Robust fuzzy model predictive control of discrete nonlinear systems is investigated in this paper. A recently developed Takagi-Sugeno (T-S) approach which uses local models adopted to approximate the systems. critical issue that restricts practical application classical online computational cost. For T-S systems, burden even worse. Especially for complex with severe nonlinearities, parametric uncertainties, and disturbances, existing usually leads a very conservative solution or no some...

Wheelchair upper-limb exoskeletons can offer a new paradigm to assist people with neuromuscular dysfunction in their activities of daily living such as eating and drinking. A key challenge control is ensure safe comfortable interaction between the human upper limb exoskeleton. Compared industrial manipulators, suffer severe kinematic dynamic uncertainties external disturbances. Therefore, selection optimal methods that address aforementioned required. In this article, method combining...

The vehicle routing problem with backhauls (VRPBs) is a challenging commonly studied in computer science and operations research. Featured by linehaul (or delivery) backhaul pickup) customers, the VRPB has broad applications real-world logistics. In this article, we propose neural heuristic based on deep reinforcement learning (DRL) to solve traditional improved variants, an encoder–decoder structured policy network trained sequentially construct routes for vehicles. Specifically, first...

In this paper, model predictive control (MPC) of discrete T-S fuzzy systems subjected to bounded time-varying delay and persistent disturbances is investigated. The Razumikhin approach adopted for time-delay because it involves a Lyapunov function associated with the original nonaugmented state space system dynamics when compared Krasovskii approach. As such, has good potential avoid inherent complexity especially in presence large delays disturbances. Based on which, both online offline MPC...

In this paper, two efficient robust fuzzy model predictive control algorithms are investigated for discrete nonlinear systems with multiple time delays and bounded disturbances. The famous Takagi-Sugeno (T-S) utilized to represent systems. Instead of the Lyapunov-Krasovskii functional, Lyapunov-Razumikhin function is adopted deal because it involves invariant sets in original state space system. A sequence explicit laws corresponding a constraint computed offline so that online computational...

This paper introduces the Long Short-Term Memory with Dual-Stage Attention (LSTM-MSA) model, an approach for analyzing electromyography (EMG) signals. EMG signals are crucial in applications like prosthetic control, rehabilitation, and human-computer interaction, but they come inherent challenges such as non-stationarity noise. The LSTM-MSA model addresses these by combining LSTM layers attention mechanisms to effectively capture relevant signal features accurately predict intended actions....

With the rapid development of world city network, traditional location theory has gradually been disproven, and advantages flow space over vertical organizational structure are being revealed. Therefore, from corporate branch networks investment networks, 21 cities in urban agglomerations Guangdong taken as case studies for this paper. Furthermore, paper, 5 representative types contact data (catering service, financial life sports leisure accommodation service) selected, social network...

In addition to the forward inference of materials properties using machine learning, generative deep learning techniques applied on science allow inverse design materials, i.e., assessing composition-processing-(micro-)structure-property relationships in a reversed way. this review, we focus (micro-)structure-property mapping, crystal structure-intrinsic property and microstructure-extrinsic property, summarize comprehensively how can be performed. Three key elements, construction latent...

The research area of bio-inspired control methods for multi-legged robots and reptile has made significant development with the use central pattern generators (CPGs) in recent years. However, there are still many problems to be solved learn clearly structure CPG adapt it different frameworks applications. One is that exiting CPGs almost only can used a special kind robots. In this article, we present an improved method constructing CPGs. phase difference between neurons which constitute set...

The central pattern generator (CPG) has been found to be a real, existing neuron controller for the locomotion control of animals and it used on bio-inspired robots widely in recent years. However, research adaptability CPG-based methods is still challenge. In particular, performance CPG method quadruped not good enough some situations compared with traditional force methods. this article, we adopt which phase difference between oscillators can arbitrarily adjusted, try improve CPG's...

In this paper, the position tracking control problem of a wheelchair upper-limb exoskeleton robot is investigated. The dynamic model an multi-input multi-output nonlinear system that usually suffers complex couplings among joints, modeling errors and uncertainties, variance in payload caused by human upper limb. Instead traditional proportional-derivative method, combination sliding mode fuzzy logic, i.e., control, developed work. free dynamics, thus it robust to uncertainties within...

Abstract Assist-as-needed control with a soft robotic hand glove for active rehabilitation is studied in this work. There are two resources of the grasping force, and subject. Compared traditional passive where force merely provided by device (such as exoskeleton, glove), assist-as-needed accounts user contribute to performing tasks collaboratively. In method, human muscle strength estimated through myoelectrical signals forearm collected MYO armband. A neural network used recognition...

This paper focuses on designing fuzzy controllers for a kind of Heating, Ventilation, and Air Conditioning (HVAC) systems. A method based T-S models with nonlinear local feedbacks is applied to specific HVAC system. Firstly, an augmented system model got existing model. Then control systems reviewed. The gain by solving set linear matrix inequalities (LMIs) where H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> performance considered....

This paper presents a robust model predictive control method for discrete nonlinear systems. Instead of conventional T-S fuzzy system where linear local models are used, with is adopted that the number rules decreased and computational burden reduced. Meanwhile, persistent external disturbances also considered in systems input-to-state stability realized. Based on concept positively invariant set, terminal constraint set built. The advantages developed demonstrated simulation by comparison...

Abstract Machine learning-based image super-resolution (SR) has garnered increasing research interest in recent years. However, there are two issues that have not been adequately addressed. The first issue is existing SR methods often overlook the importance of improving quality training dataset, which a crucial factor determining performance, regardless method employed. second while some studies report high numerical metrics, visual results remain unsatisfactory. To address problem, we...

Abstract In today's world, remote-controlled robots are widely used across various industries due to their ability enhance working efficiency in applications. Learning about robot operation and human–computer interaction has emerged as a popular topic recent times. Indeed, learning robotics can be challenging for many students it requires knowledge of programming, control systems, electronics, etc. Collaborative physical setting is common higher education received significant attention its...

Abstract Extending the workspace of cable robots can enhance their motion ability and help us make fuller use potential. This work designs a novel robot utilizes slackness to extend its workspace. First, we driving cables actuated by main motors constrained driven auxiliary equipped with lockers control restrain end-effector respectively. Then classify constraints on into different modes according whose lengths be changed continuous tension distribution switch among them. To expand...