arXiv subjects

Xu Liang

Publications and source records attributed to Xu Liang.

12 recordsLinked to original sources

arXiv2026

ExoTraj: A General Lower-limb Exoskeleton Assistance Policy for Complex Environments

Adaptive torque prediction in dynamic exoskeleton scenarios requires expensive motion capture systems, which are infeasible in complex outdoor environments. Trajectory prediction has emerged as one of the effective approaches to address such an issue. However, the core challenges of exoskeleton trajectory prediction are twofold: establishing the mapping from multi-modal features to trajectory information; constructing the mapping from trajectory to torque. For the former, most existing methods perform only single-step prediction and neglect inter-subject trajectory variability, thereby limiting the trajectory optimization space and prediction generalization. To address this, this paper proposes a fast flow matching method that enables accurate trajectory prediction and better generalization for real-time performance, where trajectory generation errors and encoded observations are used to guide the training direction. For the second challenge, due to the high dynamics of the human-robot system and the strong coupling between perception and control, simple control methods struggle to achieve efficient assistance based on the predicted trajectory. This paper utilizes model predictive control and designs a novel optimization objective to optimize torque, ensuring the exoskeleton achieves comfortable and robust assistance. By integrating the above two components, the unified policy, denoted as ExoTraj, is developed to enable adaptive assistance in complex outdoor scenarios without high data acquisition cost. Experimental results show that compared to traditional methods, ExoTraj reduces cross-subject prediction error by 14.0% during the online phase and maintains robustness against external noise. Relative to the zero torque condition, ExoTraj decreases metabolic rate by 11.5-24.4%, heart rate by 1.7-19.5%, and peak muscle activation levels by 10.9-41.3%, respectively.

cs.RO↗

arXiv2025

Dislocation Engineering: A New Key to Enhancing Ceramic Performances

Dislocations are line defects in crystalline solids and often exert a significant influence on the mechanical properties of metals. Recently, there has been a growing interest in using dislocations in ceramics to enhance materials performance. However, dislocation engineering has frequently been deemed uncommon in ceramics owing to the brittle nature of ceramics. Contradicting this conventional view, various approaches have been used to introduce dislocations into ceramic materials without crack formation, thereby paving the way for controlled ceramics performance. However, the influence of dislocations on functional properties is equally complicated owing to the intricate structure of ceramic materials. Furthermore, despite numerous experiments and simulations investigating dislocation-controlled properties in ceramics, comprehensive reviews summarizing the effects of dislocations on ceramics are still lacking. This review focuses on some representative dislocation-controlled properties of ceramic materials, including mechanical and some key functional properties, such as transport, ferroelectricity, thermal conductivity, and superconducting properties. A brief integration of dislocations in ceramic is anticipated to offer new insights for the advancement of dislocation engineering across various disciplines.

cond-mat.mtrl-sci↗

arXiv2025

Group Relative Policy Optimization for Image Captioning

Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for reinforcement learning optimization. However, the SCST algorithm has certain defects. SCST relies only on a single greedy decoding result as a baseline. If the model itself is not stable enough, the greedy decoding result may be relatively worst, which will lead to a high variance of advantage estimation, further leading to unstable policy updates. In addition, SCST only compares one sampling result with the greedy decoding result, and the generation diversity is limited, which may fall into a local optimum. In this paper, we propose using the latest Group Relative Policy Optimization (GRPO) reinforcement learning algorithm as an optimization solution for the second stage. GRPO generates multiple candidate captions for the input image and then continuously optimizes the model through intragroup comparison. By constraining the amplitude of policy updates and KL divergence, the stability of the model during training is greatly guaranteed. In addition, compared to SCST, which only samples one answer, GRPO samples and generates multiple answers. Multiple candidate answers in the group cover a wider solution space. Combined with KL divergence constraints, GRPO can improve diversity while ensuring model stability. The code for this article is available at https://github.com/liangxu-one/ms-models/tree/image_caption_grpo/research/arxiv_papers/Image_Caption_GRPO.

cs.CV↗

arXiv2024

A Weight-aware-based Multi-source Unsupervised Domain Adaptation Method for Human Motion Intention Recognition

Accurate recognition of human motion intention (HMI) is beneficial for exoskeleton robots to improve the wearing comfort level and achieve natural human-robot interaction. A classifier trained on labeled source subjects (domains) performs poorly on unlabeled target subject since the difference in individual motor characteristics. The unsupervised domain adaptation (UDA) method has become an effective way to this problem. However, the labeled data are collected from multiple source subjects that might be different not only from the target subject but also from each other. The current UDA methods for HMI recognition ignore the difference between each source subject, which reduces the classification accuracy. Therefore, this paper considers the differences between source subjects and develops a novel theory and algorithm for UDA to recognize HMI, where the margin disparity discrepancy (MDD) is extended to multi-source UDA theory and a novel weight-aware-based multi-source UDA algorithm (WMDD) is proposed. The source domain weight, which can be adjusted adaptively by the MDD between each source subject and target subject, is incorporated into UDA to measure the differences between source subjects. The developed multi-source UDA theory is theoretical and the generalization error on target subject is guaranteed. The theory can be transformed into an optimization problem for UDA, successfully bridging the gap between theory and algorithm. Moreover, a lightweight network is employed to guarantee the real-time of classification and the adversarial learning between feature generator and ensemble classifiers is utilized to further improve the generalization ability. The extensive experiments verify theoretical analysis and show that WMDD outperforms previous UDA methods on HMI recognition tasks.

eess.SP↗

arXiv2021

BPFNet: A Unified Framework for Bimodal Palmprint Alignment and Fusion

Bimodal palmprint recognition leverages palmprint and palm vein images simultaneously,which achieves high accuracy by multi-model information fusion and has strong anti-falsification property. In the recognition pipeline, the detection of palm and the alignment of region-of-interest (ROI) are two crucial steps for accurate matching. Most existing methods localize palm ROI by keypoint detection algorithms, however the intrinsic difficulties of keypoint detection tasks make the results unsatisfactory. Besides, the ROI alignment and fusion algorithms at image-level are not fully investigaged.To bridge the gap, in this paper, we propose Bimodal Palmprint Fusion Network (BPFNet) which focuses on ROI localization, alignment and bimodal image fusion.BPFNet is an end-to-end framework containing two subnets: The detection network directly regresses the palmprint ROIs based on bounding box prediction and conducts alignment by translation estimation.In the downstream,the bimodal fusion network implements bimodal ROI image fusion leveraging a novel proposed cross-modal selection scheme. To show the effectiveness of BPFNet,we carry out experiments on the large-scale touchless palmprint datasets CUHKSZ-v1 and TongJi and the proposed method achieves state-of-the-art performances.

cs.CV↗

arXiv2021

Touchless Palmprint Recognition based on 3D Gabor Template and Block Feature Refinement

With the growing demand for hand hygiene and convenience of use, palmprint recognition with touchless manner made a great development recently, providing an effective solution for person identification. Despite many efforts that have been devoted to this area, it is still uncertain about the discriminative ability of the contactless palmprint, especially for large-scale datasets. To tackle the problem, in this paper, we build a large-scale touchless palmprint dataset containing 2334 palms from 1167 individuals. To our best knowledge, it is the largest contactless palmprint image benchmark ever collected with regard to the number of individuals and palms. Besides, we propose a novel deep learning framework for touchless palmprint recognition named 3DCPN (3D Convolution Palmprint recognition Network) which leverages 3D convolution to dynamically integrate multiple Gabor features. In 3DCPN, a novel variant of Gabor filter is embedded into the first layer for enhancement of curve feature extraction. With a well-designed ensemble scheme,low-level 3D features are then convolved to extract high-level features. Finally on the top, we set a region-based loss function to strengthen the discriminative ability of both global and local descriptors. To demonstrate the superiority of our method, extensive experiments are conducted on our dataset and other popular databases TongJi and IITD, where the results show the proposed 3DCPN achieves state-of-the-art or comparable performances.

cs.CV↗

arXiv2020

Selection of multiple donor gauges via Graphical Lasso for estimation of daily streamflow time series

A fundamental challenge in estimations of daily streamflow time series at sites with incomplete records is how to effectively and efficiently select reference or donor gauges from an existing gauge network to infer the missing data. While research on estimating missing streamflow time series is not new, the existing approaches either use a single reference streamflow gauge or employ a set of "ad-hoc" reference gauges, leaving a systematic selection of reference gauges as a long-standing open question. In this work, a novel method is introduced that facilitates systematical selection of multiple reference gauges from any given streamflow network. The idea is to mathematically characterize the network-wise correlation structure of a streamflow network via graphical Markov modeling, and further transforms a dense network into a sparsely connected one. The resulted underlying sparse graph from the graphical model encodes conditional independence conditions among all reference gauges from the streamflow network, allowing determination of an optimum subset of the donor gauges. The sparsity is discovered by using the Graphical Lasso algorithm with an L1-norm regularization parameter and a thresholding parameter. These two parameters are determined by a multi-objective optimization process. Furthermore, the graphical modeling approach is employed to solve another open problem in gauge removal planning decision (e.g., due to operation budget constraints): which gauges to remove would statistically guarantee the least loss of information by estimations from the remaining gauges? Our graphical model-based method is demonstrated with daily streamflow data from a network of 34 gauges over the Ohio River basin.

stat.AP↗

arXiv2020

A calibration framework for high-resolution hydrological models using a multiresolution and heterogeneous strategy

Increasing spatial and temporal resolution of numerical models continues to propel progress in hydrological sciences, but, at the same time, it has strained the ability of modern automatic calibration methods to produce realistic model parameter combinations for these models. This paper presents a new reliable and fast automatic calibration framework to address this issue. In essence, the proposed framework, adopting a divide and conquer strategy, first partitions the parameters into groups of different resolutions based on their sensitivity or importance, in which the most sensitive parameters are prioritized with highest resolution in parameter search space, while the least sensitive ones are explored with the coarsest resolution at beginning. This is followed by an optimization based iterative calibration procedure consisting of a series of sub-tasks or runs. Between consecutive runs, the setup configuration is heterogeneous with parameter search ranges and resolutions varying among groups. At the completion of each sub-task, the parameter ranges within each group are systematically refined from their previously estimated ranges which are initially based on a priori information. Parameters attain stable convergence progressively with each run. A comparison of this new calibration framework with a traditional optimization-based approach was performed using a quasi-synthetic double-model setup experiment to calibrate 134 parameters and two well-known distributed hydrological models: the Variable Infiltration Capacity (VIC) model and the Distributed Hydrology Soil Vegetation Model (DHSVM). The results demonstrate statistically that the proposed framework can better mitigate equifinality problem, yields more realistic model parameter estimates, and is computationally more efficient.

stat.AP↗

arXiv2020

Estimation of daily streamflow from multiple donor catchments with Graphical Lasso

A novel algorithm is introduced to improve estimations of daily streamflow time series at sites with incomplete records based on the concept of conditional independence in graphical models. The goal is to fill in gaps of historical data or extend records at streamflow stations no longer in operation or even estimate streamflow at ungauged locations. This is achieved by first selecting relevant stations in the hydrometric network as reference (donor) stations and then using them to infer the missing data. The selection process transforms fully connected streamflow stations in the hydrometric network into a sparsely connected network represented by a precision matrix using a Gaussian graphical model. The underlying graph encodes conditional independence conditions which allow determination of an optimum set of reference stations from the fully connected hydrometric network for a study area. The sparsity of the precision matrix is imposed by using the Graphical Lasso algorithm with an L1-norm regularization parameter and a thresholding parameter. The two parameters are determined by a multi-objective optimization process. In addition, an algorithm based on the conditional independence concept is presented to allow a removal of gauges with the least loss of information. Our approaches are illustrated with daily streamflow data from a hydrometric network of 34 gauges between 1 January 1950 and 31 December 1980 over the Ohio River basin. Our results show that the use of conditional independence conditions can lead to more accurate streamflow estimates than the widely used approaches which are based on either distance or pair-wise correlation.

stat.AP↗

arXiv2020

Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification

RGB-Infrared (IR) person re-identification is very challenging due to the large cross-modality variations between RGB and IR images. The key solution is to learn aligned features to the bridge RGB and IR modalities. However, due to the lack of correspondence labels between every pair of RGB and IR images, most methods try to alleviate the variations with set-level alignment by reducing the distance between the entire RGB and IR sets. However, this set-level alignment may lead to misalignment of some instances, which limits the performance for RGB-IR Re-ID. Different from existing methods, in this paper, we propose to generate cross-modality paired-images and perform both global set-level and fine-grained instance-level alignments. Our proposed method enjoys several merits. First, our method can perform set-level alignment by disentangling modality-specific and modality-invariant features. Compared with conventional methods, ours can explicitly remove the modality-specific features and the modality variation can be better reduced. Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images. With them, we can directly perform instance-level alignment by minimizing distances of every pair of images. Extensive experimental results on two standard benchmarks demonstrate that the proposed model favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve a gain of 9.2% and 7.7% in terms of Rank-1 and mAP. Code is available at https://github.com/wangguanan/JSIA-ReID.

cs.CV↗

arXiv2018

Design and Implementation of Global Path Planning System for Unmanned Surface Vehicle among Multiple Task Points

Global path planning is the key technology in the design of unmanned surface vehicles. This paper establishes global environment modelling based on electronic charts and hexagonal grids which are proved to be better than square grids in validity, safety and rapidity. Besides, we introduce Cube coordinate system to simplify hexagonal algorithms. Furthermore, we propose an improved A* algorithm to realize the path planning between two points. Based on that, we build the global path planning modelling for multiple task points and present an improved ant colony optimization to realize it accurately. The simulation results show that the global path planning system can plan an optimal path to tour multiple task points safely and quickly, which is superior to traditional methods in safety, rapidity and path length. Besides, the planned path can directly apply to actual applications of USVs.

cs.RO↗

arXiv2018

Research and Implementation of Global Path Planning for Unmanned Surface Vehicle Based on Electronic Chart

Unmanned Surface Vehicle (USV) is a new type of intelligent surface craft, and global path planning is the key technology of USV research, which can reflect the intelligent level of USV. In order to solve the problem of global path planning of USV, this paper proposes an improved A* algorithm for sailing cost optimization based on electronic charts. This paper uses the S-57 electronic chart to realize the establishment of the octree grid environment model, and proposes an improved A* algorithm based on sailing safety weight, pilot quantity and path curve smoothing to ensure the safety of the route, reduce the planning time, and improve path smoothness. The simulation results show that the environmental model construction method and the improved A* algorithm can generate safe and reasonable global path.

cs.RO↗