Search Results (174)

Multi-view point cloud registration is a fundamental technology for 3D reconstruction and indoor robot navigation and remains a core challenge for robust environmental perception. Its key difficulty lies in achieving globally consistent alignment of multiple partially overlapping point clouds efficiently and reliably. To address the limitations of existing methods, including low registration accuracy under small overlaps, severe error accumulation in long sequences, and the difficulty of balancing computational efficiency with global consistency, this paper proposes a multi-view point cloud registration framework that integrates spanning tree-based global topology constraints with a multi-scale pyramid-based local refinement strategy, specifically validated for indoor environments. First, a Voxel-Guided Normal Consistency Keypoint Extraction (VG-NCKE) method is presented. It leverages voxel grids to guide stable computation of local geometric features and filters candidate keypoints using a neighborhood normal direction consistency metric, effectively improving keypoint repeatability and spatial uniformity on unevenly distributed point clouds. Second, a coarse registration strategy with global constraints is constructed based on the Overlap Confidence-weighted Minimum Spanning Tree (OC-WST). It quantifies inter-frame overlap reliability as edge weights and employs Prim’s algorithm to build the minimum spanning tree as the topological skeleton for global registration. By prioritizing high-overlap frame pairs, the method suppresses error propagation and reduces the complexity of multi-view registration. Additionally, a multi-scale pyramid ICP fine registration algorithm is designed. It adopts a point-to-plane error model instead of the traditional point-to-point distance metric and performs progressive optimization through a three-layer point cloud pyramid from coarse to fine. This expands the convergence basin and gradually improves alignment accuracy, mitigating the sensitivity of single-scale ICP to initial poses. Extensive experiments on the indoor 3DMatch dataset and real indoor LiDAR sequences demonstrate that the proposed method outperforms competing approaches in terms of registration accuracy, computational efficiency, and long-sequence robustness, validating its effectiveness for indoor multi-view point cloud registration tasks. Full article

The rapid expansion of Unmanned Aircraft Systems (UAS) operations has created an urgent need for scalable strategic conflict resolution methods within the U-space framework. When requested 4D flight plans overlap with previously authorised ones, the Flight Authorisation Service denies the request and can provide the UAS operator with an alternative, conflict-free route. While traditional pathfinding algorithms ensure optimal routes, their computational cost creates a critical bottleneck during the flight activation phase or emergency missions, which demand near-instantaneous responses. To address this, we propose a three-stage framework. First, an Octree spatial partitioning discretises the airspace to identify occupied cells. Second, both A* and JPS algorithms are implemented to establish an optimal reference route. Finally, a standard Deep Reinforcement Learning (DRL) model, trained on realistic PX4 Simulator trajectories and using a well-adjusted reward function, generates alternative paths that optimise distance and energy. Results demonstrate that this DRL architecture achieves near-optimal routing behaviour. Crucially, it reduces computation time by several orders of magnitude compared to traditional algorithms, solving complex conflicts in milliseconds rather than seconds. We conclude that simple, well-tuned DRL architectures overcome latency limitations of classical pathfinding while achieving optimal results, ensuring rapid, safe, and efficient conflict resolution for high-density U-space. Full article

The rapid expansion of Unmanned Aircraft System (UAS) operations has created an urgent need for scalable strategic conflict resolution methods within the U-space framework. When requested 4D flight plans overlap with previously authorised ones, the Flight Authorisation Service (FAS) denies the request, and can provide the UAS operator with an alternative route, free of conflict. This work introduces a Machine Learning-based tool designed to support this process, which consists of three sequential phases. First, an Octree spatial partitioning technique is proposed, discretising the airspace, further identifying the previously occupied cells and visualising the occupied airspace, so that the UAS operator can manually find an alternative route. Then, the widely known A* pathfinding algorithm is implemented in this discretized airspace, allowing the shortest or most optimal conflict-free alternative route. Finally, the methodology integrates a Machine Learning (Reinforcement Learning) model, created from scratch and trained with realistic flight trajectories from a PX4 Simulator, to further optimise flight paths, explicitly accounting for operational constraints such as distance and battery consumption. In this work, both methods are compared, addressing traditional algorithms limitations with Machine Learning (ML) techniques, showing that a near-optimal behaviour can be achieved with the ML approach, at a fraction of the computation time needed. Full article

Neural implicit surface representations have yielded impressive results in 3D reconstruction, yet existing methods tend to introduce noise in smooth regions or fail to capture fine details in complex areas, primarily due to a lack of explicit spatial structure modeling. To address these limitations, we propose a geometry-adaptive surface reconstruction method based on Morton codes. By mapping 3D space onto octree traversal paths, this approach provides a natural spatial structural prior for the reconstruction process. For each query point, an implicit octree generates a unique root-to-leaf trajectory, yielding spatially adaptive weights that modulate multi-resolution geometric features. Specifically, low-frequency coarse features dominate in flat regions to suppress noise, whereas high-frequency fine features are activated in edge-rich areas to recover intricate geometry. Experimental results demonstrate competitive performance across multiple datasets, particularly in reconstructing sharp features and fine-grained geometric details. Full article

Three-dimensional (3D) orebody boundary modeling primarily relies on spatial interpolation methods, such as radial basis functions (RBFs). However, these methods struggle with large datasets and require gradient or normal constraints for stable geometric extrapolation. This study proposes an adaptive finite difference implicit-modeling method, which avoids gradient information and can handle complex 3D orebody boundaries from large-scale, irregular datasets. We utilized difference operators for hanging and constrained octree nodes and applied adaptive density-based smoothing to reduce artifacts from sparse data, enabling complex boundary construction on nearly one million non-uniform control points. We used octree-based convolutional neural networks to fuse spatial features across octree levels, merging points with similar local geometries into the same finest-level cells. This enabled optimal adaptive octree mesh partitioning that accounts for spatial similarity among control points while controlling the total mesh count. Using this adaptive octree mesh, a finite difference scheme suitable for non-uniform mesh structures was constructed. The method outperforms traditional RBFs and uniform-grid finite difference methods in model accuracy, computational efficiency, and memory usage, exhibiting a robust performance across various data distribution patterns. Full article

In this work we propose a new strategy for the optimization of the flap position of a high-lift configuration in the framework of a hybrid electric regional aircraft. The approach is based on the multidisciplinary design optimization software GEMSEO and the high-performance CFD solver CODA. The CFD solver CODA solves the RANS equations on a body-fitted mesh along with immersed boundary methods, while the package GEMSEO employs the COBYQA optimization algorithm. The main airfoil is meshed in a body-fitted fashion, and a refined region is created just where the flap can be located. The employment of immersed boundary methods allows us to arbitrarily change the deflection angle and leading edge position of the flap inside this refined region without the need of remeshing the whole computational domain. The main advantage of this methodology with respect to a full body-fitted mesh scheme is the computational efficiency when hundreds or thousands of CFD-RANS simulations are required by the optimizer. We demonstrate the effectiveness of this optimization methodology in the computation of the optimal configuration of the flap during takeoff and landing phases of a high-lift airfoil. Full article

Self-contained local forecasting of wind and solar series can improve operational planning of wind farms and photovoltaic (PV) plant day-cycles in addition to numerical models, which are mostly behind time due to high simulation costs. Unstable electricity production requires balancing the availability of renewable energy (RE) with unpredictable user consumption to achieve effective usage. Artificial intelligence (AI) predictive modelling can minimise the intermittent uncertainty in wind and solar resources by trying to eliminate specific problems in RE-detached system reliability and optimal utilisation. The proposed 24 h day-training and prediction scheme comprises the starting detection and the following similarity re-assessment of sampling day-series intervals. Two-point professional weather stations record standard meteorological variables, of which the most relevant are selected as optimal model inputs. Automatic two-layer altitude observation captures key relationships between hill- and lowland-level data, which comply with pattern progress. New biologically inspired differential learning (DfL) is designed and developed to integrate adaptive neurocomputing (evolving node tree components) with customised numerical procedures of operator calculus (OC) based on derivative transforms. DfL enables the representation of uncertain dynamics related to local weather patterns. Angular and frequency data (wind azimuth, temperature, irradiation) are processed together with the amplitudes to solve simple 2-variable partial differential equations (PDEs) in binomial nodes. Differentiated data provide the fruitful information necessary to model upcoming changes in mid-term day horizons. Additional PDE components in periodic form improve the modelling of hidden complex patterns in cycle data. The DfL efficiency was proved in statistical experiments, compared to a variety of elaborated AI techniques, enhanced by selective difference input preprocessing. Successful LSTM-deep and stochastic tree learning shows little inferior model performances, notably in day-ahead estimation of chaotic 24 h wind series, and slightly better approximation of alterative 8 h solar cycles. Free parametric C++ software with the applied archive data is available for additional comparative and reproducible experiments. Full article

The N-body problem is a classic problem involving a system of N discrete bodies mutually interacting in a dynamical system. At any moment in time there are $N(N-1)/2$ such interactions occurring. This $N^2$ scaling leads to computational difficulties where simulations range from tens of thousands of bodies to billions or trillions. Approximation algorithms, such as the famous Barnes–Hut algorithm, simplify the number of interactions to scale as $NlogN$. Even still, this improvement in complexity is insufficient to achieve the desired performance for very large simulations on computing clusters with many nodes and many cores. In this work we explore a variety of algorithmic techniques for parallel and distributed variations on the Barnes–Hut algorithm to improve parallelism and reduce inter-process communication requirements. This includes the costzones and hashed octree techniques. We implement these techniques in a gravitational N-body simulation and show that they can be applied to both a parallel and distributed context. This work collects and unifies over 30 years of research, while filling in missing details, to provide a comprehensive and reproducible source. Full article

Accurate prediction of transient melt pool thermal fields in Laser Powder Bed Fusion (LPBF) is essential for understanding melt pool geometry and defect formation mechanisms, yet conventional finite element methods (FEM) impose prohibitive computational costs for parametric process exploration. A variational physics-informed neural network (VPINN) framework is presented for 3D transient thermal modeling of a GH3536 single-track LPBF scan. The framework incorporates a continuously differentiable Goldak double-ellipsoid moving heat source, temperature-dependent thermophysical property surrogates, and an effective heat-capacity treatment of latent heat associated with solid–liquid phase change and vaporization. These components are embedded in a weak-form residual-minimization scheme with octree-adaptive domain decomposition, hierarchical Legendre test functions, and sequential sliding-window time marching. Effective absorptivity is inferred jointly with the network parameters, using sparse experimental melt pool profiles as supervision. Within a parametric study covering laser powers from 100 to 140 W and scan speeds from 1000 to 1500 mm/s, the predicted melt pool width, depth, and aspect ratio agree closely with FEM benchmarks and cross-sectional optical micrograph measurements across both supervised and held-out interpolation conditions, with total relative L₂ nodal temperature errors ranging from 3.23% to 6.75%. Following a one-time offline training investment of 15,323 s that simultaneously resolves the full parametric space, surrogate inference reduces per-condition query time from 3000–4000 s (FEM) to merely 4–5 s, delivering a speedup of two to three orders of magnitude and making the framework increasingly cost-effective for high-throughput parametric studies and digital-twin integration as the number of queried conditions grows. Full article

While deep learning-based visual SLAM (VSLAM) has achieved remarkable localization accuracy, its high computational cost and latency remain critical bottlenecks for real-time deployment. To address these limitations, this paper presents NeuroFusion-SLAM, a novel multi-sensor fusion framework tailored for both efficiency and robustness. By incorporating depthwise separable convolution, the framework cuts down model parameters by approximately 40% and training time by 49% while preserving localization accuracy, thus boosting real-time inference performance and computational efficiency in large-scale environments. Furthermore, a global edge optimization strategy is proposed by integrating sliding window optimization with a factor graph framework, which effectively improves the global consistency of the system. Extensive experiments on the TUM-VI and KITTI-360 datasets demonstrate that our system achieves real-time performance with an average latency of 30.4 ms per frame. It runs 3× faster than ORB-SLAM2 and 4× faster than VINS-Mono, while maintaining good localization accuracy. Full article

Seafloor massive sulfide (SMS) deposits formed by hydrothermal circulation generate measurable self-potential (SP) anomalies in seawater, providing an effective geophysical indicator of sulfide mineralization. In this study, a remotely operated vehicle (ROV)-borne SP survey was conducted at the Yuhuang hydrothermal field on the Southwest Indian Ridge to investigate the spatial distribution of SMS mineralization. The survey operated at a near-bottom altitude of approximately 10 m, substantially lower than that typically achieved by autonomous underwater vehicles (AUVs) or towed systems, enabling high-resolution data acquisition with improved signal quality. To efficiently discretize complex seafloor topography under irregular data coverage, an adaptive octree mesh was employed, enabling computationally efficient three-dimensional inversion over a large survey area and recovery of the subsurface source current density distribution. The inversion results resolve a main anomaly zone spatially correlated with known SMS mineralization, as well as an additional anomaly zone that was not resolved by previous surveys and suggests potential mineralization. Anomalies associated with known mineralization show good spatial agreement with independent near-bottom observations and drilling results. The results demonstrate that ROV-borne SP surveying combined with adaptive meshing and three-dimensional inversion provides a reliable approach for imaging SMS mineralization in deep-sea environments. Full article

Low solution accuracy and efficiency are two bottleneck problems in the existing models and methodologies for spatial distance calculations to verify the minimal electrical clearance of overhead transmission lines if a dynamic windage yaw is considered. To address these two issues, the accurate numerical models and the corresponding efficient solution methodologies tailored for different scenarios are proposed. First, a conductor windage yaw surface model incorporating a horizontal specific load coefficient is established, transforming the wire-to-wire minimal distance determination into a multi-dimensional nonlinear constrained optimization problem. An improved gradient-guided crossover genetic algorithm (GGA) is subsequently developed to solve this optimization problem. By integrating the gradient information to guide the crossover operator and combining an adaptive mutation with a dimension mutation strategy, the solution efficiency is enhanced. For the wire-to-tower minimal distance determination, a simplified tower model and a hybrid optimization methodology combining an oriented octree with the GGA are proposed. Numerical results on typical case studies show that, for a wire-to-wire minimal distance calculation, the GGA outperforms both the basic genetic algorithm and particle swarm optimization in terms of both convergence speed and solution accuracy. For a wire-to-tower minimal distance calculation, the oriented octree improves the spatial utilization, and the proposed hybrid methodology substantially improves the computational performance. Full article

Background: Food-related reactions can significantly impact children’s dietary choices, health, and nutritional status. This study evaluated adherence to the Mediterranean diet and explored its associations with regional and family socioeconomic status among Croatian children whose parents reported adverse food-related reactions. Methods: The cross-sectional study analyzed data on 193 children aged 2–9 years with parent-reported food-related reactions, collected from the Croatian National Food Consumption Survey, which included 1820 children aged 3 months to 9 years, based on the EU Menu methodology (OC/EFSA/DATA/2016/02 CT3). Parents completed standardized questionnaires on food-related reactions, lifestyle, dietary patterns, and socioeconomic indicators. Regional differences were assessed, and adherence to the Mediterranean diet was evaluated using the KIDMED index. Results: This survey found an 11% prevalence of parent-reported adverse food-related reactions among children aged 2 to 9 years. Milk, eggs, and tree nuts were the most commonly reported allergens. Adherence to the Mediterranean diet was moderate (36%) to low (41%; p = 0.011), with higher KIDMED scores associated with greater fruit, vegetable, legume, fish, and olive oil intake and lower adherence associated with more ultra-processed foods and obesity. Children from coastal and urban areas had better diet quality and socioeconomic indicators. Maternal education was strongly associated with Mediterranean diet adherence (OR = 1.88, p < 0.001), while maternal employment and household income showed no significant relationship. Conclusions: The findings highlight significant nutritional challenges among Croatian children with adverse food-related reactions, driven by regional and socioeconomic disparities. An adherence to a low Mediterranean diet indicates a need for a personalized approach to the diet management of children with food-related reactions. Addressing these through targeted, equitable public health strategies may improve outcomes for affected children. Full article

This study introduces a hybrid point cloud compression method that transfers from octree-nodes to voxel occupancy estimation to find its lower-bound bitrate by using a Binary Arithmetic Range Coder. In previous attempts, we demonstrated that our entropy compression model based on index convolution achieves promising performance while maintaining low complexity. However, our previous model lacks an autoregressive approach, which is apparently indispensable to compete with the current state-of-the-art of compression performance. Therefore, we adapt an autoregressive grouping method that iteratively populates, explores, and estimates the occupancy of 1-bit voxel candidates in a more discrete fashion. Furthermore, we refactored our backbone architecture by adding a distiller layer on each convolution, forcing every hidden feature to contribute to the final output. Our proposed model extracts local features using lightweight 1D convolution applied in varied ordering and analyzes causal relationships by optimizing the cross-entropy. This approach efficiently replaces the voxel convolution techniques and attention models used in previous works, providing significant improvements in both time and memory consumption. The effectiveness of our model is demonstrated on three datasets, where it outperforms recent deep learning-based compression models in this field. Full article

Laser scanners based on the Simultaneous Localization and Mapping (SLAM) principle generate extremely dense point clouds burdened with a high level of surface noise arising from random measurement errors and repeated scanning of identical regions. This increases data volume and complicates subsequent processing. The present study introduces four novel noise filtering and subsampling algorithms that selectively preserve the points closest to the true surface. Each algorithm assigns a filtering characteristic to individual points based either on their distance from a locally estimated (planar or quadratic) surface or on the degree of local eccentricity in the spherical neighborhood of the point. The proposed methods were tested on point clouds acquired using three SLAM scanners (Emesent Hovermap ST-X, FARO Orbis, and ZEB Horizon) in three different scenes with reference data acquired by a static terrestrial scanner Leica P40. All four proposed methods effectively reduced surface noise and data volume (improving the RMSDs by 45.4–75.8% compared to the original cloud after thinning to 10% of cloud size). This clearly outperformed the standard subsampling tools, namely random subsampling (RMSD remained constant after subsampling), octree, or spatial subsampling (worsening of RMSDs with increasing subsampling). The most reliable surface noise removal in point clouds dominated by planar surfaces (building interior with planar walls) was achieved using the method based on local plane fitting. In contrast, the use of a quadratic surface proved more effective for uneven or rugged surfaces. Full article