About
428
Publications
54,661
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,806
Citations
Introduction
Skills and Expertise
Publications
Publications (428)
The Iterative Closest Point (ICP) algorithm is a crucial component of LiDAR-based SLAM algorithms. However, its performance can be negatively affected in unstructured environments that lack features and geometric structures, leading to low accuracy and poor robustness in localization and mapping. It is known that degeneracy caused by the lack of ge...
To improve human–machine interactions, many studies have replicated the human motor nervous system to control lower limb exoskeletons. However, this approach is hindered by its intricacy and the disparities between human and machine capabilities, leading to suboptimal adaptability and constrained practicality. This article presents a gait-generatio...
In this paper, a compact linkage mechanism with high mechanical advantage and stroke is designed. The mechanism converts a small input force into a large output force using a toggle mechanism. Its feasibility for application in large gripping force manipulators has been verified. In the paper, the kinematic and static analyses of the mechanism are...
Lower-limb exoskeletons have become increasingly popular in rehabilitation to help patients with disabilities regain mobility and independence. Brain–computer interface (BCI) offers a natural control method for these exoskeletons, allowing users to operate them through their electroencephalogram (EEG) signals. However, the limited EEG decoding perf...
Inspired by the kinesiology of human bionic joints, a transfemoral prosthetic mechanism based on a functional structure of parallel mechanism is developed for the transfemoral amputees. The walking interactive simulation is implemented based on human- prosthesis modeling to verify the kinematics of designed prosthetic mechanism, as well as explore...
Due to saturated regions of inputting low dynamic range (LDR) images and large intensity changes among the LDR images caused by different exposures, it is challenging to produce an information enriched panoramic LDR image without visual artifacts for a high dynamic range (HDR) scene through stitching multiple geometrically synchronized LDR images w...
The decoding of electroencephalogram (EEG) signals, especially motion-related cortical potentials (MRCP), is vital for the early detection of motor intent before movement execution. To enhance the decoding accuracy of MRCP and promote the application of early motion intention in active rehabilitation training, we propose a method for decoding MRCP...
Elevation-azimuth photoelectric survey telescopes working under long exposure station is very important for observing weak targets in space. The motion characteristics analyses including position and velocity of rotating targets show that the image stabilization system (IMSS) needs to have a self-locking capability, low temperature rise, anti-inter...
Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel physics (geometry)-driven deep learning frameworks for these two tasks by assuming that 3D scenes are constituted with piece-wise pla...
The distribution shift of electroencephalography (EEG) data causes poor generalization of braincomputer interfaces (BCIs) in unseen domains. Some methods try to tackle this challenge by collecting a portion of user data for calibration. However, it is time-consuming, mentally fatiguing, and user-unfriendly. To achieve zerocalibration BCIs, most stu...
We previously developed a powered hip prosthetic mechanism with kinematic functions of hip flexion–extension and abduction–adduction, and its theoretical and simulation-based kinematics were verified. Because internal–external hip rotation has a positive effect on the movements of human lower limbs according to medical research, we developed a nove...
Almost all living organisms exhibit autonomic oscillatory activities, which are primarily generated by the rhythmic activities of their neural systems. Several nonlinear oscillator models have been proposed to elucidate these neural behaviors and subsequently applied to the domain of robot control. However, the oscillation patterns generated by the...
Loop closure detection (LCD) plays a crucial role in simultaneous localization and mapping (SLAM) systems to eliminate accumulated odometry drifts as the map is built, and using multi-modal information can improve the accuracy and robustness of this system compared to single sensor. However, traditional fusion methods often require sophisticated sp...
In recent years, the combination of neural implicit representations with Simultaneous Localization and Mapping (SLAM) has shown promising advancements. Nevertheless, the existing methods suffer from drawbacks including poor localization accuracy and the absence of loop closure modules, resulting in suboptimal localization accuracy and issues such a...
Although there are many wearable sensors that make the acquisition of multi-modality data easier, effective feature extraction and fusion of the data is still challenging for lower limb locomotion mode recognition. In this article, a novel neural network is proposed for accurate prediction of five common lower limb locomotion modes including level...
Over the past few years, self-supervised monocular depth estimation has received widespread attention. Most efforts focus on designing different types of network architectures and loss functions or handling edge cases, for example, occlusion and dynamic objects. In this work, we take another path and propose a novel conditional diffusion-based gene...
The existing surface electromyography-based pattern recognition system (sEMG-PRS) exhibits limited generalizability in practical applications. In this paper, we propose a stacked weighted random forest (SWRF) algorithm to enhance the long-term usability and user adaptability of sEMG-PRS. First, the weighted random forest (WRF) is proposed to addres...
Efficiently grasping and releasing objects using robotic grippers is an essential step in robotic assembly. This paper presents a low-cost four-finger adaptive gripper capable of performing stable and reliable grasping operations on irregular-shaped flat objects. Unlike other grasping systems in the fixture-to-fixture robotic assembly, the assembly...
Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervision signal have emerged as the most promising paradigms. In this work, we propose two novel ideas to improve self-supervised monocular depth estimat...
Purpose:
This study aimed to evaluate the efficacy of repetitive transcranial magnetic stimulation (rTMS) in treating lower limb motor dysfunction after stroke and explore the optimal stimulation parameters.
Methods:
PubMed, Embase, Cochrane Library, and other relevant databases were systematically queried for randomised controlled trials (RCTs)...
Compliant actuators are suitable for reliable human-robot interaction applications due to their inherent flexibility and safety. However, a limitation of this type of actuators is that nonlinear hysteresis exists especially for those actuators with nonlinear stiffness, which makes accurate system modeling difficult and further degrades force/torque...
Adaptive grippers are widely used in industrial automation, manufacturing, and other applications where objects being handled are often irregular in shape or size. Cost and control complexity are the two critical considerations in the design process of an adaptive gripper. To address these problems, a novel single-input-three-output (SITO) flexible...
Objective
Post-stroke cognitive impairment (PSCI) substantially affects patients’ quality of life. This study explored the therapeutic efficacy of intermittent theta burst stimulation (iTBS) combined with cognitive training for PSCI.
Design
The experimental group received iTBS and cognitive training, whereas the control group only received cogniti...
Differently exposed low dynamic range (LDR) images are often captured sequentially using a smart phone or a digital camera with movements. Optical flow thus plays an important role in ghost removal for high dynamic range (HDR) imaging. The optical flow estimation is based on the theory of photometric consistency, which assumes that the correspondin...
Inspired by the bionic characteristics of ankle and calf skeletal muscles, a novel ankle-foot prosthesis (AFP) with variable stiffness mechanisms (VSMs) is proposed to assist transtibial amputees to restore ankle plantarflexion-dorsiflexion. The prosthesis is designed in the form of a spring-loaded three-loop linkage for function of continuous ener...
At present, the small and medium-sized enterprises have a large number of irregular-shaped workpiece grasping operations, which require a vision system to cooperate with a robotic gripper. However, the existing visual grasping systems are difficult to be widely deployed due to cost or accuracy issues. To solve this problem, this paper proposes a vi...
Deep learning methods have been widely explored in motor imagery (MI)-based brain computer interface (BCI) systems to decode electroencephalography (EEG) signals. However, most studies fail to fully explore temporal dependencies among MI-related patterns generated in different stages during MI tasks, resulting in limited MI-EEG decoding performance...
Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation. A major challenge is that the model has no access to the future and must rely solely on the history, i.e., the segmentation mask is predicted f...
Background:
The efficacy of robotic-assisted gait training (RAGT) should be considered versatilely; among which, gait assessment is one of the most important measures; observational gait assessment is the most commonly used method in clinical practice, but it has certain limitations due to the deviation of subjectivity; instrumental assessments su...
Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint and descriptor extraction. However, the conventional convolution operations do not provide the geometric invariance required for the descriptor. To address this issu...
With the improvement of sensor technology and significant algorithmic advances, the accuracy of remote heart rate monitoring technology has been significantly improved. Despite of the significant algorithmic advances, the performance of rPPG algorithm can degrade in the long-term, high-intensity continuous work occurred in evenings or insufficient...
Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervisory signal have emerged as the most promising paradigms. In this work, we propose two novel ideas to improve self-supervised monocular depth estimat...
This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and the local information is critical for accurate depth estimation. Towards this end, we introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural networ...
Objective
In recent years, there have been significant developments in lower extremity robotic exoskeletons intended for gait rehabilitation. However, wearers may not be sufficiently motivated to participate in traditional rehabilitation robot training as the training pattern is usually predefined and rigid. Enabling wearers to actively control the...
Aiming at the manipulation problem of a hexapod robot with backbone joint, this paper studies the related problems of its two-arm mode. In this mode, the four middle and rear legs are used for support, and the backbone joint and two front legs are used for manipulation. For precise control in the actual scene, the composite motion of the backbone j...
Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint and descriptor extraction. However, the conventional convolution operations do not provide the geometric invariance required for the descriptor. To address this issu...
Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation. A major challenge is that the model has no access to the future and must rely solely on the history,
i.e
., the segmentation mask is predicte...
Monocular depth estimation has attracted extensive attention and made great progress in recent years. However, the performance still lags far behind LiDAR-based depth completion algorithms. This is because the completion algorithms not only utilize the RGB image, but also have the prior of sparse depth collected by LiDAR. To reduce this performance...
Human arm exhibits superb maneuverability in performing various tasks by utilizing its ability to actively adjust impedance parameters and interaction forces. Therefore, how to identify the joint stiffness of the arm during motion and transmit them to the exoskeleton robots is the key to achieving flexible rehabilitation motion. In this paper, we p...
This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and local information is critical for accurate depth estimation. To this end, we introduce an uncertainty rectified cross-distillation between the Transformer and convolutional neural network (CN...
The closed-loop constraint provided by loop closure detection plays an essential role in eliminating accumulated errors of simultaneous localization and mapping systems. BEVLCD+: A real-time and rotation-invariant loop closure detection method based on bird’s eye view (BEV) of point cloud has been proposed in this paper. Projecting 3D point cloud t...
The generative adversarial network (GAN) is successfully applied to study the perceptual single image super-resolution (SISR). However, since the GAN is data-driven, it has a fundamental limitation on restoring real high frequency information for an unknown instance (or image) during test. On the other hand, the conventional model-based methods hav...
The functional coupling of the cerebral cortex and muscle contraction indicates that electroencephalogram (EEG) and surface electromyogram (sEMG) signals are coherent. The objective of this study is to clearly describe the coupling relationship between EEG and sEMG through a variety of analysis methods. We collected the EEG and sEMG data of left- o...
Brain–machine interfaces (BMIs) have been applied as a pattern recognition system for neuromodulation and neurorehabilitation. Decoding brain signals (e.g., EEG) with high accuracy is a prerequisite to building a reliable and practical BMI. This study presents a deep convolutional neural network (CNN) for EEG-based motor decoding. Both upper-limb a...
Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence. Existing UVOS methods either lack robustness when there are visually similar surroundings (appearance-based) or suffer from deterioration in the quality of their predictions because of dynamic back...