Search Results (306)

This paper proposes a speed-adaptive autonomous driving path-tracking framework based on the soft actor–critic (SAC) and pure pursuit (PP) methods, named the SACPP controller. The framework first analyzes the obstacles around the vehicle and plans an obstacle-free reference path with the minimum curvature using the hybrid A* algorithm. Next, based on the generated reference path, the current state of the vehicle, and the vehicle motor energy efficiency diagram, the optimal speed is calculated in real time, and the vehicle dynamics preview point at the future moment—specifically, the look-ahead distance—is predicted. This process relies on the learning of the SAC network structure. Finally, PP is used to generate the front wheel angle control value by combining the current speed and the predicted preview point. In the second layer, we carefully designed the evaluation function in the tracking process based on the uncertainties and performance requirements that may occur during vehicle driving. This design ensures that the autonomous vehicle can not only quickly and accurately track the path, but also effectively avoid surrounding obstacles, while keeping the motor running in the high-efficiency range, thereby reducing energy loss. In addition, since the entire framework uses a lightweight network structure and a geometry-based method to generate the front wheel angle, the computational load is significantly reduced, and computing resources are saved. The actual running results on the i7 CPU show that the control cycle of the control framework exceeds 100 Hz. Full article

Off-road path planning involves navigating vehicles through areas lacking established road networks, which is critical for emergency response in disaster events, but is limited by the complex geographical environments in natural conditions. How to model the vehicle’s off-road mobility effectively and represent environments is critical for efficient path planning in off-road environments. This paper proposed an improved A* path planning algorithm based on a Delaunay triangular NavMesh model with off-road environment representation. Firstly, a land cover off-road mobility model is constructed to determine the navigable regions by quantifying the mobility of different geographical factors. This model maps passable areas by considering factors such as slope, elevation, and vegetation density and utilizes morphological operations to minimize mapping noise. Secondly, a Delaunay triangular NavMesh model is established to represent off-road environments. This mesh leverages Delaunay triangulation’s empty circle and maximum-minimum angle properties, which accurately represent irregular obstacles without compromising computational efficiency. Finally, an improved A* path planning algorithm is developed to find the optimal off-road mobility path from a start point to an end point, and identify a path triangle chain with which to calculate the shortest path. The improved road-off path planning A* algorithm proposed in this paper, based on the Delaunay triangulation navigation mesh, uses the Euclidean distance between the midpoint of the input edge and the midpoint of the output edge as the cost function $g\left(n\right)$, and the Euclidean distance between the centroids of the current triangle and the goal as the heuristic function $h\left(n\right)$. Considering that the improved road-off path planning A* algorithm could identify a chain of path triangles for calculating the shortest path, the funnel algorithm was then introduced to transform the path planning problem into a dynamic geometric problem, iteratively approximating the optimal path by maintaining an evolving funnel region, obtaining a shortest path closer to the Euclidean shortest path. Research results indicate that the proposed algorithms yield optimal path-planning results in terms of both time and distance. The navigation mesh-based path planning algorithm saves 5~20% of path length than hexagonal and 8-directional grid algorithms used widely in previous research by using only 1~60% of the original data loading. In general, the path planning algorithm is based on a national-level navigation mesh model, validated at the national scale through four cases representing typical natural and social landscapes in China. Although the algorithms are currently constrained by the limited data accessibility reflecting real-time transportation status, these findings highlight the generalizability and efficiency of the proposed off-road path-planning algorithm, which is useful for path-planning solutions for emergency operations, wilderness adventures, and mineral exploration. Full article

Accurate behavioral monitoring of silkworms (Bombyx mori) during the fourth instar development is crucial for enhancing productivity and welfare in sericulture operations. Current manual observation paradigms face critical limitations in temporal resolution, inter-observer variability, and scalability. This study presents RDM-YOLO, a computationally efficient deep learning framework derived from YOLOv5s architecture, specifically designed for the automated detection of three essential behaviors (resting, wriggling, and eating) in fourth instar silkworms. Methodologically, Res2Net blocks are first integrated into the backbone network to enable hierarchical residual connections, expanding receptive fields and improving multi-scale feature representation. Second, standard convolutional layers are replaced with distribution shifting convolution (DSConv), leveraging dynamic sparsity and quantization mechanisms to reduce computational complexity. Additionally, the minimum point distance intersection over union (MPDIoU) loss function is proposed to enhance bounding box regression efficiency, mitigating challenges posed by overlapping targets and positional deviations. Experimental results demonstrate that RDM-YOLO achieves 99% mAP@0.5 accuracy and 150 FPS inference speed on the datasets, significantly outperforming baseline YOLOv5s while reducing the model parameters by 24%. Specifically designed for deployment on resource-constrained devices, the model ensures real-time monitoring capabilities in practical sericulture environments. Full article

Under the background of continuous breakthroughs in the spatial resolution of satellite remote sensing technology, high-resolution remote sensing images have become a frontier data source for intelligent inspection research of power infrastructure. To address existing issues in remote sensing image application algorithms such as difficulties in power target feature extraction, low detection accuracy, and false positives/missed detections, this paper proposes the YOLOv9-GDV power tower detection algorithm specifically for power tower detection in high-resolution satellite remote sensing images. Firstly, under high-resolution imaging conditions where transmission tower features are prominent, a Global Pyramid Attention (GPA) mechanism is proposed. This mechanism enhances global representation capabilities, enabling the model to better understand object–background relationships and effectively integrate multi-scale spatial information, thereby improving detection accuracy and robustness. Secondly, a Diverse Branch Block (DBB) is embedded in the feature extraction–fusion module, which enriches the feature space by enhancing the representation capability of single-convolution operations, thereby improving model feature extraction performance without increasing inference time costs. Finally, the Variable Minimum Point Distance Intersection over Union (VMPDIoU) loss is proposed to optimize the model’s loss function. This method employs variable input parameters to directly calculate key point distances between predicted and ground-truth boxes, more accurately reflecting positional differences between detection results and reference targets, thus effectively improving the model’s mean Average Precision (mAP). On the Satellite Remote Sensing Power Tower Dataset (SRSPTD), the YOLOv9-GDV algorithm achieves an mAP of 80.2%, representing a 4.7% improvement over the baseline algorithm. On the multi-scene high-resolution power transmission tower dataset (GFTD), the algorithm obtains an mAP of 94.6%, showing a 2.3% improvement over the original model. The significant mAP improvements on both datasets validate the effectiveness and feasibility of the proposed method. Full article

In this study, we model a solution surface, with each point having nine components using artificial intelligence (AI), to optimise the effects of ground vibration during blasting operations in an open-pit diamond mine. This model has eight input parameters that can be adjusted by blasting engineers to arrive at a desired output value of ground vibration. It is built using the best performing artificial neural network architecture that best fits the blasting data from 100 blasting events provided by the Debswana diamond mine. Other AI algorithms used to compare the model’s performance were the k-nearest neighbour, support vector machine, and random forest—together with more traditional statistical approaches, i.e., multivariate and regression analyses. The input parameters were burden, spacing, stemming length, hole depth, hole diameter, distance from the blast face to the monitoring point, maximum charge per delay, and powder factor. The optimised model allows for variations in the input values, given the constraints, such that the output ground vibration will be within the minimum acceptable value. Through unconstrained optimisation, the minimum value of ground vibration is around 0.1 mm/s, which is within the vibration range caused by a passing vehicle. Full article

Excessive bait wastage is a major issue in aquaculture, leading to higher farming costs, economic losses, and water pollution caused by bacterial growth from unremoved residual bait. To address this problem, we propose a bait residue detection and counting model named YOLOv8-BaitScan, based on an improved YOLO architecture. The key innovations are as follows: (1) By incorporating the channel prior convolutional attention (CPCA) into the final layer of the backbone, the model efficiently extracts spatial relationships and dynamically allocates weights across the channel and spatial dimensions. (2) The minimum points distance intersection over union (MPDIoU) loss function improves the model’s localization accuracy for bait bounding boxes. (3) The structure of the Neck network is optimized by adding a tiny-target detection layer, which improves the recall rate for small, distant bait targets and significantly reduces the miss rate. (4) We design the lightweight detection head named Detect-Efficient, incorporating the GhostConv and C2f-GDC module into the network to effectively reduce the overall number of parameters and computational cost of the model. The experimental results show that YOLOv8-BaitScan achieves strong performance across key metrics: The recall rate increased from 60.8% to 94.4%, mAP@50 rose from 80.1% to 97.1%, and the model’s number of parameters and computational load were reduced by 55.7% and 54.3%, respectively. The model significantly improves the accuracy and real-time detection capabilities for underwater bait and is more suitable for real-world aquaculture applications, providing technical support to achieve both economic and ecological benefits. Full article

To investigate the hindering effect of fracture on heat transfer within rock mass, real-time temperature monitoring was conducted on fractured granite heated by different constant-temperature heat sources. The heat transfer characteristics were analyzed based on the temperature field distribution, temperature variation pattern, heating rate, temperature difference, and temperature gradient evolution within the fractured granite. Additionally, the difference in temperature field distributions of both intact and fractured granite under different heat source temperatures were discussed. The study reveals that fracture exerts significant control over temperature field distribution in granite, with heat transfer governed by the combined effects of rock heterogeneity and fracture presence. During heating, fractured granite exhibits three distinct temperature response stages: rapid heating, slow heating, and temperature stabilization. Steady temperatures decrease nonlinearly and linearly with increasing distance from the heat source on the left and right side of the fracture. All monitoring points display unimodal heating rate trends (rise–peak–decline–stabilization), with peak rates of 20~120 °C/h above the horizontal monitoring line F-F versus 10~20 °C/h below it. The hindering effect of fracture on heat transfer shows spatial heterogeneity; under the condition of the 80 °C heat source, the temperature difference in the central region is the largest (ΔT_max = 10.5 °C), and the top is the smallest (ΔT_min = 4.5 °C). Concentrated isothermal gradient contours form around fractures, with the time-to-peak gradient correlating positively with heat source distance. Maximum and minimum temperature gradients within the fracture reached 825 °C/m and 345 °C/m, respectively, at 90 °C source temperature. The research results can provide a theoretical basis and technical support for HDR geothermal development. Full article

With the advancement of spatial positioning technology, trajectory data have been growing rapidly. Trajectory data record the spatiotemporal information and behavioral characteristics of moving objects, and in-depth analysis can provide decision support for urban transportation. This paper explores effective methods for trajectory data representation, with a focus on the study of data fitting methods. Data fitting can extract key information and reveal underlying patterns, and the use of fitting methods can significantly improve the efficiency and accuracy of spatiotemporal trajectory data analysis, offering new perspectives and methodological support for related research fields. This paper integrates road network data to enhance trajectory data, treating trajectory data as a dynamic signal that changes over time. Through Fourier transformation, the data are converted from the time domain to the frequency domain, and trajectory points are fitted in the frequency spectrum domain, transforming discrete trajectory points into time-continuous linear elements. By referencing the minimum visually discernible distance and velocity precision requirements at a specific scale, thresholds for positional and velocity errors are set. The similarity between the Fourier-fitted trajectory and the original trajectory is measured in both spatial and temporal dimensions. By calculating the number of expansion terms of the Fourier series at a specific spatiotemporal scale, a functional relationship between the number of expansion terms, duration, and distance is fitted within the set threshold range (R² = 0.8424). This enables the Fourier series representation of any trajectory data under specific positional and velocity error thresholds. The errors in position and velocity obtained using this expression are significantly lower than the theoretical errors. The experimental results demonstrate that the Fourier fitting method exhibits strong generality and precision, effectively approximating the original trajectory, and provides a robust mathematical foundation for the quantification and detailed analysis of trajectory data. Full article

Due to complex backgrounds, significant scale variations of targets, and dense distributions of small objects in Unmanned Aerial Vehicle (UAV) aerial images, traditional object detection algorithms face challenges in adapting to such scenarios. This article introduces a drone detection model, MEP-YOLOv5s, which optimizes the Backbone, Neck layer, and C3 module based on YOLOv5s, and combines effective attention mechanisms to improve the training efficiency of the model by replacing the traditional CIoU loss (Complete Intersection over Union) with MPDIoU (Minimum Point Distance-based Intersection over Union) loss. This model demonstrates an excellent performance in handling typical drone detection scenarios, especially for small and dense objects. To holistically balance the detection accuracy and inference efficiency, we propose a Comprehensive Performance Indicator (CPI), which evaluates the model performance by considering both accuracy and efficiency. Evaluations on the VisDrone2019 dataset demonstrate that MEP-YOLOv5s achieves a 3.3% improvement in precision (P), a 20.9% increase in mAP@0.5, and a 19.86% gain in the CPI ($\mathsf{\alpha }$ = 0.5) compared with the baseline model. Additional experiments on the NWPU VHR-10 dataset confirm that MEP-YOLOv5s outperforms the existing state-of-the-art methods, offering a robust solution for UAV-based small object detection with enhanced feature extraction and attention-driven adaptability. Full article

Given a set of n points in a plane, the General Position Subset Selection problem is that of finding a maximum-size subset of points in general position, i.e., with no three points collinear. The problem is known to be hard computationally, and the best approximation ratio known is $\mathrm{\Omega }\left(n^{-1/2}\right)$. Here, we obtain better approximations in three special cases: (I) a constant-factor approximation for the case where the input set consists of lattice points and is dense, which means that the ratio between the maximum and the minimum distance in P is of the order of $\mathrm{\Theta }\left(\sqrt{n}\right)$; (II) an $\mathrm{\Omega }\left({(logn)}^{-1/2}\right)$-approximation for the case where the input set is the set of vertices of a genericn-line arrangement, i.e., one with $\mathrm{\Omega }\left(n^2\right)$ vertices; and (III) an $\mathrm{\Omega }\left({(logn)}^{-1/2}\right)$-approximation for the case where the input set has at most $O\left(\sqrt{n}\right)$ points collinear and can be covered by $O\left(\sqrt{n}\right)$ lines. The scenario in (I) is a special case of that in (II). Our approximations rely on probabilistic methods and results from incidence geometry. Full article

Objective: The aim of this study was to investigate the immediate effects of deep core muscle training in the plank position, using the Icaros^® system, integrated with virtual reality (VR), on selected posturographic parameters. Methods: To meet the stated objective, we utilized the Icaros^® therapeutic system (Icaros GmbH, Martinsried, Germany) for VR-based exercise. The posturographic parameters were measured using the FootScan^® force platform (Materialise Motion, Paal, Belgium). A representative sample of 30 healthy participants, 13 females and 17 males (age: 22.5 ± 2.1 years; weight: 65 ± 2.9 kg; height: 1.68 ± 0.4 m; BMI: 23.04 ± 1.75) was included in the study. All participants had no prior experience with VR. The selected posturographic parameters were the ellipse area (mm²) and traveled distance (mm), assessed four times at five-minute intervals, following a 15 min VR-based training session on the Icaros^® system. Results: The results revealed that the participants experienced a sense of instability after completing the 15 min VR session, as objectively demonstrated by changes in the measured parameters. Both the ellipse area and traveled distance showed a worsening trend during the first three measurements: immediately post-exercise, at 5 min, and at 10 min post-exercise. A downward trend was observed in the fourth measurement, taken 15 min after exercise. Statistically significant differences were found between both parameters: ellipse area (p = 0.000) and traveled distance (p = 0.000). Post hoc analysis further confirmed significant differences between the time points. Conclusions: Based on the findings, it is recommended that trainers and physiotherapists supervising athletes or patients using the Icaros^® VR system allow for a minimum rest period of 15 min in a seated or lying position following exercise. This recovery period appears essential to mitigate the sensation of instability and to reduce the risk of complications or injury due to potential falls. Full article

The efficiency and smoothness of path planning algorithms are critical factors influencing their practical applications. A traditional A* algorithm suffers from limitations in search efficiency, path smoothness, and obstacle avoidance. To address these challenges, this paper introduces an improved A* algorithm that integrates the Salp Swarm Algorithm (SSA) for heuristic function optimization and proposes a refined B-spline interpolation method for path smoothing. The first major improvement involves enhancing the A* algorithm by optimizing its heuristic function through the SSA. The heuristic function combines Chebyshev distance, Euclidean distance, and obstacle density, with the SSA adjusting the weight parameters to maximize efficiency. The simulation experimental results demonstrate that this modification reduces the number of searched nodes by more than 78.2% and decreases planning time by over 48.1% compared to traditional A* algorithms. The second key contribution is an improved B-spline interpolation method incorporating a two-stage optimization strategy for smoother and safer paths. A corner avoidance strategy first adjusts control points near sharp turns to prevent collisions, followed by a path obstacle avoidance strategy that fine-tunes control point positions to ensure safe distances from obstacles. The simulation experimental results show that the optimized path increases the minimum obstacle distance by 0.2–0.5 units, improves the average distance by over 43.0%, and reduces path curvature by approximately 61.8%. Comparative evaluations across diverse environments confirm the superiority of the proposed method in computational efficiency, path smoothness, and safety. This study presents an effective and robust solution for path planning in complex scenarios. Full article

Light detection and ranging (LiDAR) sensor technology for people detection offers a significant advantage in data protection. However, to design these systems cost- and energy-efficiently, the relationship between the measurement data and final object detection output with deep neural networks (DNNs) has to be elaborated. Therefore, this paper presents augmentation methods to analyze the influence of the distance, resolution, noise, and shading parameters of a LiDAR sensor in real point clouds for people detection. Furthermore, their influence on object detection using DNNs was investigated. A significant reduction in the quality requirements for the point clouds was possible for the measurement setup with only minor degradation on the object list level. The DNNs PointVoxel-Region-based Convolutional Neural Network (PV-RCNN) and Sparsely Embedded Convolutional Detection (SECOND) both only show a reduction in object detection of less than 5% with a reduced resolution of up to 32 factors, for an increase in distance of 4 factors, and with a Gaussian noise up to $\mu =0$ and $\sigma =0.07$. In addition, both networks require an unshaded height of approx. 0.5 m from a detected person’s head downwards to ensure good people detection performance without special training for these cases. The results obtained, such as shadowing information, are transferred to a software program to determine the minimum number of sensors and their orientation based on the mounting height of the sensor, the sensor parameters, and the ground area under consideration, both for detection at the point cloud level and object detection level. Full article

Aiming at the limitations of current citrus detection methods in complex orchard environments, especially the problems of poor model adaptability and high computational complexity under different lighting, multiple occlusions, and dense fruit conditions, this study proposes an improved citrus detection model, YOLO-PBGM, based on You Only Look Once v7 (YOLOv7). First, to tackle the large size of the YOLOv7 network model and its deployment challenges, the PC-ELAN module is constructed by introducing Partial Convolution (PConv) for lightweight improvement, which reduces the model’s demand for computing resources and parameters. At the same time, the Bi-Former attention module is embedded to enhance the perception and processing of citrus fruit information. Secondly, a lightweight neck network is constructed using Grouped Shuffle Convolution (GSConv) to simplify computational complexity. Finally, the minimum-point-distance-based IoU (MPDIoU) loss function is utilized to optimize the boundary return mechanism, which speeds up model convergence and reduces the redundancy of bounding box regression. Experimental results indicate that for the citrus dataset collected in a natural environment, the improved model reduces Params and GFLOPs by 15.4% and 23.7%, respectively, while improving precision, recall, and mAP by 0.3%, 4%, and 3.5%, respectively, thereby outperforming other detection networks. Additionally, an analysis of citrus object detection under varying lighting and occlusion conditions reveals that the YOLO-PBGM network model demonstrates good adaptability, effectively coping with variations in lighting and occlusions while exhibiting high robustness. This model can provide a technical reference for uncrewed intelligent picking of citrus. Full article

Global warming has driven a marked increase in forest fire occurrences, underscoring the critical need for timely and accurate detection to mitigate fire-related losses. Existing forest fire detection algorithms face limitations in capturing flame and smoke features in complex natural environments, coupled with high computational complexity and inadequate lightweight design for practical deployment. To address these challenges, this paper proposes an enhanced forest fire detection model, YOLOv8n-SMMP (SlimNeck–MCA–MPDIoU–Pruned), based on the YOLO framework. Key innovations include the following: introducing the SlimNeck solution to streamline the neck network by replacing conventional convolutions with Group Shuffling Convolution (GSConv) and substituting the Cross-convolution with 2 filters (C2f) module with the lightweight VoV-based Group Shuffling Cross-Stage Partial Network (VoV-GSCSP) feature extraction module; integrating the Multi-dimensional Collaborative Attention (MCA) mechanism between the neck and head networks to enhance focus on fire-related regions; adopting the Minimum Point Distance Intersection over Union (MPDIoU) loss function to optimize bounding box regression during training; and implementing selective channel pruning tailored to the modified network architecture. The experimental results reveal that, relative to the baseline model, the optimized lightweight model achieves a 3.3% enhancement in detection accuracy (mAP@0.5), slashes the parameter count by 31%, and reduces computational overhead by 33%. These advancements underscore the model’s superior performance in real-time forest fire detection, outperforming other mainstream lightweight YOLO models in both accuracy and efficiency. Full article