Kunxiao Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kunxiao Wu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jianyong Zheng
School of Electrical Engineering, Southeast University, Nanjing 210096, China
8 shared publications - Xiaoyi Liu
School of Electrical Engineering, Southeast University, Nanjing 210096, China
7 shared publications - Yuhan Yin
School of Electrical Engineering, Southeast University, Nanjing 210096, China
7 shared publications - Fei Mei
College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China
6 shared publications - Yetong Zhang
School of Electrical Engineering, Southeast University, Nanjing 210096, China
5 shared publications Fei Mei
Hohai University College of Energy and Electrical Engineering
1 shared publication
Latest Publications
- 17 September 2026
VocaSense-X Framework: Advancing Voice Medicine Through Intelligent Diagnosis and Rehabilitation.
Voice disorders are a significant clinical issue that affect millions of people worldwide and can impair their quality of life, professional functioning, and communication. Current methods of diagnosis may be based on subjective clinical examination and disjointed rehabilitation regimens, which may lack accuracy and scalability. The study introduces the VocaSense-X Framework, a comprehensive intelligent system for improving voice medicine through integrated diagnosis and rehabilitation. The framework uses multimodal signal processing, deep learning models, and adaptive feedback mechanisms to provide accurate, data-driven analysis of vocal pathologies, including dysphonia, vocal fold lesions, and neurogenic voice disorders. VocaSense-X is a model that combines a real-time acoustic feature extraction pipeline with a hybrid convolutional-recurrent neural network, achieving superior classification performance across a wide range of patient populations. The framework includes a personalized rehabilitation module that dynamically adjusts therapeutic exercises based on continuous monitoring of the voice, enabling tracking of the patient's progress over time and supporting diagnosis. The experimental analysis using benchmark voice disorder datasets demonstrates that the diagnostic performance of VocaSense-X is significantly better than that of any other comparator architecture tested under the same experimental setup, with an accuracy of > 94. Furthermore, clinician usability tests confirm the framework's usability in both clinical and teletherapy settings. The system proposed herein is designed to fill the gap between intelligent computation and clinical voice medicine, is scalable and evidence-based, and can be used for early detection and structured voice rehabilitation. The implications of VocaSense-X for otolaryngology, speech-language pathology, and digital health platforms make it a pivotal step towards AI-driven voice healthcare innovations.
- 17 September 2026
VocaSense-X Framework: Advancing Voice Medicine Through Intelligent Diagnosis and Rehabilitation.
Voice disorders are a significant clinical issue that affect millions of people worldwide and can impair their quality of life, professional functioning, and communication. Current methods of diagnosis may be based on subjective clinical examination and disjointed rehabilitation regimens, which may lack accuracy and scalability. The study introduces the VocaSense-X Framework, a comprehensive intelligent system for improving voice medicine through integrated diagnosis and rehabilitation. The framework uses multimodal signal processing, deep learning models, and adaptive feedback mechanisms to provide accurate, data-driven analysis of vocal pathologies, including dysphonia, vocal fold lesions, and neurogenic voice disorders. VocaSense-X is a model that combines a real-time acoustic feature extraction pipeline with a hybrid convolutional-recurrent neural network, achieving superior classification performance across a wide range of patient populations. The framework includes a personalized rehabilitation module that dynamically adjusts therapeutic exercises based on continuous monitoring of the voice, enabling tracking of the patient's progress over time and supporting diagnosis. The experimental analysis using benchmark voice disorder datasets demonstrates that the diagnostic performance of VocaSense-X is significantly better than that of any other comparator architecture tested under the same experimental setup, with an accuracy of > 94. Furthermore, clinician usability tests confirm the framework's usability in both clinical and teletherapy settings. The system proposed herein is designed to fill the gap between intelligent computation and clinical voice medicine, is scalable and evidence-based, and can be used for early detection and structured voice rehabilitation. The implications of VocaSense-X for otolaryngology, speech-language pathology, and digital health platforms make it a pivotal step towards AI-driven voice healthcare innovations.
- Open Access
- 29 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (8) , 465
A Lightweight YOLOv8n-Based Network with CAD and DSGE for Power Line Defect Detection
To address the sampling misalignment and detail loss caused by fixed-grid downsampling for small-scale defects, as well as the insufficient differentiated modeling and interaction of defect details and structural context in UAV-acquired power-line images, an enhanced lightweight YOLOv8n-based framework for power-line defect detection is developed. First, a content-adaptive downsampling (CAD) module is developed to predict input-dependent sampling offsets and normalized aggregation weights and to perform differentiable resampling. Combined with local-global interactive depthwise separable convolution, CAD improves the preservation of small-object details while maintaining relatively low computational complexity. Second, a dynamic subspace gated exchange (DSGE) module is proposed to adaptively partition features into a high-frequency detail subspace and a low-frequency structural subspace according to the input content. Heterogeneous branches and bidirectional gated exchange are then employed to jointly model fine-grained details and structural context. In addition, the lightweight mixed local channel attention (MLCA) mechanism is incorporated in the detection head as an auxiliary feature-enhancement component. Experimental results show that the proposed model achieves mAP@0.50 and mAP@0.50:0.95 values of 92.3% and 62.9%, respectively, outperforming the compared models under the current evaluation protocol. With 1.90 M parameters and 5.6 G FLOPs, the model reaches an inference speed of 134.7 FPS on the desktop GPU platform, demonstrating that content-adaptive sampling and dynamic detail–structure interaction can improve small-defect detection and complex-background suppression while maintaining relatively low model complexity.
- 29 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (8) , 465
Open AccessA Lightweight YOLOv8n-Based Network with CAD and DSGE for Power Line Defect Detection
To address the sampling misalignment and detail loss caused by fixed-grid downsampling for small-scale defects, as well as the insufficient differentiated modeling and interaction of defect details and structural context in UAV-acquired power-line images, an enhanced lightweight YOLOv8n-based framework for power-line defect detection is developed. First, a content-adaptive downsampling (CAD) module is developed to predict input-dependent sampling offsets and normalized aggregation weights and to perform differentiable resampling. Combined with local-global interactive depthwise separable convolution, CAD improves the preservation of small-object details while maintaining relatively low computational complexity. Second, a dynamic subspace gated exchange (DSGE) module is proposed to adaptively partition features into a high-frequency detail subspace and a low-frequency structural subspace according to the input content. Heterogeneous branches and bidirectional gated exchange are then employed to jointly model fine-grained details and structural context. In addition, the lightweight mixed local channel attention (MLCA) mechanism is incorporated in the detection head as an auxiliary feature-enhancement component. Experimental results show that the proposed model achieves mAP@0.50 and mAP@0.50:0.95 values of 92.3% and 62.9%, respectively, outperforming the compared models under the current evaluation protocol. With 1.90 M parameters and 5.6 G FLOPs, the model reaches an inference speed of 134.7 FPS on the desktop GPU platform, demonstrating that content-adaptive sampling and dynamic detail–structure interaction can improve small-defect detection and complex-background suppression while maintaining relatively low model complexity.
- Open Access
- 7 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (7) , 414
NLOS-Aware LiDAR–UWB Fusion Localization for UAV Inspection in Converter Valve Halls
To address unavailable global navigation satellite system (GNSS) signals, dense metallic equipment, valve-tower occlusion, and the insufficient robustness of single-sensor localization in unmanned aerial vehicle (UAV) inspection of converter valve halls, this paper proposes a non-line-of-sight (NLOS)-aware LiDAR-ultra-wideband (UWB) fusion localization method. The method uses LiDAR odometry to provide continuous local motion constraints and UWB ranging to provide global distance constraints. The geometric relationship among the UAV, UWB anchors, and valve-hall obstacles is used to evaluate the NLOS risk of each UWB link, and the equivalent ranging variance is adaptively adjusted before tight fusion optimization. To avoid overextending simulation conclusions, this study focuses on localization-layer modeling and simulation-based validation rather than full energized valve-hall flight deployment. In the grouped-bushing valve-hall scenario, the proposed method achieves an RMSE of 0.30 m, a mean error of 0.29 m, a P95 error of 0.43 m, and a maximum error of 0.48 m, reducing the RMSE by 50.0% compared with ordinary tight LiDAR-UWB fusion. Additional Monte Carlo tests under different trajectories, anchor layouts, anchor installation errors, and obstacle densities further verify the robustness of the proposed weighting mechanism. The results indicate that the method can suppress LiDAR accumulated drift and reduce the influence of UWB NLOS ranging in GNSS-denied metallic indoor environments, while real converter-valve-hall flight tests under energized electromagnetic conditions remain necessary before engineering deployment.
- 7 July 2026
- Published by MDPI AG in Technologies
- Vol. 14 (7) , 414
Open AccessNLOS-Aware LiDAR–UWB Fusion Localization for UAV Inspection in Converter Valve Halls
To address unavailable global navigation satellite system (GNSS) signals, dense metallic equipment, valve-tower occlusion, and the insufficient robustness of single-sensor localization in unmanned aerial vehicle (UAV) inspection of converter valve halls, this paper proposes a non-line-of-sight (NLOS)-aware LiDAR-ultra-wideband (UWB) fusion localization method. The method uses LiDAR odometry to provide continuous local motion constraints and UWB ranging to provide global distance constraints. The geometric relationship among the UAV, UWB anchors, and valve-hall obstacles is used to evaluate the NLOS risk of each UWB link, and the equivalent ranging variance is adaptively adjusted before tight fusion optimization. To avoid overextending simulation conclusions, this study focuses on localization-layer modeling and simulation-based validation rather than full energized valve-hall flight deployment. In the grouped-bushing valve-hall scenario, the proposed method achieves an RMSE of 0.30 m, a mean error of 0.29 m, a P95 error of 0.43 m, and a maximum error of 0.48 m, reducing the RMSE by 50.0% compared with ordinary tight LiDAR-UWB fusion. Additional Monte Carlo tests under different trajectories, anchor layouts, anchor installation errors, and obstacle densities further verify the robustness of the proposed weighting mechanism. The results indicate that the method can suppress LiDAR accumulated drift and reduce the influence of UWB NLOS ranging in GNSS-denied metallic indoor environments, while real converter-valve-hall flight tests under energized electromagnetic conditions remain necessary before engineering deployment.
- Open Access
Closed-Loop 3D Path Planning and Local Replanning for UAV Inspection in GIS Rooms
To address the problems of closed-loop task organization, strong corridor constraints, and path failure after local disturbances in unmanned aerial vehicle (UAV) inspection of gas-insulated switchgear (GIS) rooms, this paper proposes a topology-and-corridor-guided bias-suppressed D* (TCG-BS-D*) method for closed-loop three-dimensional (3D) path planning and local replanning. The proposed method constructs a structured guidance model based on the inspection-corridor topology, generates local 3D path segments according to a predetermined inspection sequence, and forms a nominal closed-loop inspection path through bias suppression and path regularization. Meanwhile, for local maintenance blockage and dynamic disturbance scenarios, an alternative local replanning strategy is applied to the affected path segments. Simulation results show that, under the static closed-loop inspection condition, the proposed method achieves a total path length of 700.22 m, a total inspection time of 269.32 s, an average safety clearance of 8.18 m, 37 large-angle turns, a corridor adherence rate of 80.73%, and a task completion rate of 100%, showing superior performance in inspection efficiency, safety margin, trajectory regularity, and corridor consistency. Under the local blockage condition, the replanned path introduces path-length and time increments of 71.29 m and 25.88 s, respectively, while maintaining the minimum safety clearance at 1.52 m and increasing the corridor adherence rate to 83.91%. Under dynamic disturbance conditions, the minimum dynamic safety clearance is improved from −2.71 m to 17.84 m, effectively eliminating the local dynamic collision risk. The results demonstrate that the proposed method can balance closed-loop path-generation efficiency, corridor-structure consistency, safety margin, and adaptability to local disturbances, providing an effective solution for UAV inspection path planning in GIS rooms.
Open AccessClosed-Loop 3D Path Planning and Local Replanning for UAV Inspection in GIS Rooms
To address the problems of closed-loop task organization, strong corridor constraints, and path failure after local disturbances in unmanned aerial vehicle (UAV) inspection of gas-insulated switchgear (GIS) rooms, this paper proposes a topology-and-corridor-guided bias-suppressed D* (TCG-BS-D*) method for closed-loop three-dimensional (3D) path planning and local replanning. The proposed method constructs a structured guidance model based on the inspection-corridor topology, generates local 3D path segments according to a predetermined inspection sequence, and forms a nominal closed-loop inspection path through bias suppression and path regularization. Meanwhile, for local maintenance blockage and dynamic disturbance scenarios, an alternative local replanning strategy is applied to the affected path segments. Simulation results show that, under the static closed-loop inspection condition, the proposed method achieves a total path length of 700.22 m, a total inspection time of 269.32 s, an average safety clearance of 8.18 m, 37 large-angle turns, a corridor adherence rate of 80.73%, and a task completion rate of 100%, showing superior performance in inspection efficiency, safety margin, trajectory regularity, and corridor consistency. Under the local blockage condition, the replanned path introduces path-length and time increments of 71.29 m and 25.88 s, respectively, while maintaining the minimum safety clearance at 1.52 m and increasing the corridor adherence rate to 83.91%. Under dynamic disturbance conditions, the minimum dynamic safety clearance is improved from −2.71 m to 17.84 m, effectively eliminating the local dynamic collision risk. The results demonstrate that the proposed method can balance closed-loop path-generation efficiency, corridor-structure consistency, safety margin, and adaptability to local disturbances, providing an effective solution for UAV inspection path planning in GIS rooms.
- Open Access
- 12 June 2026
- Published by MDPI AG in Technologies
- Vol. 14 (6) , 355
Weather-Aware Asynchronous Vehicle–UAV Cooperative Scheduling for Distribution Network Inspection via Bi-Level MODDPG–NSGA-II Optimization
Extreme weather conditions impose significant challenges on distribution network inspection because UAV flight safety, energy consumption, vehicle mobility, and task coverage are strongly coupled under wind disturbances. To improve inspection efficiency and operational robustness, this paper proposes a weather-aware asynchronous vehicle–UAV cooperative scheduling method based on bi-level MODDPG–NSGA-II optimization. First, a dynamic wind field model and a wind-sensitive UAV energy model are established to describe the effects of background wind, vertical wind shear, and local gust disturbances on UAV motion and state-of-charge evolution. Then, an asynchronous vehicle–UAV collaboration mechanism is developed, allowing the vehicle to move toward downstream parking sites after UAV deployment while UAVs perform inspection and cross-site recovery under rendezvous and energy safety constraints. On this basis, a bi-level optimization framework is constructed, in which NSGA-II searches global coordination parameters and MODDPG learns adaptive multi-UAV scheduling policies in continuous decision spaces. Controlled wind-factor experiments show that, with the task scale fixed at 52 inspection tasks, the proposed method maintains 100% task coverage under 0–10 m/s wind conditions. As the reference wind speed increases from 0 m/s to 10 m/s, the mission completion time increases from 40.97 min to 70.24 min, while the minimum residual SOC decreases from 50.32% to 13.82%, which remains above the predefined safety threshold. Repeated stochastic trials and statistical significance analysis further indicate that the proposed method achieves shorter mission time and more stable task coverage than representative baselines under the same experimental conditions. The scope of this study is simulation-level validation; real-world flight tests and hardware-in-the-loop verification will be further investigated in future work.
- 12 June 2026
- Published by MDPI AG in Technologies
- Vol. 14 (6) , 355
Open AccessWeather-Aware Asynchronous Vehicle–UAV Cooperative Scheduling for Distribution Network Inspection via Bi-Level MODDPG–NSGA-II Optimization
Extreme weather conditions impose significant challenges on distribution network inspection because UAV flight safety, energy consumption, vehicle mobility, and task coverage are strongly coupled under wind disturbances. To improve inspection efficiency and operational robustness, this paper proposes a weather-aware asynchronous vehicle–UAV cooperative scheduling method based on bi-level MODDPG–NSGA-II optimization. First, a dynamic wind field model and a wind-sensitive UAV energy model are established to describe the effects of background wind, vertical wind shear, and local gust disturbances on UAV motion and state-of-charge evolution. Then, an asynchronous vehicle–UAV collaboration mechanism is developed, allowing the vehicle to move toward downstream parking sites after UAV deployment while UAVs perform inspection and cross-site recovery under rendezvous and energy safety constraints. On this basis, a bi-level optimization framework is constructed, in which NSGA-II searches global coordination parameters and MODDPG learns adaptive multi-UAV scheduling policies in continuous decision spaces. Controlled wind-factor experiments show that, with the task scale fixed at 52 inspection tasks, the proposed method maintains 100% task coverage under 0–10 m/s wind conditions. As the reference wind speed increases from 0 m/s to 10 m/s, the mission completion time increases from 40.97 min to 70.24 min, while the minimum residual SOC decreases from 50.32% to 13.82%, which remains above the predefined safety threshold. Repeated stochastic trials and statistical significance analysis further indicate that the proposed method achieves shorter mission time and more stable task coverage than representative baselines under the same experimental conditions. The scope of this study is simulation-level validation; real-world flight tests and hardware-in-the-loop verification will be further investigated in future work.
- Open Access
Multi-Objective Task Scheduling for Vehicle–UAV Synchronous Cooperative Distribution Network Inspection
To address the challenges of significant vehicle parking constraints, limited UAV endurance, and insufficient multi-task coordination efficiency in distribution network inspection, this paper proposes a vehicle–UAV synchronous cooperative inspection task scheduling method based on multi-objective twin delayed deep deterministic policy gradient and nondominated sorting genetic algorithm II (MOTD3-NSGA-II). First, a vehicle–UAV synchronous cooperative inspection model is established by considering staged vehicle repositioning, same-site UAV launch, landing, and retrieval, as well as state-of-charge constraints. On this basis, a multi-objective optimization model is formulated with task coverage, mission completion time, minimum residual state of charge, and load balance as objectives. Then, a bi-level closed-loop solution framework is developed, in which NSGA-II is employed to optimize cooperative parameters and objective preference weights, while the inner-layer MOTD3 learns UAV scheduling policies in a continuous action space. Finally, the proposed method is validated in four simulation scenarios with different task scales and spatial distribution characteristics. The results show that 100% task coverage is achieved in all four scenarios, with mission completion times of 11,109 s, 9693 s, 10,538 s, and 10,721 s, respectively, while the minimum residual state of charge is maintained within 0.28–0.36. The results demonstrate that the proposed method can balance inspection completeness, execution efficiency, energy safety, and cooperative stability, providing a useful reference for intelligent task scheduling in vehicle–UAV cooperative distribution network inspection.
Open AccessMulti-Objective Task Scheduling for Vehicle–UAV Synchronous Cooperative Distribution Network Inspection
To address the challenges of significant vehicle parking constraints, limited UAV endurance, and insufficient multi-task coordination efficiency in distribution network inspection, this paper proposes a vehicle–UAV synchronous cooperative inspection task scheduling method based on multi-objective twin delayed deep deterministic policy gradient and nondominated sorting genetic algorithm II (MOTD3-NSGA-II). First, a vehicle–UAV synchronous cooperative inspection model is established by considering staged vehicle repositioning, same-site UAV launch, landing, and retrieval, as well as state-of-charge constraints. On this basis, a multi-objective optimization model is formulated with task coverage, mission completion time, minimum residual state of charge, and load balance as objectives. Then, a bi-level closed-loop solution framework is developed, in which NSGA-II is employed to optimize cooperative parameters and objective preference weights, while the inner-layer MOTD3 learns UAV scheduling policies in a continuous action space. Finally, the proposed method is validated in four simulation scenarios with different task scales and spatial distribution characteristics. The results show that 100% task coverage is achieved in all four scenarios, with mission completion times of 11,109 s, 9693 s, 10,538 s, and 10,721 s, respectively, while the minimum residual state of charge is maintained within 0.28–0.36. The results demonstrate that the proposed method can balance inspection completeness, execution efficiency, energy safety, and cooperative stability, providing a useful reference for intelligent task scheduling in vehicle–UAV cooperative distribution network inspection.
- Open Access
- 6 May 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 283
Data-Driven Evolutionary Resource Allocation for Vehicle–UAV Collaborative Inspection with Path-Scheduling Feedback
To address the challenges of strong coupling between resource allocation and collaborative scheduling in vehicle–UAV cooperative inspections of power distribution lines, as well as the difficulty in balancing efficiency and stability, this paper proposes a path-scheduling feedback-based evolutionary cooperative optimization method. First, an integrated modeling framework for resource allocation and execution scheduling is constructed, incorporating vehicle path decisions and drone task scheduling into a unified optimization space. Next, a feedback-driven two-layer multi-objective evolutionary collaborative optimization algorithm (FB-MOC2) is introduced. The outer layer performs evolutionary search for adaptive resource allocation, while the inner layer solves path planning and collaborative scheduling, with dynamic resource adjustments achieved through execution-layer feedback, forming a data-driven adaptive optimization process. Subsequently, sensitivity analysis is conducted on resource deployment mechanisms, revealing phased evolutionary patterns between resource scale and system performance, and identifying the effective operational range for resource allocation. Finally, the algorithm’s robustness is validated under multiple failure scenarios. Simulation results demonstrate that the proposed method reduces total operation time from 412 min to 315 min, improves battery utilization to 78.5%, and maintains recovery costs within 1.65 times the baseline even under high drone failure rates, while ensuring full inspection coverage. This approach provides an effective bio-inspired and data-driven solution for adaptive resource allocation and robust scheduling in intelligent power distribution line inspections.
- 6 May 2026
- Published by MDPI AG in Technologies
- Vol. 14 (5) , 283
Open AccessData-Driven Evolutionary Resource Allocation for Vehicle–UAV Collaborative Inspection with Path-Scheduling Feedback
To address the challenges of strong coupling between resource allocation and collaborative scheduling in vehicle–UAV cooperative inspections of power distribution lines, as well as the difficulty in balancing efficiency and stability, this paper proposes a path-scheduling feedback-based evolutionary cooperative optimization method. First, an integrated modeling framework for resource allocation and execution scheduling is constructed, incorporating vehicle path decisions and drone task scheduling into a unified optimization space. Next, a feedback-driven two-layer multi-objective evolutionary collaborative optimization algorithm (FB-MOC2) is introduced. The outer layer performs evolutionary search for adaptive resource allocation, while the inner layer solves path planning and collaborative scheduling, with dynamic resource adjustments achieved through execution-layer feedback, forming a data-driven adaptive optimization process. Subsequently, sensitivity analysis is conducted on resource deployment mechanisms, revealing phased evolutionary patterns between resource scale and system performance, and identifying the effective operational range for resource allocation. Finally, the algorithm’s robustness is validated under multiple failure scenarios. Simulation results demonstrate that the proposed method reduces total operation time from 412 min to 315 min, improves battery utilization to 78.5%, and maintains recovery costs within 1.65 times the baseline even under high drone failure rates, while ensuring full inspection coverage. This approach provides an effective bio-inspired and data-driven solution for adaptive resource allocation and robust scheduling in intelligent power distribution line inspections.
- Open Access
- 28 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (9) , 1866
Electromagnetic Risk-Aware MPPI-Based 3D Path Planning for UAV Inspection in Converter Valve Halls
To address the challenges of insufficient safety, poor trajectory executability, and low stability of online optimization in UAV inspection path planning for converter valve halls under conditions of dense obstacles, narrow passages, and complex electromagnetic environments, an electromagnetic risk-aware three-dimensional path planning method based on model predictive path integral (MPPI) is proposed. Considering the typical “valve-tower array–bushing” layout in converter valve halls, a three-dimensional obstacle model consisting of prismatic valve towers and cylindrical bushings is established. A comprehensive cost function is then constructed by jointly incorporating path length, safety clearance, trajectory smoothness, and electromagnetic risk. On this basis, an electromagnetic risk term, a corridor guidance term, and a control increment regularization term are integrated into the MPPI receding-horizon optimization framework to enable online generation of inspection trajectories. Simulation results demonstrate that, compared with A*, Vanilla MPPI, and Corridor MPPI, the proposed method generates smoother and safer trajectories and achieves superior overall performance in terms of total cost, minimum clearance, success rate, and mean tracking error. The proposed method provides an effective solution for intelligent UAV inspection path planning in converter valve halls.
- 28 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (9) , 1866
Open AccessElectromagnetic Risk-Aware MPPI-Based 3D Path Planning for UAV Inspection in Converter Valve Halls
To address the challenges of insufficient safety, poor trajectory executability, and low stability of online optimization in UAV inspection path planning for converter valve halls under conditions of dense obstacles, narrow passages, and complex electromagnetic environments, an electromagnetic risk-aware three-dimensional path planning method based on model predictive path integral (MPPI) is proposed. Considering the typical “valve-tower array–bushing” layout in converter valve halls, a three-dimensional obstacle model consisting of prismatic valve towers and cylindrical bushings is established. A comprehensive cost function is then constructed by jointly incorporating path length, safety clearance, trajectory smoothness, and electromagnetic risk. On this basis, an electromagnetic risk term, a corridor guidance term, and a control increment regularization term are integrated into the MPPI receding-horizon optimization framework to enable online generation of inspection trajectories. Simulation results demonstrate that, compared with A*, Vanilla MPPI, and Corridor MPPI, the proposed method generates smoother and safer trajectories and achieves superior overall performance in terms of total cost, minimum clearance, success rate, and mean tracking error. The proposed method provides an effective solution for intelligent UAV inspection path planning in converter valve halls.
- Open Access
Lightweight Power Line Defect Detection Based on Improved YOLOv8n
To address the challenges of small targets, severe background clutter, and high deployment cost in UAV-based power-line defect detection, this paper proposes a lightweight defect detection model based on an improved YOLOv8n. In the downsampling stage, we design an improved lightweight adaptive downsampling module (ADownPro) to replace part of conventional convolutions, which uses a dual-branch parallel structure for stronger feature interaction and depthwise separable convolutions (DSConv) for complexity reduction. In the feature extraction stage, an integration of cross-stage partial connections and partial convolution (CSPPC) is proposed to replace the C2F module for efficient multi-scale feature fusion. In the detection head, mixed local channel attention (MLCA), which combines channel-spatial information and local–global contextual features, is introduced to strengthen defect-focused representations under complex backgrounds. For the loss function, a scale-annealed mixed-quality EIoU loss (SAMQ-EIoU) is proposed by combining iso-center scale transformation, scale factor annealing and focal-style quality reweighting to improve localization accuracy at high IoU thresholds. Experiments on a constructed dataset covering six typical defect categories show that the improved YOLOv8n achieves 91.4% mAP@0.50 and 64.5% mAP@0.50:0.95, with only 1.59 M parameters and 4.9 GFLOPs. Compared with mainstream detectors, the proposed model achieves a better balance between detection accuracy and lightweight design. In particular, compared with the recently proposed YOLOv8n-DSN and IDD-YOLO, it improves mAP@0.50 by 0.6% and 0.8%, and mAP@0.50:0.95 by 1.2% and 4.8%, respectively, while further reducing the parameter count by 1.00 M and 1.26 M, and the FLOPs by 1.7 G and 0.2 G. Moreover, the cross-dataset evaluation on the public UPID and SFID datasets further demonstrate the robustness and generalization ability of the proposed method.
Open AccessLightweight Power Line Defect Detection Based on Improved YOLOv8n
To address the challenges of small targets, severe background clutter, and high deployment cost in UAV-based power-line defect detection, this paper proposes a lightweight defect detection model based on an improved YOLOv8n. In the downsampling stage, we design an improved lightweight adaptive downsampling module (ADownPro) to replace part of conventional convolutions, which uses a dual-branch parallel structure for stronger feature interaction and depthwise separable convolutions (DSConv) for complexity reduction. In the feature extraction stage, an integration of cross-stage partial connections and partial convolution (CSPPC) is proposed to replace the C2F module for efficient multi-scale feature fusion. In the detection head, mixed local channel attention (MLCA), which combines channel-spatial information and local–global contextual features, is introduced to strengthen defect-focused representations under complex backgrounds. For the loss function, a scale-annealed mixed-quality EIoU loss (SAMQ-EIoU) is proposed by combining iso-center scale transformation, scale factor annealing and focal-style quality reweighting to improve localization accuracy at high IoU thresholds. Experiments on a constructed dataset covering six typical defect categories show that the improved YOLOv8n achieves 91.4% mAP@0.50 and 64.5% mAP@0.50:0.95, with only 1.59 M parameters and 4.9 GFLOPs. Compared with mainstream detectors, the proposed model achieves a better balance between detection accuracy and lightweight design. In particular, compared with the recently proposed YOLOv8n-DSN and IDD-YOLO, it improves mAP@0.50 by 0.6% and 0.8%, and mAP@0.50:0.95 by 1.2% and 4.8%, respectively, while further reducing the parameter count by 1.00 M and 1.26 M, and the FLOPs by 1.7 G and 0.2 G. Moreover, the cross-dataset evaluation on the public UPID and SFID datasets further demonstrate the robustness and generalization ability of the proposed method.
- Open Access
- 6 February 2026
- Published by Wiley
Optimal Design of Path Planning and Battery Resource Allocation under a Vehicle--UAV Collaborative Mode
To address the efficiency limitations of vehicle--UAV collaborative operations in large-scale, high-frequency inspections of flexible DC transmission lines, this paper proposes a path--energy coordinated bi-level nested optimization framework, targeting the inherent strong coupling among vehicle path planning, UAV task scheduling, and battery resource allocation. First, a unified multi-objective constrained optimization model is formulated at the system level, integrating vehicle parking decisions, UAV operational radius, and path-dependent energy consumption into a single decision framework to characterize the intrinsic coupling between routing and energy allocation. Second, a dual-layer collaborative optimization structure is developed, where closed-loop interaction between outer-layer routing decisions and inner-layer energy scheduling enables the co-evolution and joint convergence of vehicle paths, UAV task assignments, and battery resource distribution. A path-feature-based UAV energy demand prediction mechanism is further incorporated to enhance the foresight and feasibility of energy scheduling. Finally, simulation studies based on representative flexible DC transmission line scenarios are conducted. The results demonstrate that the proposed framework consistently outperforms existing decoupled or partially coupled optimization strategies in system-level metrics, including total operation time, vehicle travel distance, and battery utilization efficiency, while exhibiting robust performance and practical deployability under expanded inspection scales and varying UAV endurance conditions.
- 6 February 2026
- Published by Wiley
Open AccessOptimal Design of Path Planning and Battery Resource Allocation under a Vehicle--UAV Collaborative Mode
To address the efficiency limitations of vehicle--UAV collaborative operations in large-scale, high-frequency inspections of flexible DC transmission lines, this paper proposes a path--energy coordinated bi-level nested optimization framework, targeting the inherent strong coupling among vehicle path planning, UAV task scheduling, and battery resource allocation. First, a unified multi-objective constrained optimization model is formulated at the system level, integrating vehicle parking decisions, UAV operational radius, and path-dependent energy consumption into a single decision framework to characterize the intrinsic coupling between routing and energy allocation. Second, a dual-layer collaborative optimization structure is developed, where closed-loop interaction between outer-layer routing decisions and inner-layer energy scheduling enables the co-evolution and joint convergence of vehicle paths, UAV task assignments, and battery resource distribution. A path-feature-based UAV energy demand prediction mechanism is further incorporated to enhance the foresight and feasibility of energy scheduling. Finally, simulation studies based on representative flexible DC transmission line scenarios are conducted. The results demonstrate that the proposed framework consistently outperforms existing decoupled or partially coupled optimization strategies in system-level metrics, including total operation time, vehicle travel distance, and battery utilization efficiency, while exhibiting robust performance and practical deployability under expanded inspection scales and varying UAV endurance conditions.