Journal of Field Robotics最新文献_第8页

Change Detection of Non-Fixed Targets in Low-Altitude Unmanned Aerial Vehicle Inspections Based on Style Transfer 基于风格迁移的低空无人机检测非固定目标变化检测

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-18 DOI: 10.1002/rob.22536

Feng Chen, Huiqin Wang, Ke Wang

{"title":"Change Detection of Non-Fixed Targets in Low-Altitude Unmanned Aerial Vehicle Inspections Based on Style Transfer","authors":"Feng Chen, Huiqin Wang, Ke Wang","doi":"10.1002/rob.22536","DOIUrl":"https://doi.org/10.1002/rob.22536","url":null,"abstract":"<div>\u0000 \u0000 <p>With the rapid development of UAV technology, the demand for detecting changes in targets during low-altitude inspections is increasing. In low-altitude inspection scenarios, natural changes account for a much larger proportion than unnatural changes. Unsupervised change detection based on statistical and clustering algorithms often results in false detections of the more prevalent natural changes, leading to decreased detection accuracy. To address this issue, this paper proposes a low-altitude inspection change detection model (LPCD) based on style transfer. The model extracts features through an encoder and uses differential attention to analyze style differences. An adaptive instance normalization (AdaIN) module in the decoder ensures natural style consistency. Reconstruction loss between generated and source images in unnatural change regions is used with mapping and thresholding to improve the detection of unnatural changes. Compared to existing change detection algorithms in the remote sensing domain, the proposed model achieves improvements in accuracy of 0.01 and 0.01 on two data sets, respectively. <i>F</i>1 scores increase by 0.14 and 0.3, and the false alarm rate is reduced to 0.025 and 0.021.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2764-2776"},"PeriodicalIF":5.2,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Integrated Intelligent Autonomous Driving Bulldozer System: Pose Estimation, Object Detection, and Work Planning for Dumping Operations 一种集成的智能自动驾驶推土机系统：姿态估计、目标检测和倾倒作业工作计划

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-10 DOI: 10.1002/rob.22542

Gang Peng, Qiang Gao, Xingyu Liu, Yicheng Zhou, Hangqi Duan, ZhanGang Wu, Bin Hu, Xukang Zhu, Daosheng Xu

{"title":"An Integrated Intelligent Autonomous Driving Bulldozer System: Pose Estimation, Object Detection, and Work Planning for Dumping Operations","authors":"Gang Peng, Qiang Gao, Xingyu Liu, Yicheng Zhou, Hangqi Duan, ZhanGang Wu, Bin Hu, Xukang Zhu, Daosheng Xu","doi":"10.1002/rob.22542","DOIUrl":"https://doi.org/10.1002/rob.22542","url":null,"abstract":"<div>\u0000 \u0000 <p>In recent years, the rapid advancement of automation control and intelligent sensing technologies has positioned autonomous driving as a focal point of interest for both academia and industry. As core equipment in modern construction and industrial production, engineering machinery urgently requires intelligent transformation. To promote the intelligent development of engineering machinery, we have designed an integrated intelligent autonomous driving bulldozer system, which can be extended to various types of engineering machinery. For the specific mine dumping operation environment, we propose a multisensor fusion pose estimation algorithm framework based on the Global Navigation Satellite System, inertial measurement unit, visual cameras, and light detection and ranging (LiDAR) to address issues arising from sensor failures under harsh construction conditions. Furthermore, to ensure safety during task execution, we design a three-dimensional object detection method based on the optimal observation plane from LiDAR data. By integrating pose estimation and environmental perception results, we develop a comprehensive work planning and path-tracking algorithm to maintain task efficiency. Experimental results demonstrate that our intelligent autonomous driving bulldozer system performs excellently under various working conditions. The accuracy of its pose estimation, object detection, and path tracking meets the requirements of actual construction environments, showcasing its significant potential in engineering applications.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2740-2763"},"PeriodicalIF":5.2,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Singularity-Free Guiding Vector Field Over Bézier's Curves Applied to Rovers Path Planning and Path Following bzier曲线上无奇异引导向量场在漫游者路径规划和路径跟踪中的应用

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-07 DOI: 10.1002/rob.22541

Alfredo González-Calvin, Lía García-Pérez, Juan F. Jiménez

{"title":"Singularity-Free Guiding Vector Field Over Bézier's Curves Applied to Rovers Path Planning and Path Following","authors":"Alfredo González-Calvin, Lía García-Pérez, Juan F. Jiménez","doi":"10.1002/rob.22541","DOIUrl":"https://doi.org/10.1002/rob.22541","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper presents a guidance algorithm for solving the problem of following parametric paths, as well as a curvature-varying speed setpoint for land-based car-type wheeled mobile robots (WMRs). The guidance algorithm relies on singularity-free guiding vector fields (SF-GVFs). This novel guiding vector field (GVF) approach expands the desired robot path and the GVF to a higher dimensional space, in which an angular control function can be found to ensure global asymptotic convergence to the desired parametric path while avoiding field singularities. In SF-GVF, paths should follow a parametric definition. This feature makes using Bezier's curves attractive to define the robot's desired path. The curvature-varying speed setpoint, combined with the guidance algorithm, eases the convergence to the path when physical restrictions exist, such as minimal turning radius or maximal lateral acceleration. We provide theoretical results, simulations, and outdoor experiments using a WMR platform assembled with off-the-shelf components. The small rover (WMR) selected provides an easy-to-use nonholonomic platform for the experiments. The results could be extrapolated to full-scale or more complex vehicles, providing the necessary vehicle control system adaptations, while the GVF algorithm would remain the same.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2720-2739"},"PeriodicalIF":5.2,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a Semiautonomous Young Spruce Forest Late Cleaning 半自主的年轻云杉林后期清理

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-04 DOI: 10.1002/rob.22539

Issouf Ouattara, Jyri Hallikas, Heikki Hyyti, Arto Visala

{"title":"Towards a Semiautonomous Young Spruce Forest Late Cleaning","authors":"Issouf Ouattara, Jyri Hallikas, Heikki Hyyti, Arto Visala","doi":"10.1002/rob.22539","DOIUrl":"https://doi.org/10.1002/rob.22539","url":null,"abstract":"<p>Cleaning a seedling spruce stand is an important silvicultural task required to help the young spruce trees thrive. It is usually manual work with a clearing saw. Mechanized solutions have been proposed, but they have not worked out well, since the driver has challenges in seeing the seedling trees that should be left growing. Instead, we demonstrate that a semiautonomous forest machine could do the cleaning operation using a suitable map of the environment. We propose using a low-cost unmanned aerial vehicle (UAV) to map the area beforehand, and a real-time perception system onboard the forest machine performing the semiautonomous late cleaning of a seedling spruce stand with the help of a driver using a dedicated human–machine interface (HMI). In the proposed solution, overlapping color images are collected by a UAV to build a map that integrates both color and depth information. This map is used to detect the young spruce trees, among other species. We also propose a graph-based point-cloud matching method, which can precisely locate the forest machine on the map using forest machine-mounted sensors. An HMI is developed to improve the situational awareness of the operator in the forest machine cabin during the cleaning process. The proposed integrated solution has been demonstrated in a real seedling spruce forest.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2701-2719"},"PeriodicalIF":5.2,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22539","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Searching for an Accurate Robot Calibration via Improved Levenberg–Marquardt and Radial Basis Function System 基于改进Levenberg-Marquardt和径向基函数系统的机器人精确标定研究

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-02 DOI: 10.1002/rob.22543

Zhibin Li, Xun Deng, Tinghui Chen, Yuhang Yang, Linlin Chen, Xiwen Yang, Zhenzhen Hu, Lun Hu, Pengwei Hu, Shuai Li, Xin Luo

{"title":"Searching for an Accurate Robot Calibration via Improved Levenberg–Marquardt and Radial Basis Function System","authors":"Zhibin Li, Xun Deng, Tinghui Chen, Yuhang Yang, Linlin Chen, Xiwen Yang, Zhenzhen Hu, Lun Hu, Pengwei Hu, Shuai Li, Xin Luo","doi":"10.1002/rob.22543","DOIUrl":"https://doi.org/10.1002/rob.22543","url":null,"abstract":"<div>\u0000 \u0000 <p>Robots are frequently utilized in manufacturing, aviation, and other industries, which enhance industrial production efficiency and quality. Specifically, robots perform high-precision tasks like welding, assembly and material handling, which reduce the intensity of manual labor in factories. In the logistics field, robots automatically sort and deliver goods, thereby speeding up supply chain operations. However, the prolonged operation of robots suffers from a decline in positioning accuracy, which makes them unable to satisfy task requirements. To address this challenging issue, this study designs an efficient calibration system integrating the Levenberg–Marquardt algorithm with fuzzy proportion integration differentiation controller and radial basis function neural network. The innovations of this method include: (1) integrating the fuzzy proportion integration differentiation controller into the updating rules of Levenberg–Marquardt algorithm, which further enhances the identification performance of kinematic errors; (2) adopting the radial basis function neural network to handle the robot dynamic errors, which addresses the complexity of dynamic error sources. Extensively experimental robot positioning points are gathered on an HSR JR680 robot, and then experimental validations are conducted by using the designed calibration system. The experiments indicate that the developed algorithm outperforms these existing advanced algorithms.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2691-2700"},"PeriodicalIF":5.2,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Independent Soft Actor-Critic Deep Reinforcement Learning for UAV Cooperative Air Combat Maneuvering Decision-Making 无人机协同空战机动决策的独立软评价深度强化学习

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-02 DOI: 10.1002/rob.22538

Haolin Li, Delin Luo, Haibin Duan

引用次数: 0

Optimization-Based Geometric Enhancement and Motion Estimation for Non-Cooperative Spacecrafts 基于优化的非合作航天器几何增强与运动估计

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-02 DOI: 10.1002/rob.22540

Chi Zhang, Yu Han, Qiaokang Liang, Jianqing Peng

{"title":"Optimization-Based Geometric Enhancement and Motion Estimation for Non-Cooperative Spacecrafts","authors":"Chi Zhang, Yu Han, Qiaokang Liang, Jianqing Peng","doi":"10.1002/rob.22540","DOIUrl":"https://doi.org/10.1002/rob.22540","url":null,"abstract":"<div>\u0000 \u0000 <p>The state estimation of non-cooperative spacecrafts is a crucial prerequisite for on-orbit services. Aiming at the challenges in the fusion-based scheme with monocular vision and sparse point cloud, an optimization-based method of geometric enhancement and motion estimation is proposed in this paper. First, with the novel idea of geometric shape representation using simple features, a real-time segmentation framework is established. Differing from segmentation models, it can guarantee both complete segmentation and high inference speed. Second, given the assumption of local shared planes, a new label-free algorithm of point cloud densification is developed with an explainable model. To improve its efficiency, a curvature-guided strategy is employed to sample depth-incomplete points conducive to feature enhancement. Compared with sparse point clouds, it shows higher pose observation accuracy. Third, a truncation compensator is built to fit the high-order terms of a nonlinear state transition model with online optimization, which mitigates the impairment in a priori estimation. Combined with the adaptive extended Kalman filter, the motion can be estimated with fewer errors. Finally, the proposed method is validated through comparative simulations and ground experiments.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2671-2690"},"PeriodicalIF":5.2,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal Trajectory Generation of Various English Alphabets Using Deep Learning Model for 3-R Manipulator 基于深度学习模型的3-R机械臂各种英文字母最优轨迹生成

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-03-02 DOI: 10.1002/rob.22537

Swapnil Murai, Rahul Das Vairagi, Vijay Bhaskar Semwal

{"title":"Optimal Trajectory Generation of Various English Alphabets Using Deep Learning Model for 3-R Manipulator","authors":"Swapnil Murai, Rahul Das Vairagi, Vijay Bhaskar Semwal","doi":"10.1002/rob.22537","DOIUrl":"https://doi.org/10.1002/rob.22537","url":null,"abstract":"<div>\u0000 \u0000 <p>The modern era of medicine and industry extensively utilizes the manipulator's hand for a variety of vital automated activities. Handling a manipulator hand is a complex task. Due to the nonlinear characteristics of inverse kinematics (IK) mathematical model, inverse kinematics is a time-consuming and laborious procedure, making it difficult to provide a mathematical solution. This research employs a 3-R (revolute) robotic manipulator to achieve joint trajectories for drawing different alphabets and shapes. The IK problem has been solved using a hybrid model. The model is a hybrid of an artificial neural network (ANN) based model, the forward and backward reaching inverse kinematics (FABRIK) technique provides stability and the control barrier function (CBF) with the Lyapunov function. Using the proposed model, coordinates for different alphabets and shapes within the confined workspace were calculated. The ANN automatically obtains specific end-effector coordinates. This model combines the CBF with the Lyapunov function to ensure that a safe region is selected. The accuracy of the model exceeds 99.5%. We have calculated the mean square error (MSE) as 1.66, the root mean square error (RMSE) as 1.25, and the mean absolute error (MAE) as 0.96 for our model. The error between the model's predicted and actual coordinates also demonstrates letter coordinates and shapes drawn using a physical 3R manipulator model. As a result, this method can be applied to precisely estimate the angles in intricate 3DoF inverse kinematics models.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2639-2655"},"PeriodicalIF":5.2,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Flow Memory Effect on Open-Frame Remotely Operated Vehicle Motion 开放式遥控车辆运动的流动记忆效应

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-02-23 DOI: 10.1002/rob.22535

Ruinan Guo, Yingfei Zan, Wenzhi Fu, Chenlei Cao, Duanfeng Han, Nan Sun

{"title":"Flow Memory Effect on Open-Frame Remotely Operated Vehicle Motion","authors":"Ruinan Guo, Yingfei Zan, Wenzhi Fu, Chenlei Cao, Duanfeng Han, Nan Sun","doi":"10.1002/rob.22535","DOIUrl":"https://doi.org/10.1002/rob.22535","url":null,"abstract":"<p>The flow memory effect is a kind of viscous force caused by acceleration between continuous phases and underwater vehicles and the development of the boundary layer near the interfacial surface. This paper establishes a 6-degrees-of-freedom unsteady equation of motion describing the flow memory effect on viscous hydrodynamic loads. Motion simulations based on the unsteady and steady equations of motion for a work-class open-frame remotely operated vehicle are studied. Comparative studies show that the flow memory effect decreases the roll amplitude by over 50% at the natural frequency and has a greater impact on the motions in directions without control forces. The flow memory increases the lateral distance of rotation motions by over 10%. Under the flow memory effect, velocity fluctuations that persist over 2–5 times the length of the remotely operated vehicle are induced after the thrust control stops. The application of the unsteady equation of motion as part of a controller is verified through simulation experiments. A sudden motion in the process of rotation is designed to study the improvement of the control ability of the unsteady model. The experimental results suggest a performance improvement of ~30% over the steady-model-based controller when the roll angle error reaches the extreme value. The lower sensitivity of the unsteady-model-based controller is proved by motion control under multiple gains.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2611-2638"},"PeriodicalIF":5.2,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22535","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Path Planning Algorithm for UAV 3D Surface Inspection Based on Normal Vector Filtering and Integrated Viewpoint Evaluation 基于法向量滤波和综合视点评价的无人机三维表面检测路径规划算法

IF 5.2 2区计算机科学

Journal of Field Robotics Pub Date : 2025-02-23 DOI: 10.1002/rob.22530

Yunlong Wang, Shaoke Wan, Rongcan Qiu, Xiaohu Li

{"title":"A Path Planning Algorithm for UAV 3D Surface Inspection Based on Normal Vector Filtering and Integrated Viewpoint Evaluation","authors":"Yunlong Wang, Shaoke Wan, Rongcan Qiu, Xiaohu Li","doi":"10.1002/rob.22530","DOIUrl":"https://doi.org/10.1002/rob.22530","url":null,"abstract":"<div>\u0000 \u0000 <p>The use of unmanned aerial vehicles (UAVs) for three-dimensional (3D) surface inspection has become an important tool in the field of large-scale structure maintenance. However, the commonly used UAVs inspection path planning (IPP) algorithms for 3D surface suffer from problems, such as path quality-dependent model accuracy, path inspection efficiency, and low inspection quality. To address these issues, this paper proposes a UAV 3D surface IPP algorithm based on normal vector filtering and integrated viewpoint evaluation (IVE). Generate a safe and effective set of viewpoints through uniform sampling and normal vector viewpoint filtering, and then use an IVE method combined with Monte Carlo tree search to select viewpoints, thereby generating a safe, efficient, and complete UAV surface inspection path. Simulation results show that the proposed method reduces path length by up to 72.5%, inspection time by up to 80.6%, planning time by up to 54.3%, and defective coverage ratio by up to 55.8% compared with existing algorithms. Real-world experiments on the sail sculpture and the Terracotta Warrior sculpture further illustrate the efficiency of the algorithm, successfully collecting high-quality surface data and validating its practical applicability for 3D structural inspections.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 6","pages":"2561-2579"},"PeriodicalIF":5.2,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0