Autonomous exploration in unknown environments has become a critical capability of mobile robots. Many methods often suffer from problems such as exploration goal selection based solely on information gain and inefficient tour optimization. Recent reinforcement learning-based methods do not consider full area coverage and the performance of transferring learned policy to new environments cannot be guaranteed. To address these issues, a dual-stage exploration method has been proposed, which combines spatial clustering of possible exploration goals and Traveling Salesman Problem (TSP) based tour planning on both local and global scales, aiming for efficient full-area exploration in highly convoluted environments. Our method involves two stages: exploration and relocation. During the exploration stage, we introduce to generate local navigation goal candidates straight from clusters of all possible local exploration goals. The local navigation goal is determined through tour planning, utilizing the TSP framework. Moreover, during the relocation stage, we suggest clustering all possible global exploration goals and applying TSP-based tour planning to efficiently direct the robot toward previously detected but yet-to-be-explored areas. The proposed method is validated in various challenging simulated and real-world environments. Experimental results demonstrate its effectiveness and efficiency. Videos and code are available at https://github.com/JiatongBao/exploration.

Bone fractures are common injuries that require quick and accurate diagnosis to provide the right medical care. The “convolutional neural network” technique relies mostly on manual inspection, by radiologists and can be laborious and prone to error. The objective of this work was to increase the efficiency and accuracy of fracture identification by automating the examination of X-ray images using convolutional neural networks. A “convolutional neural network” model created to detect bone fractures in X-ray images was used in the present study. The model was trained and validated using an extensive dataset of X-ray images, which included both fractured and nonfractured bones. Multiple convolutional layers were used in the “convolutional neural network” architecture for feature extraction, and pooling and fully connected layers were added for classification. The main measures used to assess the model's performance were sensitivity, specificity, and accuracy. In regard to identifying bone fractures, the “convolutional neural network”-based model outperformed the conventional technique. With significant gains in sensitivity and specificity, this approach achieved a high accuracy rate and decreased the frequency of false positives and false negatives. We used “convolutional neural network” tool in PyTorch for bone fracture detection and we outlined the important considerations that must be considered when attempting to achieve this goal Additionally, we contrasted every study with our baseline. Here our maximum accuracies were 99.05%, 98.60%, 99.45% and 99.74% for epochs 8, 9, 10 and 11, respectively. These findings highlight the model's ability to improve the diagnostic efficiency and accuracy in clinical settings. Using “convolutional neural network” to identify bone fractures from X-ray images is a promising development in medical imaging. In the end, our method improves patient outcomes by ensuring faster and more reliable fracture diagnosis while also lessening the diagnostic burden on radiologists. Subsequent investigations will focus on incorporating this system into clinical procedures and investigating its utilization in real-time emergency situations. Since there was no medical intervention on human subjects in this investigation, trial registration regulations were not applied.

The transition from centralized fossil fuel-based power systems toward decentralized smart grids with high penetration of renewable energy sources (RESs) introduces substantial challenges in monitoring, control, coordination, and management. These challenges are particularly evident at the active power grid periphery, defined in this work as the decentralized edge layer of modern power systems comprising low-voltage distribution networks, distributed energy resources (DERs), prosumers, energy storage systems, electric vehicles (EVs), and localized intelligent control entities operating near the consumer side of the grid. This review systematically examines the role of multi-agent systems (MASs) in addressing these emerging challenges. A total of 160 Q1 journal articles published up to March 2026 were systematically analyzed to evaluate recent methodological advances, identify persistent research gaps, and compare existing problem formulations and mathematical techniques. The review covers MAS-based applications including distributed energy management, voltage and frequency regulation, demand-side management, microgrid coordination, EV charging coordination, resilience enhancement, and cyber-physical supervisory control. The findings indicate that although MASs offer enhanced scalability, flexibility, resilience, and decentralized decision-making capabilities, existing approaches continue to face significant limitations associated with communication latency, cybersecurity vulnerabilities, interoperability constraints, heterogeneous agent dynamics, and limited real-time experimental validation. Furthermore, this review proposes six emerging research hypotheses targeting underexplored domains, presents a methodological decision flowchart for MAS implementation and selection, and discusses future research directions involving the integration of digital twins, blockchain technologies, edge intelligence, and advanced communication architectures with MAS frameworks. Unlike previous review studies, this work provides a systematic comparison between MAS-based architectures and hierarchical industrial control frameworks based on IEC 61850 standards while identifying the absence of standardized benchmarking platforms as a critical limitation within the existing literature. Overall, this paper aims to serve as a comprehensive reference for researchers and practitioners seeking to design, evaluate, and implement MAS-driven control and management strategies for future active power grid peripheries.

The transition from centralized fossil fuel-based power systems toward decentralized smart grids with a high penetration of renewable energy sources (RES) introduces substantial challenges in monitoring, control, coordination, and management. These challenges are particularly evident at the active power grid periphery, defined in this work as the decentralized edge layer of modern power systems comprising low-voltage distribution networks, distributed energy resources (DERs), prosumers, energy storage systems, electric vehicles (EVs), and localized intelligent control entities operating near the consumer side of the grid. This review systematically examines the role of multi-agent systems (MASs) in addressing these emerging challenges. A total of 160 articles, drawn predominantly from top-tier Q1 journals and published up to March 2026, were systematically analyzed to evaluate recent methodological advances, identify persistent research gaps, and compare existing problem formulations and mathematical techniques. The review covers MAS-based applications including distributed energy management, voltage and frequency regulation, demand-side management, microgrid coordination, EV charging coordination, resilience enhancement, and cyber-physical supervisory control. The findings indicate that although MASs offer enhanced scalability, flexibility, resilience, and decentralized decision-making capabilities, existing approaches continue to face significant limitations associated with communication latency, cybersecurity vulnerabilities, interoperability constraints, heterogeneous agent dynamics, and limited real-time experimental validation. Furthermore, this review proposes six emerging research hypotheses targeting underexplored domains, presents a methodological decision flowchart for MAS implementation and selection, and discusses future research directions involving the integration of digital twins, blockchain technologies, edge intelligence, and advanced communication architectures with MAS frameworks.