IET Cybersystems and Robotics最新文献

{"title":"Path Planning on Multi-Level Point Cloud With a Weighted Traversability Graph","authors":"Yujie Tang,&nbsp;Quan Li,&nbsp;Yangmin Xie,&nbsp;Yusheng Yang,&nbsp;Hang Shi","doi":"10.1049/csy2.70069","DOIUrl":"https://doi.org/10.1049/csy2.70069","url":null,"abstract":"<p>This article proposes a new path planning method for addressing multi-level terrain situations. The proposed method includes innovations in the following three aspects: (1) the pre-processing of point cloud maps with a multi-level skip-list structure and data-slimming algorithm for well-organised and simplified map formalisation and management, (2) the direct acquisition of local traversability indexes through vehicle and point cloud interaction analysis, which saves work in surface fitting and (3) the assignment of traversability indexes on a multi-level connectivity graph to generate a weighted traversability graph for generally search-based path planning. Then a modified A* algorithm is employed to exploit this traversability graph and generate short and safe paths across level transitions such as ramps, bridges and overpasses. The proposed map structure reduces memory usage by over 70% and achieves a 2<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>×</mo>\u0000 </mrow>\u0000 <annotation> ${times} $</annotation>\u0000 </semantics></math> speedup in surface retrieval compared to state-of-the-art approaches designed for multi-layered environments. The planner attains a 100% success rate across all evaluated scenarios, including challenging multi-level environments where conventional single-height 2.5-dimensional (2.5D) planners fail. The effectiveness and reliability of the proposed method are verified through indoor and outdoor experiments conducted in various environments, including multi-floor buildings, woodland and rugged mountainous regions. The results demonstrate that the proposed method can properly address three-dimensional (3D) path planning problems for ground vehicles in a wide range of situations.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Object Detection Model for ROV-Based Underwater Foreign Object Salvage","authors":"Zhongyue Zhang,&nbsp;Xingguang Duan,&nbsp;Fusen Zhang,&nbsp;Jiale Huan,&nbsp;Changsheng Li,&nbsp;Shikui Jia","doi":"10.1049/csy2.70068","DOIUrl":"https://doi.org/10.1049/csy2.70068","url":null,"abstract":"<p>Addressing challenges in underwater industrial maintenance, such as degraded quality, target occlusion and platform constraints, this paper proposes UGS-YOLO_SP, a high-precision lightweight model for foreign object recovery using a remotely operated vehicle (ROV). To mitigate data scarcity, a real-world underwater operation dataset is first constructed. The study then introduces the gated strip-aware spatial separation (GS3) block to enhance spatial context modelling for slender structures and the lightweight enhanced shared detail convolutional detection (LESCD) head to reduce redundancy via parameter sharing. This paper presents a self-distillation and pruning (SP) lightweight framework that applies bridging cross-task protocol inconsistency self-knowledge distillation (BCSKD) for feature discrimination against underwater interference and layer-adaptive magnitude-based pruning (LAMP) for parameter reduction, achieving an optimal trade-off between detection accuracy and computational efficiency under resource-constrained conditions. Experimental results demonstrate superior performance on the underwater dataset. Compared to the YOLOv11 baseline, UGS-YOLO_SP reduces parameters by 61.3% and computational costs (giga floating-point operations per second, GFLOPs) by 39.7%, while achieving 98.66% precision and 98.18% mean average precision (mAP) at an intersection-over-union (IoU) threshold of 0.50 (mAP50).</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149048142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning-Guided Bidding Weight Selection for Dynamic Heterogeneous Multi-Robot Task Allocation","authors":"Haomiao Zeng,&nbsp;Donghui Zhao,&nbsp;Tianqi Lu,&nbsp;Shixuan Cheng,&nbsp;Jiahui Ding,&nbsp;Junyou Yang,&nbsp;Shuoyu Wang","doi":"10.1049/csy2.70067","DOIUrl":"https://doi.org/10.1049/csy2.70067","url":null,"abstract":"<p>To address the limited adaptability of fixed bidding weights to task arrivals, cooperative requirement changes, and online replanning in dynamic heterogeneous multi-robot task allocation (MRTA), this paper proposes a learning-guided market-based task allocation (LGMTA) method. The proposed method combines learning-guided bidding weight template selection with market-based constrained matching, and introduces assignment retention into event-driven local replanning to improve dynamic allocation adaptability and online replanning stability. To validate the effectiveness of the proposed method, a heterogeneous MRTA simulation system is built, forming a unified validation environment with six representative environment maps and five types of heterogeneous robot platforms. Random simulation runs are conducted under small, medium, and large online dynamic task scenarios. The simulation results show that LGMTA maintains high task completion and cooperative task completion rates, while achieving the lowest allocation-quality normalised regret under all three scales, with values of 0.360, 0.244, and 0.224, respectively. Compared with the fixed market method and the consensus-based bundle algorithm (CBBA), LGMTA shows a better overall allocation quality and keeps the assignment perturbation rates at 0.021, 0.012, and 0.009 under the three scales, respectively, indicating a better online replanning stability. Within the evaluated simulation scenarios, the results show that learning-guided bidding weight template selection improves the adaptability of market-based allocation to dynamic task states, whereas assignment retention reduces disturbances to still-valid assignments and improves online replanning stability.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The State of Dynamic and Wireless In-Motion Power Delivery to Grounded Mobile Robots","authors":"Nicklas Vraa,&nbsp;Uffe Jakobsen,&nbsp;Mohammad Hassan Khooban","doi":"10.1049/csy2.70065","DOIUrl":"https://doi.org/10.1049/csy2.70065","url":null,"abstract":"<p>This work reviews efforts to develop systems for in-motion wireless power delivery, that is, the transmission of energy to moving receivers (RX) through untethered interaction. The application in focus is supplying small-to-medium-sized grounded mobile robots, but the insights extend beyond this context and the review serves as a platform for developing such systems. A review of the literature strongly indicates that such systems must rely on inductive coupling with magnetic resonance (MR), a technique that introduces its own set of technical challenges in real-world scenarios. The most significant of these are analysed, and corresponding solutions from the literature are presented and critically reviewed. This review differs from earlier work in that prior findings are examined in the context of multi-transmitter (TX) multi-receiver systems, as this configuration was found to be preferable for sufficiently efficient dynamic wireless power transfer.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Proposal on Generalisable Emergent Synchronisation via Swarm-Inspired Central Pattern Generators","authors":"Ji Chen,&nbsp;Song Chen,&nbsp;Li Fan,&nbsp;Chao Xu","doi":"10.1049/csy2.70066","DOIUrl":"https://doi.org/10.1049/csy2.70066","url":null,"abstract":"<p>Central pattern generators (CPGs) provide a powerful biological principle for rhythmic coordination, but artificial CPGs often depend on manually designed coupling functions and topology-specific analysis. This proposal focuses on the generalisation mechanism of a swarm-inspired central pattern generator (SCPG), in which each oscillator learns local attention-based interactions with its neighbours and collective synchronisation emerges from these distributed decisions. The central hypothesis is that learnt local attention can serve as a general coupling rule that transfers across network scale and target synchronisation mode. To test this hypothesis, the proposal centres on scale/task generalisation experiments, a simplified phase-model experiment that probes whether a fixed phase-dependent coupling rule can generalise across network sizes and ablation studies that identify the architectural source of generalisation. The expected outcome is a focused mechanistic account of why SCPG can replace handcrafted CPG coupling rules with scalable learnt local interaction.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70066","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Modelling and Energy Efficiency Prediction of a Multi-Energy Complementary Thermal Storage System for Cigarette Manufacturing via a Physics-Enhanced LSTM","authors":"Yin He,&nbsp;Lihong Zhang,&nbsp;Yaoguang Xia,&nbsp;Fan Wu,&nbsp;Xiaoming Jin","doi":"10.1049/csy2.70063","DOIUrl":"https://doi.org/10.1049/csy2.70063","url":null,"abstract":"<p>To address the challenges of strong nonlinearity, high thermal inertia and severe data discontinuity caused by ‘off-peak’ storage strategies in large-capacity thermal storage systems within cigarette manufacturing, this paper proposes a physics-enhanced long short-term memory (PE-LSTM) modelling framework. By systematically integrating engineering thermophysics with deep learning, the framework enhances model credibility and generalisation across multiple layers. Specifically, a temporal causality integrity check algorithm is developed to mitigate intermittent sampling issues, preventing the learning of spurious dynamic responses across data gaps by blocking gradient backpropagation during non-operational periods. Furthermore, physics-aware feature engineering reconstructs highly coupled variables, such as heating power and coefficient of performance (COP), based on energy conservation laws. A multi-task collaborative learning architecture is then employed, utilising an asymmetric weighted loss function to explicitly embed energy consistency residuals and reverse Carnot cycle constraints. Compared with task-specific single-output standard LSTM baselines, the proposed PE-LSTM maintains comparable test-set accuracy for tank temperature, heat-pump power, COP and stepwise heat production within a unified multi-output framework. These results indicate that the proposed model provides a physically consistent modelling foundation for energy analysis and operation optimisation in tobacco industrial thermal systems.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70063","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"System-Level Validation of a Digital Twin-Mixed Reality Framework Towards Proactive Human–Robot Collaboration","authors":"Michael M. Gichane,&nbsp;Jean B. Byiringiro,&nbsp;Mourad Benoussaad,&nbsp;Micky Rakotondrabe","doi":"10.1049/csy2.70064","DOIUrl":"https://doi.org/10.1049/csy2.70064","url":null,"abstract":"<p>In the pursuit of proactive human–robot collaboration, mutual cognition depends not only on smarter robots but also on more capable human operators able to anticipate robot actions through enhanced cognitive function. In this study, we propose a digital twin (DT)-based mixed reality system that delivers immersive and real-time representations of robot states, task progression and motion trajectories which establish the system-level preconditions for human prediction and informed intervention during collaboration. The framework is validated through system-level properties—spatial fidelity, temporal relevance and robustness. These constitute necessary technical conditions for improved cognitive function, such as trust and anticipation in proactive human–robot collaboration, rather than directly measuring human cognitive outcomes. Validation involves a full-factorial case study that assesses positional accuracy and communication delay across varying motion trajectories, tool centre point speeds and network conditions. Results demonstrate positional precision of 0.105, 0.150 and 0.158 mm in <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>X</mi>\u0000 </mrow>\u0000 <annotation> $X$</annotation>\u0000 </semantics></math>, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>Y</mi>\u0000 </mrow>\u0000 <annotation> $Y$</annotation>\u0000 </semantics></math> and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>Z</mi>\u0000 </mrow>\u0000 <annotation> $Z$</annotation>\u0000 </semantics></math> axes, respectively, under optimal conditions, a high correlation between actual and virtual locations (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>r</mi>\u0000 </mrow>\u0000 <annotation> $r$</annotation>\u0000 </semantics></math> &gt; 0.97) and a communication latency of 54.85 ms and DT rendering latency of 7.09 ms. This contributes to proactive human–robot collaboration research by illustrating system-level technical preconditions necessary to support human-cognitive function such as trust and anticipatory control for scalable human–robot collaboration in industrial applications.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70064","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Hierarchical Hybrid Framework for Real-Time Dense Semantic Mapping With Semantic Rendering and Dynamic Keyframe Optimisation","authors":"Fengkai Zhou,&nbsp;Chi Li,&nbsp;Yan Zhuang","doi":"10.1049/csy2.70062","DOIUrl":"https://doi.org/10.1049/csy2.70062","url":null,"abstract":"<p>Real-time dense three-dimensional (3D) semantic mapping plays a crucial role in robotics. However, existing explicit and implicit representations often entail a trade-off among geometric precision, semantic richness and computational efficiency. To address this challenge, we propose a hierarchical hybrid mapping framework that unifies geometry, appearance and dense semantics within a shared multiresolution hash grid, enabling end-to-end optimisation via differentiable rendering. By caching per-keyframe semantic masks and reusing them during incremental refinement, our method eliminates redundant semantic segmentation and significantly accelerates runtime. Additionally, an adaptive keyframe pruning strategy further ensures bounded memory usage. Extensive experiments demonstrate that our framework achieves real-time performance with superior geometric and semantic accuracy.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70062","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatio-Temporal Alignment of On-Board Sensors for Railway Systems","authors":"Ping Tan,&nbsp;Shaofei Li,&nbsp;Dongsheng Zhu,&nbsp;Xianjie Li,&nbsp;Huoping Yi,&nbsp;Yongbo Wu,&nbsp;Yang Zhao,&nbsp;Wenjun Huang","doi":"10.1049/csy2.70056","DOIUrl":"10.1049/csy2.70056","url":null,"abstract":"<p>To address the challenges of obstacle detection in railway environments, this paper proposes a highly robust perception method based on light detection and ranging (LiDAR) and camera fusion. The core of this method is an innovative spatio-temporal alignment framework designed to resolve the critical issue of spatio-temporal misalignment in conventional point cloud and image data processing. For temporal synchronisation, the framework employs the precision time protocol (PTP) to achieve microsecond-level time synchronisation between the LiDAR and camera, thereby improving cross-modal temporal consistency at their acquisition timestamps. In the spatial domain, the method eliminates the dependency on specific calibration targets by introducing an adaptive and targetless calibration strategy based on natural scene features. This strategy constructs a multi-channel scoring function to maximise the mutual information (MI) between point cloud and image features, and it leverages a particle swarm optimisation (PSO) algorithm to efficiently solve for the sensors' six-degree-of-freedom (6-DoF) extrinsic parameters. Experimental results demonstrate that the proposed method achieves high-precision online calibration in railway scenarios. By providing an integrated solution to the spatio-temporal misalignment problem, this study effectively improves the performance of multi-sensor fusion, significantly enhancing the reliability and accuracy of perception for railway perimeter security.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70056","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent AgUAV Path Optimisation Using SAC for IoT-Enabled Agricultural Monitoring and Data Collection","authors":"Emmanuel Baba,&nbsp;Hamayadji Abdoul Aziz,&nbsp;Ado Adamou Abba Ari,&nbsp;Gerard Kponhinto,&nbsp;Khouloud Boukadi,&nbsp;Zibouda Aliouat","doi":"10.1049/csy2.70057","DOIUrl":"10.1049/csy2.70057","url":null,"abstract":"<p>In the context of smart agricultural monitoring, the issue of complete coverage of the field area and connectivity among agricultural Internet of Things (AgIoT) devices for data collection represents a major challenge. To resolve this issue, it is imperative to implement sophisticated optimisation methods. This paper proposes a hybrid scheme combining a multiplicatively weighted Voronoi diagram (MWVD) and deep reinforcement learning (DRL) for agricultural field coverage-based agricultural unmanned aerial vehicle (AgUAV) data collection. The first method divides the field to be monitored into several areas of interest based on epidemics, areas with low irrigation or large infestations. The second method, which is a DRL algorithm, optimises the position of drones as part of their data collection mission at preselected agricultural cluster head (AgCH) nodes in the MWVD agricultural field. The objective of this article is to optimise the movement of drones to collect data from AgIoT sensors in the agricultural field by using the MWVD algorithm to segment the field and initialise the position of the rendezvous point AgCH collector and DRL to optimise the position of drones to reduce the total energy consumption of drones, collect data reliably and optimise the total coverage of the field in an intelligent manner.</p>","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"8 1","pages":""},"PeriodicalIF":1.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/csy2.70057","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148381138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}