation and finite element analysis, the performance of the Braille dot actuator is optimized to provide sufficient feedback force and latching force for finger's touch-reading. Then, this paper designs a virtual Braille interactive environment based on the CHAI3D, and combines the sense of touch with audio to effectively improve the recognition accuracy and reading efficiency of BVI for Braille through the multi-modal presentation of Braille information. The performance test results of the device show that the average lifting force of the Braille dot actuator is 101.67 mN, the latching force is over 5 N, and the average refresh frequency is 17.1 Hz, which meets the touch-reading needs of BVI. User experiments show that the average accuracy rate of BVI subjects in identifying digitized Braille is 95.5%, and subjects have a high subjective evaluation of the system.

A highly adhesive flexible strain sensor based on ultra-violet adhesive filled by graphene and carbon black for wearable monitoring

A vibro-tactile system for image contour display

This paper presents the design and testing of an image contour display system with vibrotactile array. The tactile image display system is attached on the user's back. It produces non-visual image and permits subjects to determine the position, size, shape of visible objects through vibration stimulus. The system comprises three parts: 1) a USB camera; 2) 48 (6×8) vibrating motors; 3) ARM micro-controlled system. Image is captured with the camera and the 2D contour is extracted and transformed into vibrotactile stimulus with a "contour following" (time-spatial dynamic coding) pattern. With this system subjects could identify the shape of object without special training; meanwhile fewer vibrotactile actuators are adopted. Preliminary experiments were carried out and the results demonstrated that the prototype was satisfactory and efficient for the visually impaired in seeing aid and environment perception.

Exploring the interaction strategy and release timing for robot-to-human handovers with manually guided motion

Haptic Texture Rendering Using Single Texture Image

This paper describes a method of generation of forces from a two-dimensional static image to make texture tangible using haptic devices. The proposed technique consists in creating a height map computed thanks to Tsai & Shah algorithm - an algorithm in shape-from-shading. This height map is then used to generate the virtual surface, and forces fields creating haptic texture are calculated by a new haptic texture rendering model.

KAN-GCNN: EEG-Based Emotion Recognition with a Kolmogorov-Arnold Network-Enhanced Graph Convolutional Neural Network

Design and Calibration of a Novel Multi-Axis Sensor for Measuring the Wheel-Terrain Interaction Forces of Robotic Vehicles

Channel-Equalization-HAR: A Light-weight Convolutional Neural Network for Wearable Sensor Based Human Activity Recognition

Recently, human activity recognition (HAR) that uses wearable sensors has become a research hotspot because its wide applications in real-world scenarios. Essentially, HAR can be treated as multi-channel time series classification problem, where different channels may come from heterogeneous sensor modalities. Deep learning, especially convolutional neural networks (CNNs) have made breakthroughs in ubiquitous HAR scenario. Various normalization methods enable layers of networks to learn more independently by normalizing hybrid sensor features. However, normalization tends to produce a channel collapse phenomenon, where many channels generates tiny values. Most channels are inhibited and contribute very little to output. As a result, the network has to rely on only a few valid channels, which inevitably impair the generality ability. In this paper, we provide an alternative called Channel Equalization to reactivate these inhibited channels by performing whitening or decorrelation operation, which compels all channels to contribute more or less to feature representation. Extensive experiments are conducted on several public HAR benchmarks, which indicate that the proposed method significantly surpasses recent SOTA at negligible computational overhead. To our knowledge, the Channel Equalization is for the first time to be applied in multimodal HAR scenario. Finally, the actual operation is evaluated on an embedded platform.

Vision-based Autonomous Detecting and Grasping Framework for the Fully-actuated Aerial Manipulator

The Aerial Manipulator (AM) combines the flexibility of aerial platforms with the manipulative capability of manipulators. Autonomous grasping of the AM poses challenges due to its complex kinematics/dynamics and target object pose acquisition. This paper introduces a fully-actuated AM which consists of a fully-actuated hexarotor and a 3-DoF manipulator. The fully-actuated aerial platform provides a more stable view for the camera during the AM motion. The feedback linearization controller is used in the aerial platform to ensure the stability of the AM during the motion of the manipulator. The YOLO v5 object detector combines the Oriented Bounding Box (OBB) to form a rotating object detector which can identify the target object and obtain its tilt angle. Combined with the depth camera, the position of the target object in three-dimensional (3D) space can be obtained. Within the working space, the manipulator performs autonomous planning and grasping according to the position and tilt angle of the target. Experimental demonstrates the performance of the proposed AM system.

Seismic behavior and numerical simulation of damaged beam-column joints retrofitted with viscoelastic steel-enveloped elements

Design and evaluation of a small-scale multi-drum magnetorheological brake

Magnetorheological fluid, whose rheological properties can be continuously and reversely changed, is a new-type smart material. Based on magnetorheological fluid, magnetorheological brake is a potential actuation method in haptics due to its desirable features, such as inherent passiveness and high compactness. Most of the existing magnetorheological brakes are powerful enough, but they are too bulky and heavy. If they were smaller and lighter, they would be more favourable for haptics. In this article, a small-scale yet powerful magnetorheological brake was designed, modelled and evaluated. We adopted a novel multi-drum architecture to activate more shearing areas within a limited volume. To obtain an ideal sealing effect and reduce the off-state friction, the ferro-fluidic sealing technique was used. The ferro-fluidic sealing assemblies can be assembled from both sides of the shaft. The current–torque model of this brake was derived to predict the torque output based on the current input. The optimal design has the diameter of 28 mm and the width of 23.5 mm. It can provide the maximum and minimum torque of 403 and 4 N mm, respectively, giving the torque–volume ratio of 27.864 kN/m 2 and the dynamic range of about 40 dB with the 54 ms time constant.

LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

Robust watermarking requires finding invariant features under multiple attacks to ensure correct extraction. Deep learning has extremely powerful in extracting features, and watermarking algorithms based on deep learning have attracted widespread attention. Most existing methods use small kernel convolution to extract image features and embed the watermarking. However, the effective perception fields for small kernel convolution are extremely confined, so the pixels that each watermarking can affect are restricted, thus limiting the performance of the watermarking. To address these problems, we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss functions. It uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a high-dimensional space by convolution to achieve adaptability in the channel dimension. Subsequently, the modification of the embedded watermarking on the cover image is extended to more pixels. Because the magnitude and convergence rates of each loss function are different, an adaptive loss weight assignment strategy is proposed to make the weights participate in the network training together and adjust the weight dynamically. Further, a high-frequency wavelet loss is proposed, by which the watermarking is restricted to only the low-frequency wavelet sub-bands, thereby enhancing the robustness of watermarking against image compression. The experimental results show that the peak signal-to-noise ratio (PSNR) of the encoded image reaches 40.12, the structural similarity (SSIM) reaches 0.9721, and the watermarking has good robustness against various types of noise.

Sliding Mode Impedance Control for Dual Hand Master Single Slave Teleoperation Systems

For the purpose of avoiding injury and realizing precise operations, the multilateral teleoperation system is the most efficient way to transport trace toxic or radioactive substances, to perform minimally invasive surgery, etc. It is essential to enhance the transparency of a multilateral teleoperation system including multiple masters and the single slave manipulator. However, there are few researchers focus on the allocation of the contact force of the single slave manipulator to different master manipulators. In this paper, we firstly introduce the concept of force translation for teleoperation systems consisting of dual hand master (left and right hands) manipulators and a single slave manipulator. Force translation reflects how the impedance on the single slave side is translated or allocated to contact forces on different master sides. To maintain the stability of the system and to improve transparency, we elucidate the mechanism of the force translation and analyze the relation among masters and the slave. Furthermore, the force translation mechanism is analyzed through numerical simulations and CHAI 3D virtual physical simulations. It is used to propose a multilateral impedance control, and the Lyapunov function is used to analyze the system stability. The results of numerical simulations and real robot experiments verify the effectiveness of the proposed control methods based on the proposed force translation mechanism.

Brain-Computer Interface Using Brain Power Map and Cognition Detection Network During Flight

This article presents a new aviation brain-computer interface, which includes the construction of a color brain power map and a cognitive detection network. The developed network, Bpmnet, can effectively detect the cognitive state of the brain. To improve the effectiveness of model parameter optimization algorithms, momentum and batch normalization are proposed during Bayesian posterior parameter inference. Bpmnet reduces the risk of model overfitting and increases the uncertainty of outlier prediction. Experimental results demonstrate that our approach significantly outperforms state-of-the-art techniques.

Adversarial Subgraph Contrastive Learning for Predicting Grasp Stability of Robotic Hands with Multimodal Signals