Search

After apple fruit maturation, the optimal harvest period is short, and the picking robot is expected to improve harvesting efficiency. While it is common for apples to be overlapped and occluded by branches and leaves, which pose challenges to the robot's apple harvesting. Therefore, precise and swift identification and localization of the target fruit is crucial. To this end, this paper proposes a lightweight apple detection method, YOLOv5s-ShuffleNetV2-DWconv-Add, or "YOLOv5s-SDA" for short. The red and green apple datasets in natural environment were collected by a mobile phone, which were divided into four categories: red and green apples that can be directly grasped and cannot be directly grasped, in order to avoid damage to the robotic arm. Different deep learning object detection models were compared, with the YOLOv5s algorithm providing superior recognition performance. To improve harvest efficiency and portability of hardware devices, modifications are made to the YOLOv5s algorithm, replacing the Focus, C3, and Conv structures within the backbone with 3 × 3 Conv structures and ShuffleNetV2, removing SPP and C3 structures; substituting the C3 in the Neck portion with DWConv modules; and replacing two Concat layers in the PANet structure with smaller computational Add layers. Results demonstrate that the model achieved a mAP of 94.6% on the test set, doubled the detection speed, and compressed the model weight to 11.8% of its original value, while maintaining model accuracy. This new method exhibits promising performance in fruit target recognition in natural scenes, providing an effective means of visual acquisition for fruit picking robots. [ABSTRACT FROM AUTHOR]

Green innovation plays a critical role in attaining carbon neutrality and supporting high-quality economic development in China; however, its promotion remains challenging. Hence, this study uses asymmetric innovation theory and fuzzy-set qualitative comparative analysis (fsQCA) to explore the drivers of green innovation in China's complex regional environments. Using data from 30 Chinese provinces, it investigates the combined effects of factors at the market, institution, and technology levels on regional green innovation. The findings indicate the following. (1) R&D investment is necessary for high-level green innovation, whereas its absence is a necessary condition for low-level green innovation. (2) Three configurations produce high-level green innovation, and these configurations coalesce into demand--regulation--subsidy--technology-driven and competition--technology-driven paths. (3) Four configurations result in low-level green innovation, and the antecedent configurations of high-level and low-level green innovation have an asymmetric relationship. This study adds to the understanding of the causal configurations that promote green innovation and provides valuable insights for policymakers in China and other developing regions. [ABSTRACT FROM AUTHOR]

To solve the complicated steering control of small vehicles in the agriculture and difficult steering on complex roads, this study designed a wheel-track composite vehicle. The vehicle incorporated a novel power differential steering mechanism with dual driving, enabling steering through the differential rotation of the rear two wheels. The vehicle is simple to control, small in size, and is able to work under the conditions of complex roads, such as hills, mountains, and muddy land. The study initially focused on presenting the design, theoretical analysis, and dynamic simulation analysis of the power differential steering mechanism with dual driving. Subsequently, the vehicle underwent modeling and simulation using UG software to validate the reasonability of the values. Finally, utilizing test data, four mathematical models for the actual steering radius of the vehicle on four road surfaces were derived through neural network fitting. The maximum relative error between the model results and the actual steering radius value was reported to be 3.53%. The advantages of the vehicle included continuous radius steering, deceleration and torsion increase, differential lock, etc. This made it well-suited for applications in all-terrain military and civilian vehicles, as well as various special equipment mobile platforms equipped with walking devices. [ABSTRACT FROM AUTHOR]

Background: The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan Big leaf kind of tea within its complex ecological niche. Results: Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 98.58% and a verification accuracy rate of 98.2310%. Conclusions: These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan. [ABSTRACT FROM AUTHOR]

The efficient operation of heating ventilation and air conditioning systems relies on advanced control strategies. However, current control methods are often limited by issues such as uncertain system parameter information and spatial coupling constraints related to the supply rate of the air supply fan. To this end, an energy joint thermal comfort management method for complex environments in multiple regions is proposed. The long-term total cost minimization of the system is established, and then the Lyapunov optimization technology is used to design the distributed control algorithm. Simulation validation shows that the proposed method reduces the energy cost by an average of 11.24% compared to other methods with a thermal discomfort cost coefficient of 0. The average temperature deviation in the area is improved by 0.15 °C and 0.68 °C, respectively. The method saves more than 10% of the total energy cost under different thermal perturbations with an average total temperature deviation of 0.04 °C. The results indicate that the proposed energy joint thermal comfort management method can flexibly balance energy costs and user thermal comfort without knowing any prior information of system parameters, which can also greatly protect user privacy information. This method has application value in the control of heating ventilation and air conditioning systems in complex environments such as commercial buildings. [ABSTRACT FROM AUTHOR]

It has been a challenge to obtain accurate detection results in a timely manner when faced with complex and changing surface target detection. Detecting targets on water surfaces in real-time can be challenging due to their rapid movement, small size, and fragmented appearance. In addition, traditional detection methods are often labor-intensive and time-consuming, especially when dealing with large water bodies such as rivers and lakes. This paper presents an improved water surface target detection algorithm that is based on the YOLOv7 (you only look once) model to enhance the performance of water surface target detection. We have enhanced the accuracy and speed of detecting surface targets by making improvements to three key structures: the network aggregation structure, the pyramid pooling structure, and the down-sampling structure. Furthermore, we implemented the model on mobile devices and designed a detection software. The software enables real-time detection through images and videos. The experimental results demonstrate that the improved model outperforms the original YOLOv7 model. It exhibits a 6.4% boost in accuracy, a 4.2% improvement in recall, a 4.1% increase in mAP, a 14.3% reduction in parameter counts, and archives the FPS of 87. The software has the ability to accurately recognize 11 typical targets on the water surface and demonstrates excellent water surface target detection capability. [ABSTRACT FROM AUTHOR]

Marine anchor buoys, as fixed-point profile observation platforms, are highly susceptible to the threat of ship collisions. Installing cameras on buoys can effectively monitor and collect evidence from ships. However, when using a camera to capture images, it is often affected by the continuous shaking of buoys and rainy and foggy weather, resulting in problems such as blurred images and rain and fog occlusion. To address these problems, this paper proposes an improved YOLOv8 algorithm. Firstly, the polarized self-attention (PSA) mechanism is introduced to preserve the high-resolution features of the original deep convolutional neural network and solve the problem of image spatial resolution degradation caused by shaking. Secondly, by introducing the multi-head self-attention (MHSA) mechanism in the neck network, the interference of rain and fog background is weakened, and the feature fusion ability of the network is improved. Finally, in the head network, this model combines additional small object detection heads to improve the accuracy of small object detection. Additionally, to enhance the algorithm's adaptability to camera detection scenarios, this paper simulates scenarios, including shaking blur, rain, and foggy conditions. In the end, numerous comparative experiments on a self-made dataset show that the algorithm proposed in this study achieved 94.2% mAP50 and 73.2% mAP50:95 in various complex environments, which is superior to other advanced object detection algorithms. [ABSTRACT FROM AUTHOR]

Abstract Background The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan Big leaf kind of tea within its complex ecological niche. Results Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 98.58% and a verification accuracy rate of 98.2310%. Conclusions These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan.

Abstract The efficient operation of heating ventilation and air conditioning systems relies on advanced control strategies. However, current control methods are often limited by issues such as uncertain system parameter information and spatial coupling constraints related to the supply rate of the air supply fan. To this end, an energy joint thermal comfort management method for complex environments in multiple regions is proposed. The long-term total cost minimization of the system is established, and then the Lyapunov optimization technology is used to design the distributed control algorithm. Simulation validation shows that the proposed method reduces the energy cost by an average of 11.24% compared to other methods with a thermal discomfort cost coefficient of 0. The average temperature deviation in the area is improved by 0.15 °C and 0.68 °C, respectively. The method saves more than 10% of the total energy cost under different thermal perturbations with an average total temperature deviation of 0.04 °C. The results indicate that the proposed energy joint thermal comfort management method can flexibly balance energy costs and user thermal comfort without knowing any prior information of system parameters, which can also greatly protect user privacy information. This method has application value in the control of heating ventilation and air conditioning systems in complex environments such as commercial buildings.

In response to the current challenges of numerous background influencing factors and low detection accuracy in the open railway foreign object detection, a real-time foreign object detection method based on deep learning for open railways in complex environments is proposed. Firstly, the images of foreign objects invading the clearance collected by locomotives during long-term operation are used to create a railway foreign object dataset that fits the current situation. Then, to improve the performance of the target detection algorithm, certain improvements are made to the YOLOv7-tiny network structure. The improved algorithm enhances feature extraction capability and strengthens detection performance. By introducing a Simple, parameter-free Attention Module for convolutional neural network (SimAM) attention mechanism, the representation ability of ConvNets is improved without adding extra parameters. Additionally, drawing on the network structure of the weighted Bi-directional Feature Pyramid Network (BiFPN), the backbone network achieves cross-level feature fusion by adding edges and neck fusion. Subsequently, the feature fusion layer is improved by introducing the GhostNetV2 module, which enhances the fusion capability of different scale features and greatly reduces computational load. Furthermore, the original loss function is replaced with the Normalized Wasserstein Distance (NWD) loss function to enhance the recognition capability of small distant targets. Finally, the proposed algorithm is trained and validated, and compared with other mainstream detection algorithms based on the established railway foreign object dataset. Experimental results show that the proposed algorithm achieves applicability and real-time performance on embedded devices, with high accuracy, improved model performance, and provides precise data support for railway safety assurance. [ABSTRACT FROM AUTHOR]

This paper presents a novel hybrid optimization method to solve the resource allocation problem for multi-target multi-sensor tracking of drones. This hybrid approach, the Improved Prairie Dog Optimization Algorithm (IPDOA) with the Genetic Algorithm (GA), utilizes the strengths of both algorithms to improve the overall optimization performance. The goal is to select a set of sensors based on norms of weighted distances cost function. The norms are the Euclidean distance and the Mahalanobis distance between the drone location and the sensors. The second one depends on the predicted covariance of the tracker. The Extended Kalman Filter (EKF) is used for state estimation with proper clutter and detection models. Since we use Multi-objects to track, the Joint Probability Distribution Function (JPDA) estimates the best measurement values with a preset gating threshold. The goal is to find a sensor or minimum set of sensors that would be enough to generate high-quality tracking based on optimum resource allocation. In the experimentation simulated with Stone Soup, one radar among five radars is selected at every time step of 50-time steps for 200 tracks distributed over 20 different ground truths. The proposed IPDOA provided optimum solutions for this complex problem. The obtained solution is an optimum offline solution that is used to select one or more sensors for any future flights within the vicinity of the 5 radars. Environment and conditions are assumed to be similar in future drone flights within the radars' defined zone. The IPDOA performance was compared with the other 8 metaheuristic optimization algorithms and the testing showed its superiority over those techniques for solving this complex problem. The proposed simulated model can find the most relevant sensor(s) capable of generating the best quality tracks based on weighted distance criteria (Euclidean and Mahalanobis). That would cut down the cost of operating extra sensors and then it would be possible to move them to other vicinity. [ABSTRACT FROM AUTHOR]

Efficient navigation is crucial for intelligent mobile robots in complex environments. This paper introduces an innovative approach that seamlessly integrates advanced machine learning techniques to enhance mobile robot communication and path planning efficiency. Our method combines supervised and unsupervised learning, utilizing spline interpolation to generate smooth paths with minimal directional changes. Experimental validation with a differential drive mobile robot demonstrates exceptional trajectory control efficiency. We also explore Motion Planning Networks (MPNets), a neural planner that processes raw point-cloud data from depth sensors. Our tests demonstrate MPNet's ability to create optimal paths using the Probabilistic Roadmap (PRM) method. We highlight the importance of correctly setting parameters for reliable path planning with MPNet and evaluate the algorithm on various path types. Our experiments confirm that the trajectory control algorithm works effectively, consistently providing precise and efficient trajectory control for the robot. [ABSTRACT FROM AUTHOR]

In this study, our aim is to find an effective method to solve the problem of disease similarity caused by multiple diseases occurring on the same leaf. This study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases. We conducted comparisons and analyses on the impact of various factors, such as training methods, data expansion methods, optimizer selection, image background, and other factors, on model performance. The findings suggest that utilizing offline expansion and transfer learning to fine-tune all layer parameters can enhance the model's classification performance, while complex image backgrounds significantly influence model performance. Additionally, the optimized RegNet network model demonstrates good generalization ability for both datasets, achieving testing accuracies of 93.85% and 99.23%, respectively. These results highlight the potential of the optimized RegNet network model to achieve high-precision identification of different diseases on the same apple leaf under complex field backgrounds. This will be of great significance for intelligent disease identification in apple orchards in the future. [ABSTRACT FROM AUTHOR]

This article uses ultra‐high performance concrete (UHPC) to repair damaged concrete and analyzes the durability performance of the repaired concrete. Among them, three erosion solutions with a mass concentration of 2.8% NaCl + 0.29% Na2SO4, 5% NaCl, and 5% NaCl + 10% Na2SO4 were designed to soak the concrete specimens for 1 to 3 months. Taking the SWC test group as an example, when the concrete test block undergoes 30 dry wet cycles and the erosion depth is 20 mm, the difference in chloride ion concentration under different diffusion dimensions is not significant. After 90 dry wet cycles, at a depth of 20 mm, the chloride ion concentration inside the concrete in the three‐dimensional diffusion state reached 3 times that of one‐dimensional diffusion, and the chloride ion concentration in the two‐dimensional diffusion state also reached 2 times that of one‐dimensional diffusion. At a depth of 30 mm, a small amount of chloride ion content was also found in the two‐dimensional diffusion and three‐dimensional diffusion. [ABSTRACT FROM AUTHOR]

The YOLOv7-tiny algorithm does not achieve high detection accuracy for crested ibis in rainy environments. Therefore, we developed a rainy day crested ibis target detection algorithm based on YOLOv7-tiny. Firstly, the RainMix method is used to simulate the rainy day shooting data to synthesise a set of ibis dataset which is closer to the real environment. Then, the k-means algorithm is applied to re-cluster the predicted anchor frames to improve the approximation between the predicted and real frames in the output. Finally, an efficient hybrid attention mechanism (E-SEWSA) is developed and integrated into a lightweight efficient layer aggregation network, while a dense residual network reconstruction module is utilised to improve the detection accuracy of the model. In the PAN+FPN structure, the context information fusion capability of the feature aggregation part of the network is enhanced by integrating the CARAFE module instead of the up-sampling module, so as to improve the model detection accuracy. After experimental verification, the algorithm proposed in this paper has better results in rainy day ibis detection. [ABSTRACT FROM AUTHOR]

Accurate and stable positioning is significant for vehicle navigation systems, especially in complex urban environments. However, urban canyons and dynamic interference make vehicle sensors prone to disturbance, leading to vehicle positioning errors and even failures. To address these issues, an adaptive loosely coupled IMU/GNSS/LiDAR integrated navigation system based on factor graph optimization with sensor weight optimization and fault detection is proposed. First, the factor nodes and system framework are constructed based on error models of sensors, and the optimization method principle is derived. Second, the interactive multiple-model algorithm based on factor graph optimization (IMMFGO) is utilized to calculate and adjust sensor weights for global optimization, which will reduce the impact of disturbed sensors. Finally, a multi-stage fault detection, isolation, and recovery (MSFDIR) strategy is implemented based on the IMMFGO results and IMU pre-integration measurements, which can detect significant sensor faults and optimize the system structure. Vehicle experiments show that our IMMFGO method generally obtains better performance in positioning accuracy by 23.7% compared to adaptive factor graph optimization (AFGO) methods, and the MSFDIR strategy possesses the capability of fault sensor detection, which provides an essential reference for multi-source vehicle navigation systems in urban canyons. [ABSTRACT FROM AUTHOR]

Mars exploration significantly advances our understanding of planetary evolution, the origin of life, and possibilities for Earth's future. It also holds potential for discovering new mineral resources, energy sources, and potential settlement sites. Navigating Mars' complex environment and unknown terrain is a formidable challenge, particularly for autonomous exploration. The hexapod walking robot, inspired by ant morphology, emerges as a robust solution. This design offers diverse gait options, mechanical redundancy, high fault tolerance, and stability, rendering it well suited for Martian terrain. This paper details the development of an ant-inspired hexapod robot, emphasizing its terrain adaptability on Mars. A novel terrain detection method utilizing a convolutional neural network enables efficient identification of varied terrain types through semantic segmentation of visual images. Additionally, we introduce a comprehensive motion performance evaluation index for the hexapod robot, including speed and stability. These metrics facilitate effective performance assessment in different environments. A key innovation is the proposed gait switching method for the hexapod robot. This approach allows seamless transition between gaits while in motion, enhancing the robot's ability to traverse challenging terrains. The experimental results validate the effectiveness of this method. Utilizing gait switching leads to a significant improvement in robot performance and stability—58.5% and 41.4% better than using tripod and amble gaits, respectively. Compared to single tripod, amble, and wave gaits, the comprehensive motion performance indices of the robot improved by 36.3%, 30.6%, and 41.1%, respectively. This study can provide new ideas and methods for the motion evaluation and adaptive gait switching of multilegged robots in complex terrains. It significantly enhances the mobility and adaptability of such robots in challenging environments, contributing valuable knowledge to the field of planetary exploration robotics. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) finds widespread applications in environmental monitoring, disaster management, ship surveillance, and military intelligence. However, existing target detection methods are ineffective in SAR scenes due to the intricate background environments, small target displays, and irregular appearances. To address these challenges, this thesis introduces a target detection model named YOLOv8-FDF, tailored for SAR scenes based on the YOLOv8 architecture. The model effectively incorporates the FADC module to distinguish targets from complex backgrounds and integrates a deformable feature adaptive mechanism to focus on irregular targets. Additionally, this thesis devised a specialized detection head designed to identify small targets in SAR-wide scenes, thereby improving the effectiveness of detecting such targets. The proposed YOLOv8-FDF model is evaluated on the HRSID dataset. Experiment results show a 3.6% improvement in Map75 on both the training and test sets. Furthermore, under the COCO standard, the model achieves improvements of 4.1%, 2.9%, and 5.5% on AP, AP50, and AP75, along with 6.8%, 1.2%, and 1.2% improvements on small, medium, and large-sized ship detection. An accuracy enhancement of 6.8%, 1.0%, and 14.9% is achieved. These experimental findings validate the efficacy of the proposed YOLOv8-FDF model in SAR scenarios.

Monitoring soil salinity is essential for agricultural development and ecological systems in the coastal saline area. The global navigation satellite system (GNSS) interferometry reflectometry (GNSS-IR) can provide new opportunities to retrieve long-term soil salinity at the point-scale theoretically, because the utilized L-band of GNSS-IR is sensitive to soil dielectric permittivity, while the soil salinity can affect its imaginary part. However, the method of soil salinity retrieval has not been researched currently. This study, taking the GNSS-IR data from the station located in the coastal saline area, gives the first evaluation of using this data source for soil salinity retrievals. First, the three interferogram metrics (i.e., phase, amplitude, and reflector height) and their corresponding statistics are extended to include the contributions from the environmental conditions. Then, the model for semi-empirically retrieving soil salinity from these parameters is constructed through the gradient boosting regression tree (GBRT) machine learning (ML) technique. The results show that the phase and height and their corresponding statistics have a relatively strong relationship with the soil salinity as independent variables. Meanwhile, the soil salinity retrieved from the global positioning system and BeiDou navigation satellite system (BDS) agree and correlate well with the in-situ measurements derived from the 5TE sensor (R varies from 0.670 to 0.808, RMSE varies from 1.350 to 1.895 mS/cm, and MAE ranges from 1.049 to 1.749 mS/cm). The work shows the capability of GNSS-IR in retrieving soil salinity and considerably increases the service available from the geodetic-grade GNSS receivers.

Path planning is a critical process in mobile robot navigation. Sampling-based path planning algorithms represented by Rapidly Exploring Random Tree star (RRT*) have gained widespread adoption due to their asymptotic optimality and proven efficiency. However, when applied to intricate environments, characterized by narrow passages and cluttered obstacles, these algorithms encounter challenges in both the initial solution generation and the convergence towards the optimal path, mainly caused by the inefficient sampling strategy, thereby impeding its overall effectiveness. To address these limitations, we introduced Agile-RRT* (A-RRT*), an advancement of RRT* algorithm. Our contributions are twofold: firstly, we introduce an adaptive goal-biased sampling strategy, which employs an adaptive principle for determining the step size on the basis of the goal-biased strategy. This avoids getting trapped in local minima and enhances the efficiency of the initial solution generation. Secondly, we introduce a path optimization approach using a secondary tree and subset-informed sampling, to accelerate the convergence toward the optimal path. It optimizes the path by gradually shrinking the designed elliptical planning space around local states, which effectively narrows down the search space. The experimental results demonstrated that the proposed A-RRT* diminishes the initial solution search time by 71.00% and the sub-optimal solution search time by 82.86% in comparison to RRT*. The A-RRT* exhibits superior performance over RRT*, Informed-RRT*, P-RRT* and Quick-RRT* in terms of soundness and efficiency in narrow and intricate environments. This method could expedite efficient motion planning for drones and mobile robots in complex environments.

This paper introduces an airborne object dataset comprising 22,516 images categorizing four classes of airborne objects: airplanes, helicopters, drones, and birds. The dataset was compiled from YouTube-8 M, Anti-UAV, and Ahmed Mohsen's dataset hosted on Roboflow. Videos were sourced from the first two platforms and converted into individual frames, whereas the latter dataset already consisted of images. Following collection, the dataset underwent labelling and annotation processes utilizing Roboflow's annotation tool, resulting in 7,900 annotations per class. Researchers can leverage this dataset to develop and refine algorithms for airborne object detection and tracking, with potential applications spanning military surveillance, border security, and public safety.

Detecting multiple human targets in indoor scenarios using ultra-wideband (UWB) radar usually involves false detection results caused by the secondary reflections, which might reduce the target detection accuracy and cause a more severe deterioration when the number of targets increases. This article proposed a two-step accuracy improvement method for multitarget detection in environments with multiple human targets of more than three and strong secondary reflections by the surroundings, especially the walls. Based on the rough detection results acquired by the modified CA-CFAR (MCA-CFAR) processing, the first step achieves the primary false alarm suppression using a short-window accumulation in the time domain. Then, the second step applies the decision confidence on the detection results from the first step to assess the reliability of results for improved accuracy. The two-step accuracy improvement could thus have a higher accuracy through cascading false alarm suppression. The effectiveness and accuracy of the proposed algorithm are verified based on the experimental results. [ABSTRACT FROM AUTHOR]

Accurate identification and monitoring of aircraft on the airport surface can assist managers in rational scheduling and reduce the probability of aircraft conflicts, an important application value for constructing a "smart airport." For the airport surface video monitoring, there are small aircraft targets, aircraft obscuring each other, and affected by different weather, the aircraft target clarity is low, and other complex monitoring problems. In this paper, a lightweight model network for video aircraft recognition in airport field video in complex environments is proposed based on SSD network incorporating coordinate attention mechanism. First, the model designs a lightweight feature extraction network with five feature extraction layers. Each feature extraction layer consists of two modules, Block_A and Block_I. The Block_A module incorporates the coordinate attention mechanism and the channel attention mechanism to improve the detection of obscured aircraft and to enhance the detection of small targets. The Block_I module uses multi-scale feature fusion to extract feature information with rich semantic meaning to enhance the feature extraction capability of the network in complex environments. Then, the designed feature extraction network is applied to the improved SSD detection algorithm, which enhances the recognition accuracy of airport field aircraft in complex environments. It was tested and subjected to ablation experiments under different complex weather conditions. The results show that compared with the Faster R-CNN, SSD, and YOLOv3 models, the detection accuracy of the improved model has been increased by 3.2%, 14.3%, and 10.9%, respectively, and the model parameters have been reduced by 83.9%, 73.1%, and 78.2% respectively. Compared with the YOLOv5 model, the model parameters are reduced by 38.9% when the detection accuracy is close, and the detection speed is increased by 24.4%, reaching 38.2fps, which can well meet the demand for real-time detection of aircraft on airport surfaces. [ABSTRACT FROM AUTHOR]

Abstract This article uses ultra‐high performance concrete (UHPC) to repair damaged concrete and analyzes the durability performance of the repaired concrete. Among them, three erosion solutions with a mass concentration of 2.8% NaCl + 0.29% Na2SO4, 5% NaCl, and 5% NaCl + 10% Na2SO4 were designed to soak the concrete specimens for 1 to 3 months. Taking the SWC test group as an example, when the concrete test block undergoes 30 dry wet cycles and the erosion depth is 20 mm, the difference in chloride ion concentration under different diffusion dimensions is not significant. After 90 dry wet cycles, at a depth of 20 mm, the chloride ion concentration inside the concrete in the three‐dimensional diffusion state reached 3 times that of one‐dimensional diffusion, and the chloride ion concentration in the two‐dimensional diffusion state also reached 2 times that of one‐dimensional diffusion. At a depth of 30 mm, a small amount of chloride ion content was also found in the two‐dimensional diffusion and three‐dimensional diffusion.

Buildings in service are severely affected by the complex environment with multiple coupled factors such as high temperatures, humidity, and inorganic salt attack. In this work, the mechanical properties of nano-SiO2-reinforced geopolymer composites (NSGPC) incorporated with varying dosages of polyvinyl alcohol (PVA) fibers were investigated under a complex environment. A simulated environmental chamber was employed to simulate the complex environment with relative humidity, temperature, and NaCl solution concentration of 100%, 45°C, and 5%, respectively. Fly ash/metakaolin geopolymer composites (GPCs) were fabricated by utilizing 1.5% nano-SiO2 by weight and five various dosages of PVA fibers by volume (0, 0.2, 0.4, 0.6, and 0.8%). The compressive strength, tensile strength, elastic modulus, and impact resistance of NSGPC eroded in a simulated environmental chamber for 60 days were determined. Then, the impact of the PVA fiber dosage on the mechanical properties of NSGPC under complex coupled environments was analyzed. In addition, scanning electron microscopy (SEM) was employed to evaluate and analyze the microstructural behavior of NSGPC under complex environments. Results indicated that the compressive strength, tensile strength, elastic modulus, and impact resistance of NSGPC increased with increasing PVA fiber to 0.6% and then decreased with a continuous increase to 0.8% but remained higher than those of the reference specimen. NSGPC exhibited the best performance at a PVA fiber dosage of 0.6%, which increased by 13.3, 12.0, 17.2, and 522%, respectively. The outcomes of SEM analysis indicated that the usage of PVA fiber and NS remarkably improved the mechanical properties and microstructural behavior of GPC by making the inner structure of GPCs more robust and compact under a complex environment. The outcomes of this work can provide theoretical guidance for buildings serving under a complex environment.

Marine anchor buoys, as fixed-point profile observation platforms, are highly susceptible to the threat of ship collisions. Installing cameras on buoys can effectively monitor and collect evidence from ships. However, when using a camera to capture images, it is often affected by the continuous shaking of buoys and rainy and foggy weather, resulting in problems such as blurred images and rain and fog occlusion. To address these problems, this paper proposes an improved YOLOv8 algorithm. Firstly, the polarized self-attention (PSA) mechanism is introduced to preserve the high-resolution features of the original deep convolutional neural network and solve the problem of image spatial resolution degradation caused by shaking. Secondly, by introducing the multi-head self-attention (MHSA) mechanism in the neck network, the interference of rain and fog background is weakened, and the feature fusion ability of the network is improved. Finally, in the head network, this model combines additional small object detection heads to improve the accuracy of small object detection. Additionally, to enhance the algorithm’s adaptability to camera detection scenarios, this paper simulates scenarios, including shaking blur, rain, and foggy conditions. In the end, numerous comparative experiments on a self-made dataset show that the algorithm proposed in this study achieved 94.2% mAP50 and 73.2% mAP50:95 in various complex environments, which is superior to other advanced object detection algorithms.

(1) Background: In real road scenarios, various complex environmental conditions may occur, including bright lights, nighttime, rain, and snow. In such a complex environment for detecting pole-shaped obstacles, it is easy to lose the feature information. A high rate of leakage detection, false positives, and measurement errors are generated as a result. (2) Methods: The first part of this paper utilizes the improved YOLOv5 algorithm to detect and classify pole-shaped obstacles. Then, the identified target frame information is combined with binocular stereo matching to obtain more accurate distance information. (3) Results: The experimental results demonstrate that this method achieves a mean average precision (mAP) of 97.4% for detecting pole-shaped obstacles, which is 3.1% higher than the original model. The image inference time is only 1.6 ms, which is 1.8 ms faster than the original algorithm. Additionally, the model size is only 19.0 MB. Furthermore, the range error of this system is less than 7% within the range of 3–15 m. (4) Conclusions: Therefore, the algorithm not only achieves real-time and accurate identification and classification but also ensures precise measurement within a specific range. Meanwhile, the model is lightweight and better suited for deploying sensing systems. [ABSTRACT FROM AUTHOR]

Swarms of self-propelled micromotors can mimic the processes of natural systems and construct artificial intelligent materials to perform complex collective behaviors. Compared to self-propelled Janus micromotors, the isotropic colloid motors, also called micromotors or microswimmers, have advantages in self-assembly to form micromotor swarms, which are efficient in resistance to external disturbance and the delivery of large quantity of cargos. In this minireview, we summarize the fundamental principles and interactions for the assembly of isotropic active particles to generate micromotor swarms. Recent discoveries based on either catalytic or external physical field-stimulated micromotor swarms are also presented. Then, the strategy for the reconstruction and motion control of micromotor swarms in complex environments, including narrow channels, maze, raised obstacles, and high steps/low gaps, is summarized. Finally, we outline the future directions of micromotor swarms and the remaining challenges and opportunities. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite System (GNSS) is an important technical tool for building deformation monitoring, but in complex environments such as urban canyons, the GNSS signals received by monitoring stations are susceptible to severe multipath errors, resulting in a significant decrease in positioning precision. The multipath hemispherical map (MHM) model is a common method to mitigate multipath errors in GNSS, but its performance can be compromised by high-frequency multipath errors, outliers, and non-line-of-sight signals caused by nearby obstructions. In this study, an MHM model with geographic cut-off elevation constraints is proposed, which considers signal quality and terrain topography surrounding the station to mask those unsatisfactory signals, and leverages the advantages of the MHM model for mitigating low-frequency multipath. To validate the effectiveness of the proposed method, a GNSS deformation monitoring experiment was carried out in an urban environment. The results show that the root mean square (RMS) values of horizontal and vertical positioning errors for the ambiguity-fixed solution using the proposed method are 0.40 and 0.68 cm, respectively, showing improvements of 65.9% and 63.4% compared to the solution without multipath correction (M0), 43.8% and 37.0% to the solution using traditional MHM model (M1), and 63.2% and 50.0% to the solution using geographic cut-off elevation model (M2), respectively. Correspondingly, the ambiguity fixing rate increased from 84.95%, 95.31% and 98.97% of M0, M1 and M2 solutions to 99.95%. The proposed MHM model with geographic cut-off elevation constraints can improve the positioning precision, and thus would be helpful for GNSS deformation monitoring in complex environments. [ABSTRACT FROM AUTHOR]

Efficient navigation is crucial for intelligent mobile robots in complex environments. This paper introduces an innovative approach that seamlessly integrates advanced machine learning techniques to enhance mobile robot communication and path planning efficiency. Our method combines supervised and unsupervised learning, utilizing spline interpolation to generate smooth paths with minimal directional changes. Experimental validation with a differential drive mobile robot demonstrates exceptional trajectory control efficiency. We also explore Motion Planning Networks (MPNets), a neural planner that processes raw point-cloud data from depth sensors. Our tests demonstrate MPNet’s ability to create optimal paths using the Probabilistic Roadmap (PRM) method. We highlight the importance of correctly setting parameters for reliable path planning with MPNet and evaluate the algorithm on various path types. Our experiments confirm that the trajectory control algorithm works effectively, consistently providing precise and efficient trajectory control for the robot.

In this study, our aim is to find an effective method to solve the problem of disease similarity caused by multiple diseases occurring on the same leaf. This study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases. We conducted comparisons and analyses on the impact of various factors, such as training methods, data expansion methods, optimizer selection, image background, and other factors, on model performance. The findings suggest that utilizing offline expansion and transfer learning to fine-tune all layer parameters can enhance the model’s classification performance, while complex image backgrounds significantly influence model performance. Additionally, the optimized RegNet network model demonstrates good generalization ability for both datasets, achieving testing accuracies of 93.85% and 99.23%, respectively. These results highlight the potential of the optimized RegNet network model to achieve high-precision identification of different diseases on the same apple leaf under complex field backgrounds. This will be of great significance for intelligent disease identification in apple orchards in the future.

Accurate and stable positioning is significant for vehicle navigation systems, especially in complex urban environments. However, urban canyons and dynamic interference make vehicle sensors prone to disturbance, leading to vehicle positioning errors and even failures. To address these issues, an adaptive loosely coupled IMU/GNSS/LiDAR integrated navigation system based on factor graph optimization with sensor weight optimization and fault detection is proposed. First, the factor nodes and system framework are constructed based on error models of sensors, and the optimization method principle is derived. Second, the interactive multiple-model algorithm based on factor graph optimization (IMMFGO) is utilized to calculate and adjust sensor weights for global optimization, which will reduce the impact of disturbed sensors. Finally, a multi-stage fault detection, isolation, and recovery (MSFDIR) strategy is implemented based on the IMMFGO results and IMU pre-integration measurements, which can detect significant sensor faults and optimize the system structure. Vehicle experiments show that our IMMFGO method generally obtains better performance in positioning accuracy by 23.7% compared to adaptive factor graph optimization (AFGO) methods, and the MSFDIR strategy possesses the capability of fault sensor detection, which provides an essential reference for multi-source vehicle navigation systems in urban canyons.

Gesture recognition nowadays has grabbed the attention of researchers as they represent human behaviour in multiple practical ways. Amongst a variety of gestures available, hand gestures play an essential role in the field of human‐computer interaction when recognised efficiently in complex and dynamic environments. In this paper, we propose a dynamic hand gesture recognition system to recognise hand gestures appearing in different indoor and outdoor environments. Hand detection and tracking uses a two‐level system resulting in the formation of gesture trajectory in challenging conditions in which existing detection and tracking algorithms could not do so. A set of 45 features is provided as input to the various classification techniques. The redundancy problem has been reduced by selecting a set of optimum features using the analysis of variance method, which ranks the list of features. An incremental feature selection technique calculates recognition accuracy by selecting features according to rankings. This system provides an accuracy of 96.32% when used with machine learning and 97.5% when used with deep learning techniques. Recognition accuracy is calculated for various environments, including an extra hand, multiple persons in the video frame, and outdoor environment. All machine‐learning classifiers are combined using classifier combination to calculate the accuracy according to the majority‐voting rule. Based on the experimental results, it has been observed that deep learning provides better results compared to machine learning. [ABSTRACT FROM AUTHOR]

The indoor environment is typically a complex time-varying environment. At present, the problem of indoor modeling is still a hot research topic for scholars at home and abroad. This paper primarily studies indoor time-varying space. On the basis of the Beidou grid framework and time coding model, in the first scenario, a local space subdivision framework based on Beidou is proposed. The necessity of local space subdivision framework is analyzed. In the second scenario, based on the time coding model needle, a local temporal subdivision model, more suitable for a short time domain, is proposed. Then, for the spatial modeling of an indoor time-varying environment, an indoor time-varying mesh frame based on global subdivision, local space subdivision, and local time subdivision is proposed. Using this framework, the indoor environment is represented by the space–time grid, and the basic storage data structure is designed. Finally, the experiment of local subdivision coding in the indoor space–time grid, indoor space–time grid modeling, and an organization experiment is carried out using real data and simulation data. The experimental results verify the feasibility and correctness of the encoding and decoding algorithm of local subdivision encoding in space–time encoding and the calculation algorithm of the space–time relationship. The experimental results also verify the multi-space organization and the management ability of the indoor space–time grid model. [ABSTRACT FROM AUTHOR]

The online automated maturity grading and counting of tomato fruits has a certain promoting effect on digital supervision of fruit growth status and unmanned precision operations during the planting process. The traditional grading and counting of tomato fruit maturity is mostly done manually, which is time-consuming and laborious work, and its precision depends on the accuracy of human eye observation. The combination of artificial intelligence and machine vision has to some extent solved this problem. In this work, firstly, a digital camera is used to obtain tomato fruit image datasets, taking into account factors such as occlusion and external light interference. Secondly, based on the tomato maturity grading task requirements, the MHSA attention mechanism is adopted to improve YOLOv8's backbone to enhance the network's ability to extract diverse features. The Precision, Recall, F1-score, and mAP50 of the tomato fruit maturity grading model constructed based on MHSA-YOLOv8 were 0.806, 0.807, 0.806, and 0.864, respectively, which improved the performance of the model with a slight increase in model size. Finally, thanks to the excellent performance of MHSA-YOLOv8, the Precision, Recall, F1-score, and mAP50 of the constructed counting models were 0.990, 0.960, 0.975, and 0.916, respectively. The tomato maturity grading and counting model constructed in this study is not only suitable for online detection but also for offline detection, which greatly helps to improve the harvesting and grading efficiency of tomato growers. The main innovations of this study are summarized as follows: (1) a tomato maturity grading and counting dataset collected from actual production scenarios was constructed; (2) considering the complexity of the environment, this study proposes a new object detection method, MHSA-YOLOv8, and constructs tomato maturity grading models and counting models, respectively; (3) the models constructed in this study are not only suitable for online grading and counting but also for offline grading and counting. [ABSTRACT FROM AUTHOR]

The focus of car-following models is to analyze the microscopic characteristics of traffic flows, with particular attention given to the interaction between adjacent vehicles. This paper presents a systematic review of existing studies on car-following models, with an emphasis on the behavior of both human-driven vehicles (HDVs) and autonomous vehicles (AVs). We classify car-following models based on their applicable background and structure. By considering driving behavior and specific model parameters, we identify the advantages and limitations of each microscopic simulation model in terms of accuracy and continuity. We also discuss model calibration methods, stability analysis, and the impact of complex traffic environments on the car-following process. Finally, we present detailed discussions of each model's features and provide recommendations based on reviewed works and development trends for future research, including mixed traffic flow composed of AVs and HDVs. [ABSTRACT FROM AUTHOR]

To improve the precision of intelligent sugarcane harvesting, and to meet the requirements of high precision and low complexity for use with embedded devices, a lightweight model called MobileNet v2-YOLO v5s for the real-time detection of sugarcane stem nodes in complex natural environments was developed. In this study, images of sugarcane stem nodes in a complex natural environment were collected and a dataset containing 12,600 images was constructed using a data extension process. The MobileNet network was introduced to replace the backbone of the YOLO v5s algorithm and the improved algorithm was used to train the MobileNet-YOLO v5s sugarcane stem node identification model. In experiments aiming to verify the advantages of the lightweight model, MobileNet v2-YOLO v5s achieved the best combination of high precision and low complexity. Its AP was decreased by only 0.8%, while its complexity was reduced by 40% compared to YOLO v5s. It also had a fast detection speed of 4.4 ms on a Dell workstation P7920. Therefore, 11 other models were selected for comparative experiments to demonstrate the superiority of MobileNet v2-YOLO v5s. Finally, TensorRT accelerated optimization tests, execution tests, and real-time detection tests were performed on Jetson Nano. The results showed that the optimised MobileNet v2-YOLO v5s outperformed YOLO v5s in terms of identification, lightweight and detection speed on embedded devices. Overall, MobileNet v2-YOLO v5s model meets the requirements of embedded devices and can provide a visual identification method for intelligent sugarcane harvesting.

Detecting multiple human targets in indoor scenarios using ultra-wideband (UWB) radar usually involves false detection results caused by the secondary reflections, which might reduce the target detection accuracy and cause a more severe deterioration when the number of targets increases. This article proposed a two-step accuracy improvement method for multitarget detection in environments with multiple human targets of more than three and strong secondary reflections by the surroundings, especially the walls. Based on the rough detection results acquired by the modified CA-CFAR (MCA-CFAR) processing, the first step achieves the primary false alarm suppression using a short-window accumulation in the time domain. Then, the second step applies the decision confidence on the detection results from the first step to assess the reliability of results for improved accuracy. The two-step accuracy improvement could thus have a higher accuracy through cascading false alarm suppression. The effectiveness and accuracy of the proposed algorithm are verified based on the experimental results.

This study aims to address the challenge of low-cost hardware implementation of a combined backstepping with fractional order PID (FOPID) controller for mobile robots in real-time applications. Moreover, this work proposes a self-designed mobile robot prototype that is easy to realize, low in cost, spares time, and reduces human effort. This robot platform was equipped with two DC motors with quadratic encoders and two passive wheels, controlled by an Arduino mega, where the software code was developed in the Matlab-Simulink environment, using Simulink support package for Arduino. Four case studies were conducted to demonstrate the effectiveness of the suggested methodology. Experimental results demonstrate improved trajectory tracking performance with less tracking error and smooth control efforts, and is capable of handling trajectories with continuous and non-continuous gradients. [ABSTRACT FROM AUTHOR]

Abstract The paper presents a novel 2D geometrical path plan algorithm that reduces calculation load and time by filtering obstacles before path planning starts by the newly introduced hexagon filter and also while path search is in progress. Unlike other methods that use only obstacle filtering before path planning starts. The suggested algorithm was able to solve a randomly created maze that contains 400 obstacles with 800 nodes, which was considered before, as next to impossible to solve. This is because computational time is proportional to n2log(n) where n is the number of obstacles, node suggested algorithm reduced the computational time to about 1 in 2500 times compared to the best of (ESOVG, DVG or ECoVG). In addition, the suggested algorithm can be used in the case of a fixed start point and different target points (e.g. a swarm of robots leaving from the same start point with different targets).

The accurate segmentation of apple leaf disease spots is the key to identifying the classification of apple leaf diseases and disease severity. Therefore, a DeepLabV3+ semantic segmentation network model with an actors spatial pyramid pool module (ASPP) was proposed to achieve effective extraction of apple leaf lesion features and to improve the apple leaf disease recognition and disease severity diagnosis compared with the classical semantic segmentation network models PSPNet and GCNet. In addition, the effects of the learning rate, optimizer, and backbone network on the performance of the DeepLabV3+ network model with the best performance were analyzed. The experimental results show that the mean pixel accuracy (MPA) and mean intersection over union (MIoU) of the model reached 97.26% and 83.85%, respectively. After being deployed into the smartphone platform, the detection time of the detection system was 9s per image for the portable and intelligent diagnostics of apple leaf diseases. The transfer learning method provided the possibility of quickly acquiring a high-performance model under the condition of small datasets. The research results can provide a precise guide for the prevention and precise control of apple diseases in fields. [ABSTRACT FROM AUTHOR]

We propose a hierarchical cognitive navigation model (HCNM) to improve the self-learning and self-adaptive ability of mobile robots in unknown and complex environments. The HCNM model adopts the divide and conquers approach by dividing the path planning task into different levels of sub-tasks in complex environments and solves each sub-task in a smaller state subspace to decrease the state space dimensions. The HCNM model imitates animal asymptotic properties through the study of thermodynamic processes and designs a cognitive learning algorithm to achieve online optimum search strategies. We prove that the learning algorithm designed ensures that the cognitive model can converge to the optimal behavior path with probability one. Robot navigation is studied on the basis of the cognitive process. The experimental results show that the HCNM model has strong adaptability in unknown and environment, and the navigation path is clearer and the convergence time is better. Among them, the convergence time of HCNM model is 25 s, which is 86.5% lower than that of HRLM model. The HCNM model studied in this paper adopts a hierarchical structure, which reduces the learning difficulty and accelerates the learning speed in the unknown environment. [ABSTRACT FROM AUTHOR]

Smart vehicles with embedded Autonomous Vehicle (AV) technologies are currently equipped with different types of mounted sensors, aiming to ensure safe movement for both passengers and other road users. The sensors' ability to capture and gather data to be synchronically interpreted by neural networks for a clear understanding of the surroundings is influenced by lighting conditions, such as natural lighting levels, artificial lighting effects, time of day, and various weather conditions, such as rain, fog, haze, and extreme temperatures. Such changing environmental conditions are also known as complex environments. In addition, the appearance of other road users is varied and relative to the vehicle's perspective; thus, the identification of features in a complex background is still a challenge. This paper presents a pre-processing method using multi-sensorial RGB and thermal camera data. The aim is to handle issues arising from the combined inputs of multiple sensors, such as data registration and value unification. Foreground refinement, followed by a novel statistical anomaly-based feature extraction prior to image fusion, is presented. The results met the AV challenges in CNN's classification. The reduction of the collected data and its variation level was achieved. The unified physical value contributed to the robustness of input data, providing a better perception of the surroundings under varied environmental conditions in mixed datasets for day and night images. The method presented uses fused images, robustly enriched with texture and feature depth and reduced dependency on lighting or environmental conditions, as an input for a CNN. The CNN was capable of extracting and classifying dynamic objects as vehicles and pedestrians from the complex background in both daylight and nightlight images. [ABSTRACT FROM AUTHOR]

Because of the high similarity of leaves of different Cerasus humilis varieties, it is difficult to identify them with the naked eye. In this study, the leaves of four different Cerasus humilis varieties collected in the field were used as the research objects, and a new leaf recognition model based on the improved lightweight convolution neural network model EfficientNet-B0 was proposed. Firstly, the performance of the network models Efficientnet-B0 and ResNet50, GoogleNet, ShuffleNet, and MobileNetV3 were compared based on two different learning methods. Then, the influence of different optimizers on model recognition accuracy was compared based on the optimal model. Finally, different learning rates were used to optimize the optimal model. The results show that the recognition rate of the proposed Efficientnet-B0 +Ranger+0.0005 model was up to 86.9%, which was 2.23% higher than that of the original Efficientnet-B0 model. The results show that this method can effectively improve the recognition accuracy of Cerasus humilis auriculate leaves, which can provide a reference for the deployment of the leaf identification model of Cerasus humilis variety on the mobile terminal. [ABSTRACT FROM AUTHOR]

Swarms of self-propelled micromotors can mimic the processes of natural systems and construct artificial intelligent materials to perform complex collective behaviors. Compared to self-propelled Janus micromotors, the isotropic colloid motors, also called micromotors or microswimmers, have advantages in self-assembly to form micromotor swarms, which are efficient in resistance to external disturbance and the delivery of large quantity of cargos. In this minireview, we summarize the fundamental principles and interactions for the assembly of isotropic active particles to generate micromotor swarms. Recent discoveries based on either catalytic or external physical field-stimulated micromotor swarms are also presented. Then, the strategy for the reconstruction and motion control of micromotor swarms in complex environments, including narrow channels, maze, raised obstacles, and high steps/low gaps, is summarized. Finally, we outline the future directions of micromotor swarms and the remaining challenges and opportunities.

(1) Background: In real road scenarios, various complex environmental conditions may occur, including bright lights, nighttime, rain, and snow. In such a complex environment for detecting pole-shaped obstacles, it is easy to lose the feature information. A high rate of leakage detection, false positives, and measurement errors are generated as a result. (2) Methods: The first part of this paper utilizes the improved YOLOv5 algorithm to detect and classify pole-shaped obstacles. Then, the identified target frame information is combined with binocular stereo matching to obtain more accurate distance information. (3) Results: The experimental results demonstrate that this method achieves a mean average precision (mAP) of 97.4% for detecting pole-shaped obstacles, which is 3.1% higher than the original model. The image inference time is only 1.6 ms, which is 1.8 ms faster than the original algorithm. Additionally, the model size is only 19.0 MB. Furthermore, the range error of this system is less than 7% within the range of 3–15 m. (4) Conclusions: Therefore, the algorithm not only achieves real-time and accurate identification and classification but also ensures precise measurement within a specific range. Meanwhile, the model is lightweight and better suited for deploying sensing systems.

In this paper, considering the heterogeneity of travelers' decision-making behavior caused by travel environment factors, thus affecting the choice of travel path, the theories and methods of travel path choice based on improved cumulative prospect theory (ICPT) in complex environment were proposed. On the basis of cumulative prospect theory (CPT), the value function was improved, and the parameter value range was enlarged. The nonlinear curve of value function and weight function of cumulative prospect theory was fitted through thousands of data tests and experiments. Then according to the decision preference, the decision makers were divided into different categories and the reference point value relationship of heterogeneous decision makers was found. In this paper, fuzzy travel time reference point and periodic dynamic risk degree reference point were set up, and a dynamic path selection model based on heterogeneous double reference point was established to improve the cumulative prospect value. Taking the highway network in Sichuan-Tibet region for example, the optimal path selection scheme of heterogeneous travel groups under the complex environmental factors such as debris flow and landslide in each time stage was studied, and the influence of preference parameter of travel time and risk degree on path choice was analyzed, and then the parameter sensitivity in the cumulative prospect theory (ICPT) was analyzed. The research results verified the rationality of the improved theory and method proposed in this study, which not only provide a new way of thinking for the study of travel path choice in complex environment but also provide theoretical guidance value for supporting regional traffic planning and construction in complex environment. [ABSTRACT FROM AUTHOR]

The paper presents a novel 2D geometrical path plan algorithm that reduces calculation load and time by filtering obstacles before path planning starts by the newly introduced hexagon filter and also while path search is in progress. Unlike other methods that use only obstacle filtering before path planning starts. The suggested algorithm was able to solve a randomly created maze that contains 400 obstacles with 800 nodes, which was considered before, as next to impossible to solve. This is because computational time is proportional to n2log(n) where n is the number of obstacles, node suggested algorithm reduced the computational time to about 1 in 2500 times compared to the best of (ESOVG, DVG or ECoVG). In addition, the suggested algorithm can be used in the case of a fixed start point and different target points (e.g. a swarm of robots leaving from the same start point with different targets). [ABSTRACT FROM AUTHOR]