Article
Automation & Control Systems
Chengpeng Li, Qinyuan Ren, Zuhua Xu, Jun Zhao, Chunyue Song
Summary: In this paper, an adaptive finite-time impedance control strategy based on optimised backstepping (OB) technique is proposed. The proposed method overcomes the drawback of existing OB methods by constructing simplified reinforcement learning (RL) updating laws and relaxing the persistence excitation requirement. The effectiveness of the proposed method is demonstrated through a simulation example with environment-robot interaction.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Automation & Control Systems
Kaixin Lu, Shuaishuai Han, Jun Yang, Haoyong Yu
Summary: Compliant actuators have great advantages in safe robot control, but achieving optimal trajectory tracking control remains a challenge. This study proposes an inverse optimal adaptive neural control scheme, which uses a tuning functions-based adaptive learning mechanism to improve control efficiency and simplify implementation in practical engineering systems.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Dan Bao, Xiaoling Liang, Shuzhi Sam Ge, Baolin Hou
Summary: This article proposes an adaptive neural trajectory tracking control scheme for n-DOF robotic manipulators subjected to parameter variations, unknown functions, and time-varying external disturbances. The computed torque control (CTC) method is used to reduce the system's nonlinearity. Radial basis function neural networks (RBFNNs) are constructed to approximate the uncertainties due to parameter variations and unknown functions. The effectiveness of the proposed method is validated through simulations on a seven-degrees of freedom robotic manipulator.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Mien Van, Yuzhu Sun, Stephen Mcllvanna, Minh-Nhat Nguyen, Mohammad Omar Khyam, Dariusz Ceglarek
Summary: This article aims to address three major issues in fault tolerant control (FTC) for robot manipulators: improving the response time, reducing tracking errors and chattering, and increasing the robustness of FTC; reducing the requirement of robot dynamics knowledge for model-based FTC; achieving global fixed-time convergence of the system. An adaptive fuzzy backstepping control is proposed to enhance system tracking performance without the need for complete prior knowledge. The fixed time convergence is mathematically proven and the performance is demonstrated for a PUMA560 robot FTC.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Automation & Control Systems
Shuzong Xie, Meiling Tao, Qiang Chen, Liang Tao
Summary: This article proposes a neural-network-based adaptive finite-time output constraint control scheme for attitude stabilization of rigid spacecrafts. The scheme includes a novel singularity-free terminal sliding mode variable, an auxiliary function to avoid singularity, an adaptive neural control law to approximate uncertainty, and a finite-time prescribed performance function to characterize convergence rate and steady state. Rigorous theoretical proofs and comparative simulations demonstrate the effectiveness and superiority of the proposed scheme.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Automation & Control Systems
Haoran Fang, Yuxiang Wu, Tian Xu, Fuxi Wan
Summary: In this article, a predefined time convergence adaptive tracking control scheme is proposed for uncertain robotic manipulators with input saturation. The scheme utilizes an auxiliary dynamic system, radial basis function neural networks, and a nonsingular terminal sliding mode surface to handle input saturation and improve convergence rate.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Engineering, Electrical & Electronic
Gang Li, Xinkai Chen, Jinpeng Yu, Jiapeng Liu
Summary: This paper proposes an adaptive neural network-based finite-time impedance control method for robotic manipulators with constraints and a disturbance observer. The proposed method combines barrier Lyapunov functions with finite-time stability control theory to achieve faster convergence rate without violating full state constraints. Simulation results demonstrate the effectiveness of the proposed control method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2022)
Article
Automation & Control Systems
Anbang Zhai, Jin Wang, Haiyun Zhang, Guodong Lu, Howard Li
Summary: This paper investigates the cooperative robotic manipulators under uncertain base coordinate and proposes an adaptive robust controller to solve the problem. Mathematical proof and numerical experiments are conducted to demonstrate its effectiveness.
Article
Automation & Control Systems
Zhiguo Xu, Lin Zhao
Summary: This article investigates the consensus tracking problem of uncertain multiple robot manipulators with disturbances. It proposes a distributed adaptive gain-varying finite-time event-triggered strategy. The well-designed dynamic gain functions are added to the static gains to strengthen the antidisturbance ability of the networked system. The command filters and compensation strategy with dynamic gains improve the performance compared to traditional backstepping-based algorithms. The event-triggered mechanism reduces the waste of communication resources in the complex system. Three simulation examples demonstrate its effectiveness.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Xinyu Song, Lin Zhao, Guozeng Cui
Summary: This brief introduces a finite-time tracking control algorithm for robot manipulator systems in a random vibration environment. The algorithm tackles the challenges of parameter uncertainty and input saturation by combining command filtered adaptive backstepping with neural networks. It also introduces an error compensation mechanism based on the fractional power function to enhance trajectory tracking accuracy. The algorithm ensures practical finite-time stability in mean square. Numerical simulations demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Computer Science, Artificial Intelligence
Gang Li, Jinpeng Yu, Xinkai Chen
Summary: In this article, an adaptive fuzzy neural network (NN) command filtered impedance control method is proposed for constrained robotic manipulators with disturbance observers. The barrier Lyapunov functions are introduced to handle the full-state constraints, and the adaptive fuzzy NN is utilized to handle the unknown system dynamics. A disturbance observer is designed to eliminate the effect of unknown bound disturbance. The effectiveness of the proposed control method is validated through simulation studies.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ning Tan, Peng Yu
Summary: Recent studies have shown that using zeroing neural network for model-free feedback control of redundant robot manipulators can achieve excellent convergence and accuracy. By employing nonlinear activation functions, the proposed control scheme is able to track desired paths without knowing kinematic models of robots, and systematically investigates finite-time convergence and robustness. The theoretical analysis proves that the control scheme has finite-time convergence with nonlinear activation functions and the tracking error remains below the upper bound with bounded noise interference.
Article
Automation & Control Systems
Jie Gao, Wei He, Hong Qiao
Summary: This article investigates the event and self-triggered adaptive output feedback control of a manipulator suffering from limited knowledge of states and dynamics, aiming to realize trajectory tracking with less communication occupation. The study proposes a control scheme utilizing a co-located observer and controller with discontinued output feedback. An adaptive event-triggered mechanism based on model estimation is designed to compensate for the error accumulation caused by intermittent open-loop control. The control stability under uncertainty of system dynamics is solved using an adaptive backstepping method with network estimation. A first-order filter is employed to remove the derivative explosion and singularity of the discontinuous virtual signal, while an additional self-adaption signal is designed for error compensation. A gradual updating method is designed for state updating at event instants, and a dead-zone event-triggered condition is built to avoid Zeno-behavior. An easy-implemented self-triggered mechanism is also constructed. The stability of the system is analyzed using Lyapunov function, and simulation results demonstrate the effectiveness of the proposed control method.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Huayang Sai, Zhenbang Xu, Enyang Zhang
Summary: This paper presents an adaptive practical predefined-time neural control scheme for uncertain multi-joint robotic manipulators with input saturation. The proposed control scheme establishes a practical predefined-time stability criterion and approximates the unknown robotic dynamic model using radial basis function neural networks. The input saturation of the robotic manipulator is compensated by introducing an adaptive term. Numerical simulations and experiments on different robotic manipulators demonstrate the effectiveness of the proposed control scheme.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Automation & Control Systems
Yanghe Feng, Linghuan Kong, Zhongyi Zhang, Ruijun Liu, Guangquan Cheng, Xinbo Yu
Summary: In this article, an event-triggered control policy is proposed for a robotic manipulator with flexible joint (RMFJ) to achieve finite-time convergence under output constraints. The challenging problem of vibration in the flexible joint is addressed by introducing a fractional order term in the design of a finite-time convergence policy. The angular displacements of the link are further constrained using the Barrier function to enhance operation safety, and neural networks learning is utilized to approximate unknown model parameters. The event-trigger design reduces the communication burden.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Guanbin Gao, Yangtao Gao, Fei Liu, Jing Na
Summary: A novel modeling and calibration method for collaborative robots based on position information and modified local product of exponentials (LPoE) is proposed, which improves the speed and accuracy of the identification calculation by simplifying the error model and separating the position error.
JOURNAL OF SENSORS
(2022)
Article
Engineering, Electrical & Electronic
Bin Wang, Ramon Costa-Castello, Jing Na, Oscar de la Torre, Xavier Escaler
Summary: This paper proposes a new adaptive estimation approach for online parameter estimation of a piezoelectric cantilever beam. By introducing the Galerkin method and separating the time and space variables of the PDE, the unknown parameters of the derived ODE model can be estimated in real time.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Engineering, Electrical & Electronic
Yingbo Huang, Huidong Hou, Jing Na, Haoran He, Jing Zhao, Zhenghao Shi
Summary: This paper presents a novel control method for half-vehicle active suspension systems driven by hydraulic actuators. It introduces a coordinate transform approach to reformulate the strict-feedback system into a canonical form without using the backstepping method. A modified high-gain observer (HGO) is studied to rebuild the unknown system states of the nonlinear active suspension system. To eliminate the effect of unknown nonlinearities, a simple robust unknown system dynamics estimator (USDE) is developed. Finally, the observer and estimator are integrated to design an output feedback controller to regulate the vehicle motion. Comparative experiments demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Automation & Control Systems
Xin Chen, Yu Guo, Jing Na
Summary: Synchronous averaging (SA) is a powerful signal processing tool that enhances the features of periodic events by suppressing nonsynchronous components. However, under random slip conditions, SA may not effectively enhance the features related to rolling element bearing (REB) faults. This article proposes two frameworks based on instantaneous angular speed (IAS) for synchronous averaging and introduces an improved negentropy indicator to characterize the richness of REB fault information. The effects of encoder resolution and structure damping factor on the waveform related to faulty REB are also studied. Simulation and experiment results demonstrate the effectiveness of the proposed schemes in enhancing the features of REB faults under random slip conditions.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Haoran He, Jing Na, Yingbo Huang, Tao Liu
Summary: In this article, a novel adaptive parameter estimation scheme is proposed for the continuous-time Hammerstein model. A continuous piecewise linear neural network is adopted to reformulate the dead-zone dynamics, and the K-filter operation is applied to obtain an integrated parametric model. Two adaptive laws based on estimation error are given to estimate the unknown parameters, and an observer is designed to reconstruct the unknown system states. Theoretical analysis and experiments verify the effectiveness of the proposed methods.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Computer Science, Artificial Intelligence
Jing Zhao, Jincan Liu, Pak Kin Wong, Zhongchao Liang, Zhengchao Xie, Jing Na
Summary: This article proposes a generalized fuzzy subset (GFS) method to assess the time-varying multistate reliability. The method integrates all possible perturbations as inputs and constructs a GFS reliability model based on the composite limit state. The concept of uncertain subset boundary is introduced to conduct the reliability assessment using embedded interval type-2 fuzzy sets. A data-driven strategy is designed to address the deficiency of the GFS reliability model.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Automation & Control Systems
Dong-Dong Zheng, Xianyan Li, Xuemei Ren, Jing Na
Summary: The purpose of this study is to improve the transient performance and address the potential boundary-crossing issue in the design of a neural network-based intelligent prescribed performance control for robotic manipulators with input saturation. An auxiliary system is created to modify the performance boundaries when saturation occurs, ensuring that the tracking errors meet the performance constraints even when control effort is limited. A composite learning-based online identification scheme is employed to enhance the transient performance, and a Gaussian function is used to adaptively adjust the learning rate during weight updating. The stability of the closed-loop system is demonstrated through the Lyapunov approach, and simulation results support the effectiveness of the proposed identification and control schemes.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Automation & Control Systems
Xingling Shao, Fei Zhang, Wendong Zhang, Jing Na
Summary: This article investigates a finite-time composite learning-based elliptical enclosing control for nonholonomic robots under a GPS-denied environment. A novel bearing measurement-based relative position observer is proposed to assure estimation errors decay without GPS. An elliptical guidance law is established to yield the reference velocity and angular rate using observation outcomes. A finite-time composite neural learning driven by weight and tracking errors is devised to achieve precise disturbance compensation and error convergence.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Automation & Control Systems
Xiaomei Wang, Jing Na, Ben Niu, Xudong Zhao, Tingting Cheng, Wenqi Zhou
Summary: This paper proposes an adaptive bipartite secure consensus asymptotic tracking control scheme based on event-triggered strategy for the nonlinear multi-agent systems (MASs) under denial-of-service (DoS) attacks. The paper successfully addresses the bipartite consensus control problem with unbalanced communication topology by incorporating the concept of shortest path into the hierarchical algorithm. An anti-attack bipartite control strategy is proposed using improved forms of tracking errors and virtual controllers, and a modified event-triggered mechanism based on relative threshold strategy ensures asymptotic convergence of bipartite consensus tracking errors.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Jintao Zhang, Xingling Shao, Wendong Zhang, Jing Na
Summary: This article proposes a path-following control method that enhances transient performances for networked mobile robots traveling over a single curve. By using a coordinated error based on projective arc length, a path-following controller is designed for multiple robots, achieving a queue formation pattern with equal arc spacing at a uniform velocity. Additionally, a tracking differentiator-based prescribed performance control scheme is proposed to enforce tracking deviations of geometric and dynamic objectives before a specified time. The developed scheme allows for cooperative behavior over a general curve and arbitrary designation of desired settling time for each robot, while ensuring convergence of all error variables.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Chao Zhang, Xuemei Ren, Jing Na, Dongdong Zheng
Summary: This article proposes a safe dual-layer nested adaptive prescribed performance control approach for nonlinear systems, which ensures predefined transient and steady-state performances for the discontinuous reference signal. A monitoring mechanism and a novel dual-layer nested adaptive sliding mode compensation technique are introduced to handle system uncertainties effectively.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Zhijiang Gao, Pak Kin Wong, Jing Zhao, Zhixin Yang, Yingbo Huang, Jing Na
Summary: This article addresses the optimal control problem for magnetorheological fluid-based semiactive suspension systems with input saturation and time-varying delay. A robust switched H∞ method based on the Takagi-Sugeno fuzzy theory is proposed to handle this problem. A novel hybrid model incorporating the fluid flow mechanism and hysteresis phenomenon model is used to separate the passive and active components of the MRF damper. Linear matrix inequality conditions are derived to capture the features of input saturation and time-varying delay, and a Lyapunov-Krasovskii function is employed to ensure stability. Numerical examples demonstrate the effectiveness of the proposed method in dealing with the MRF-SAS system with input saturation and time-varying delay.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.