In this paper, we propose a policy-guided Monte Carlo Tree Search (MCTS) decoder that achieves near maximum-likelihood decoding (MLD) performance for short block codes. The MCTS decoder searches for test error patterns (TEPs) in the received information bits and obtains codeword candidates through re-encoding. The TEP search is executed on a tree structure, guided by a neural network policy trained via MCTS-based learning. The trained policy guides the decoder to find the correct TEPs with minimal steps from the root node (all-zero TEP). The decoder outputs the codeword with maximum likelihood when the early stopping criterion is satisfied. The proposed method requires no Gaussian elimination (GE) compared to ordered statistics decoding (OSD) and can reduce search complexity by 95\% compared to non-GE OSD. It achieves lower decoding latency than both OSD and non-GE OSD at high SNRs.

Corrosion semantic segmentation (CSS) is essential for early and accurate detection and positioning of corrosion in complex real-life scenarios. However, the unique characteristics of corrosion patterns, including the diverse forms, blurred boundaries, and intra-class heterogeneity, pose significant challenges in CSS. To address these challenges, we propose a Prototype-based Multi-dimension Sample-Adaptive Intensity Mapping with Density Sampling network (PMSAD) for CSS. PMSAD leverages nonparametric nearest prototype retrieving to enhance intra-class cohesion and inter-class separation, thereby handling the challenge of diverse forms. In PMSAD, prototypes are equally assigned to each class during training to mitigate class imbalance and capture intra-class variations. In addition, we elaborately design and implement three core components in PMSAD, including Multi-Scale Dual Attention (MSDA), Multi-dimension Sample-adaptive Intensity Mapping (MSAIM), and Density Sampling (DS). The MSDA enhances feature discrimination, facilitating robust representation learning. The end-to-end MSAIM adaptively adjusts RGB channel intensity contrasts of the input corrosion image to enhance feature robustness, counteracting the effects of uneven natural illumination. The DS is proposed for training refinement to tackle fuzzy boundaries and internal interference between corrosion classes. It focuses on high-density, high-error regions, offering refined guidance to correct intra-cluster centers and reduce inter-cluster similarity. Extensive evaluations on real-world datasets, including coarse and relabeled fine-grained dataset, validate the superior performance and generalization ability of PMSAD, achieving the new state-of-the-art performance in precise boundary delineation and accurate corrosion classification. The code is available at: https://github.com/c1oTTpD/PMSAD.

Wireless Human-Machine Collaboration (WHMC) represents a critical advancement for Industry 5.0, enabling seamless interaction between humans and machines across geographically distributed systems. As the WHMC systems become increasingly important for achieving complex collaborative control tasks, ensuring their stability is essential for practical deployment and long-term operation. Stability analysis certifies how the closed-loop system will behave under model randomness, which is essential for systems operating with wireless communications. However, the fundamental stability analysis of the WHMC systems remains an unexplored challenge due to the intricate interplay between the stochastic nature of wireless communications, dynamic human operations, and the inherent complexities of control system dynamics. This paper establishes a fundamental WHMC model incorporating dual wireless loops for machine and human control. Our framework accounts for practical factors such as short-packet transmissions, fading channels, and advanced HARQ schemes. We model human control lag as a Markov process, which is crucial for capturing the stochastic nature of human interactions. Building on this model, we propose a stochastic cycle-cost-based approach to derive a stability condition for the WHMC system, expressed in terms of wireless channel statistics, human dynamics, and control parameters. Our findings are validated through extensive numerical simulations and a proof-of-concept experiment, where we developed and tested a novel wireless collaborative cart-pole control system. The results confirm the effectiveness of our approach and provide a robust framework for future research on WHMC systems in more complex environments.

Deep reinforcement Learning (DRL) offers a powerful framework for training AI agents to coordinate with human partners. However, DRL faces two critical challenges in human-AI coordination (HAIC): sparse rewards and unpredictable human behaviors. These challenges significantly limit DRL to identify effective coordination policies, due to its impaired capability of optimizing exploration and exploitation. To address these limitations, we propose an innovative behavior- and context-aware reward (BCR) for DRL, which optimizes exploration and exploitation by leveraging human behaviors and contextual information in HAIC. Our BCR consists of two components: (i) A novel dual intrinsic rewarding scheme to enhance exploration. This scheme composes an AI self-motivated intrinsic reward and a human-motivated intrinsic reward, which are designed to increase the capture of sparse rewards by a logarithmic-based strategy; and (ii) A new context-aware weighting mechanism for the designed rewards to improve exploitation. This mechanism helps the AI agent prioritize actions that better coordinate with the human partner by utilizing contextual information that can reflect the evolution of learning. Extensive simulations in the Overcooked environment demonstrate that our approach can increase the cumulative sparse rewards by approximately 20%, and improve the sample efficiency by around 38% compared to state-of-the-art baselines.

Reconfigurable intelligent surface (RIS) has emerged as a promising wireless communication technology in the 6G era. Its ability to adaptively reflect signals offers improved coverage and low energy consumption. Existing channel estimation methods for RIS primarily rely on sparse signal recovery techniques with large overcomplete dictionaries, which results in prohibitive computational complexity. To address this issue, we employ the vision transformer (ViT) model for adaptive user positioning and propose a novel user position based dictionary design approach, to effectively reduce dictionary size and solve the off-grid problem. This design approach is incorporated into a unified framework, where user positioning and channel estimation are performed jointly for integrated sensing and communications. A modified unitary approximate message passing sparse Bayesian learning algorithm with an early stopping scheme is proposed to address potential overfitting issues in channel estimation. Extensive simulation results demonstrate the effectiveness and robustness of our proposed framework.

Conventional passive WiFi tracking systems often rely on a triple-antenna receiver, significantly restricting practical scalability and hindering cost-effective deployment in ubiquitous environments. This paper presents WiDuo, a passive WiFi tracking system that achieves real-time single-target Tracking using a compact hardware configuration of one transmitter with a single antenna and one receiver with dual antennas. WiDuo using a channel state information (CSI) quotient modeling to resolve Doppler sign ambiguity, providing coarse velocity estimates as preliminary motion cues. To enhance localization accuracy, we develop a novel spatio-temporal fusion framework that leverages differential estimation of angle of arrival (AoA) and time of flight (ToF), dynamically capturing spatio and temporal variations. This framework employs extended Kalman filter to seamlessly combine AoA and ToF differential estimation with conventional fusion methods, achieving precise trajectory estimation. Extensive experiments in typical indoor scenarios demonstrate that WiDuo attains sub-meter median localization accuracy, offering a practical alternative to more complex antenna configurations while maintaining competitive performance across diverse conditions.

Wireless networked control systems (WNCSs) are critical to Industry 4.0, enabling applications like drone swarms and autonomous robots. The tight interdependence between communication and control demands integrated design, yet traditional approaches treat them separately, leading to inefficiencies. Existing codesign methods often rely on simplified models for single-loop or independent multi-loop systems, overlooking the complexities of large-scale WNCSs. These include coupled control loops, time-correlated wireless channels, sensing-control trade-offs, and computational challenges. To address these challenges, we propose a practical WNCS model that captures correlated dynamics among spatially distributed sensors and actuators sharing limited wireless resources over multi-state Markov block-fading channels. To solve the resulting high-dimensional codesign problem, we develop a deep reinforcement learning (DRL) algorithm that scales efficiently by managing hybrid action spaces, capturing communication-control dependencies, and maintaining robust performance under time-correlated dynamics and resource constraints. Simulations demonstrate that our DRL approach outperforms benchmarks, providing a scalable and effective solution for large-scale industrial WNCSs.

Following the rule of human-centricity, Human Motion Digital Twin (HMDT) attempts to apply human motion data to ensure the development and well-being of human beings. Particularly, perception and estimation of human motion play fundamental roles in realizing HMDT. This work proposes an inertial motion capture system for human motion digital twin (InMoDT). The designed motion capture device is made up of a hub node and inertial measurement units attached to the human body. The proposed algorithm framework supported by sensor fusion and pose calibration algorithms, enables to acquire orientations of sensors and body segments. With the deployment of algorithms, InMoDT achieves an average root mean square error of 4.7$^{\circ}$in estimating orientations when compared with an optical motion capture system. Experimental results show a great correlation ($92.5\%$) and agreement ($97.8\%$) between InMoDT and the optical system. The abilities of InMoDT are spotted in terms of human-centric applications based on the integration of human, cyber system, and physical system, such as motion monitoring and estimation, and human-robot teleoperation.Note to Practitioners—This paper is motivated by the problem of inadequate attention on humans in Cyber-Physical System (CPS) while the roles of operators have a significant effect on industry. With the popular applications of digital twins in CPS, HMDT is expected to monitor, analyze, and assess motion data for facilitating the Human-Cyber-Physical System (HCPS) In this research work, the authors present a system for whole-body motion capture. The proposed system based on a wearable inertial sensor-based device provides a solution to construct HMDT. Moreover, a novel algorithm framework is employed, which consists of the sensor fusion algorithm and the kinematic constraints-based pose calibration algorithm. Experimental results demonstrate the system’s effectiveness in motion sensing accuracy, correlation, and agreement in comparison with the gold standard. The validated applications of the system lie in motion monitoring and estimation, and human-robot teleoperation, showing the potential for enhancing HMDT.

We consider a joint uplink and downlink scheduling problem of a fully distributed wireless networked control system (WNCS) with a limited number of frequency channels. Using elements of stochastic systems theory, we derive a sufficient stability condition of the WNCS, which is stated in terms of both the control and communication system parameters. Once the condition is satisfied, there exists a stationary and deterministic scheduling policy that can stabilize all plants of the WNCS. By analyzing and representing the per-step cost function of the WNCS in terms of a finite-length countable vector state, we formulate the optimal transmission scheduling problem into a Markov decision process and develop a deep reinforcement learning (DRL)-based framework for solving it. To tackle the challenges of a large action space in DRL, we propose novel action space reduction and action embedding methods for the DRL framework that can be applied to various algorithms, including deep Q-network (DQN), deep deterministic policy gradient (DDPG), and twin delayed DDPG (TD3). Numerical results show that the proposed algorithm significantly outperforms benchmark policies.

Remote state estimation where sensors send their measurements of distributed dynamic plants to a remote estimator over shared wireless resources is essential for mission-critical applications of Industry 4.0. Existing algorithms on dynamic radio resource allocation for remote estimation systems assumed oversimplified wireless communications models and can only work for small-scale settings. In this work, we consider remote estimation systems with practical wireless models over the orthogonal multiple-access and non-orthogonal multiple-access schemes. We derive necessary and sufficient conditions under which remote estimation systems can be stabilized. The conditions are described in terms of the transmission power budget, channel statistics, and plants’ parameters. For each multiple-access scheme, we formulate a novel dynamic resource allocation problem as a decision-making problem for achieving the minimum overall long-term average estimation mean-square error. Both the estimation quality and the channel quality states are taken into account for decision making. We systematically investigated the problems under different multiple-access schemes with large discrete, hybrid discrete-and-continuous, and continuous action spaces, respectively. We propose novel action-space compression methods and develop advanced deep reinforcement learning algorithms to solve the problems. Numerical results show that our algorithms solve the resource allocation problems effectively and provide much better scalability than the literature.

Remote state estimation, where many sensors send their measurements of distributed dynamic plants to a remote estimator over shared wireless resources, is essential for mission-critical applications of Industry 4.0. Most of the existing works on remote state estimation assumed orthogonal multiple access and the proposed dynamic radio resource allocation algorithms can only work for very small-scale settings. In this work, we consider a remote estimation system with non-orthogonal multiple access. We formulate a novel dynamic resource allocation problem for achieving the minimum overall long-term average estimation mean-square error. Both the estimation quality state and the channel quality state are taken into account for decision making at each time. The problem has a large hybrid discrete and continuous action space for joint channel assignment and power allocation. We propose a novel action-space compression method and develop an advanced deep reinforcement learning algorithm to solve the problem. Numerical results show that our algorithm solves the resource allocation problem effectively, presents much better scalability than the literature, and provides significant performance gain compared to some benchmarks.

With the fourth revolution of healthcare, i.e., Healthcare 4.0, collaborative robotics is spilling out from traditional manufacturing and will blend into human living or working environments to deliver care services, especially telehealthcare. Because of the frequent and seamless interaction between robots and care recipients, it poses several challenges that require careful consideration: 1) the ability of the human to collaborate with the robots in a natural manner; and 2) the safety of the human collaborating with the robot. In this regard, we have proposed a proximity sensing solution based on the self-capacitive technology to provide an extended sense of touch for collaborative robots, allowing approach and contact measurement to enhance safe and natural human-robot collaboration. The modular design of our solution enables it to scale up to form a large-area sensing system. The sensing solution is proposed to work in two operation modes: the interaction mode and the safety mode. In the interaction mode, utilizing the ability of the sensor to localize the point of action, gesture command is used for robot manipulation. In the safety mode, the sensor enables the robot to actively avoid obstacles.