Journal of Field Robotics最新文献

{"title":"Aerial online mapping on-board system by real-time object detection for UGV path generation in unstructured outdoor environments","authors":"Jehong Lee,&nbsp;Jeonggeun Lim,&nbsp;Sangjin Pyo,&nbsp;Jongho Lee","doi":"10.1002/rob.22213","DOIUrl":"https://doi.org/10.1002/rob.22213","url":null,"abstract":"<p>An optimal path provides efficient operation of unmanned ground vehicles (UGVs) for many kinds of tasks such as transportation, exploration, surveillance, and search and rescue in unstructured areas that include various unexpected obstacles. Various onboard sensors such as LiDAR, radar, sonar, and cameras are used to detect obstacles around the UGVs. However, their range of view is often limited by movable obstacles or barriers, resulting in inefficient path generation. Here, we present the aerial online mapping system to generate an efficient path for a UGV on a two-dimensional map. The map is updated by projecting obstacles detected in the aerial images taken by an unmanned aerial vehicle through an object detector based on a conventional convolutional neural network. The proposed system is implemented in real-time by a skid steering ground vehicle and a quadcopter with relatively small, low-cost embedded systems. The frameworks and each module of the systems are given in detail to evaluate the performance. The system is also demonstrated in unstructured outdoor environments such as in a football field and a park with unreliable communication links. The results show that the aerial online mapping is effective in path generation for autonomous UGVs in real environments.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1754-1765"},"PeriodicalIF":8.3,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5909719","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}

{"title":"Real-time vibration monitoring and analysis of agricultural tractor drivers using an IoT-based system","authors":"Amandeep Singh,&nbsp;Naser Nawayseh,&nbsp;Siby Samuel,&nbsp;Yash Kumar Dhabi,&nbsp;Harwinder Singh","doi":"10.1002/rob.22206","DOIUrl":"https://doi.org/10.1002/rob.22206","url":null,"abstract":"<p>Agricultural tractor drivers experience a high amplitude of vibration, especially during soil tillage operations. In the past, most research studied vibration exposure with more focus on the vertical (<i>z</i>) axis than on the fore-and-aft (<i>x</i>) and lateral (<i>y</i>) axes. This study examines how rotary soil tillage affects the vibration acceleration and frequency, and the power spectral densities (PSDs) at the seat pan and head along three translational axes in a real-field multiaxis vibration context. Moreover, this study aimed to identify the characteristics of the seat-to-head transmissibility (STHT) response to identifying the most salient resonant frequencies along the <i>x</i>-, <i>y</i>-, and <i>z</i>-axes. Nine (9) male tractor drivers operated the tractor with a mounted rotary tiller throughout the soil tillage process. In the event of a COVID-19 pandemic, and to respect social distancing, this study developed an Internet of Things (IoT) module with the potential to integrate with existing data loggers for online data transmission and to make the experimentation process more effective by removing potential sources of experimenter errors. The raw acceleration data retrieved at the seat pan and the head were utilized to obtain daily exposure (A(8)), PSDs, and STHT along the <i>x</i>-, <i>y</i>-, and <i>z</i>-axes. The vibration energy was found to be dominant along the <i>z</i>-axis than the <i>x</i>- and <i>y</i>-axes. A(8) response among tractor drivers exceeds the exposure action value explicitly stated by Directive 2002/44/EU. PSDs along the <i>x</i>-, <i>y</i>-, and <i>z</i>-axes depicted the low-frequency vibration induced by rotary soil tillage operation. The STHT response exhibited a higher degree of transmissibility along the <i>y</i>- and <i>z</i>-axes when compared with that along the <i>x</i>-axis. The frequency range of 4–7 Hz may plausibly be associated with cognitive impairment in tractor drivers during rotary soil tillage.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1723-1738"},"PeriodicalIF":8.3,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22206","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5823760","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}

{"title":"Research on unmanned electric shovel autonomous driving path tracking control based on improved pure tracking and fuzzy control","authors":"Guohua Wu,&nbsp;Guoqiang Wang,&nbsp;Qiushi Bi,&nbsp;Yongpeng Wang,&nbsp;Yi Fang,&nbsp;Guangyong Guo,&nbsp;Wentao Qu","doi":"10.1002/rob.22208","DOIUrl":"https://doi.org/10.1002/rob.22208","url":null,"abstract":"<p>This paper proposes a path tracking control method combining pure tracking algorithms and self-adaptive fuzzy control for autonomous driving of an unmanned electric shovel. An improved pure tracking controller was designed based on the kinematic model of heavy crawler taking both the value of deviation and its variation as inputs with the crawler speed on each side as output. The proposed controller and MPC algorithm were simulated using MATLAB for comparison. The results show that the proposed controller has more anthropomorphic characteristics than the MPC method. To verify the actual control effect of the controller, experiments were carried out using a prototype electric shovel for different working conditions. The experimental results proved that the controller is able to meet the control requirements for unmanned electric shovel path tracking.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1739-1753"},"PeriodicalIF":8.3,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5822868","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}

{"title":"RumexWeeds: A grassland dataset for agricultural robotics","authors":"Ronja Güldenring,&nbsp;Frits K. van Evert,&nbsp;Lazaros Nalpantidis","doi":"10.1002/rob.22196","DOIUrl":"https://doi.org/10.1002/rob.22196","url":null,"abstract":"<p>Computer vision can lead toward more sustainable agricultural production by enabling robotic precision agriculture. Vision-equipped robots are being deployed in the fields to take care of crops and control weeds. However, publicly available agricultural datasets containing both image data as well as data from navigational robot sensors are scarce. Our real-world dataset RumexWeeds targets the detection of the grassland weeds: <i>Rumex obtusifolius</i> L. and <i>Rumex crispus</i> L. RumexWeeds includes whole image sequences instead of individual static images, which is rare for computer vision image datasets, yet crucial for robotic applications. It allows for more robust object detection, incorporating temporal aspects and considering different viewpoints of the same object. Furthermore, RumexWeeds includes data from additional navigational robot sensors—GNSS, IMU and odometry—which can increase robustness, when additionally fed to detection models. In total the dataset includes 5510 images with 15,519 manual bounding box annotations collected at three different farms and four different days in summer and autumn 2021. Additionally, RumexWeeds includes a subset of 340 ground truth pixels-wise annotations. The dataset is publicly available at https://dtu-pas.github.io/RumexWeeds/. In this paper we also use RumexWeeds to provide baseline weed detection results considering a state-of-the-art object detector; in this way we are elucidating interesting characteristics of the dataset.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1639-1656"},"PeriodicalIF":8.3,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22196","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6008645","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}

{"title":"Multiposture leg tracking for temporarily vision restricted environments based on fusion of laser and radar sensor data","authors":"Nils Mandischer,&nbsp;Ruikun Hou,&nbsp;Burkhard Corves","doi":"10.1002/rob.22195","DOIUrl":"https://doi.org/10.1002/rob.22195","url":null,"abstract":"<p>Leg tracking is an established field in mobile robotics and machine vision in general. These algorithms, however, only distinguish the scene between leg and nonleg detections. In application fields like firefighting, where people tend to choose squatting or crouching over standing postures, those methods will inevitably fail. Further, tracking based on a single sensor system may reduce the overall reliability if brought to outdoor or complex environments with limited vision on the target objectives. Therefore, we extend our recent work to a multiposture detection system based on laser and radar sensors, that are fused to allow for maximal reliability and accuracy in scenarios as complex as indoor firefighting with vastly limited vision. The proposed tracking pipeline is trained and extensively validated on a new data set. We show that the radar tracker reaches state-of-the-art performance, and that laser and fusion tracker outperform recent methods.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1620-1638"},"PeriodicalIF":8.3,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22195","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6008634","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}

{"title":"Whole-body motion planning and control of a quadruped robot for challenging terrain","authors":"Guanglin Lu,&nbsp;Teng Chen,&nbsp;Xuewen Rong,&nbsp;Guoteng Zhang,&nbsp;Jian Bi,&nbsp;Jingxuan Cao,&nbsp;Han Jiang,&nbsp;Yibin Li","doi":"10.1002/rob.22197","DOIUrl":"https://doi.org/10.1002/rob.22197","url":null,"abstract":"<p>Quadruped robots working in jungles, mountains or factories should be able to move through challenging scenarios. In this paper, we present a control framework for quadruped robots walking over rough terrain. The planner plans the trajectory of the robot's center of gravity by using the normalized energy stability criterion, which ensures that the robot is in the most stable state. A contact detection algorithm based on the probabilistic contact model is presented, which implements event-based state switching of the quadruped robot legs. And an on-line detection of contact force based on generalized momentum is also showed, which improves the accuracy of proprioceptive force estimation. A controller combining whole body control and virtual model control is proposed to achieve precise trajectory tracking and active compliance with environment interaction. Without any knowledge of the environment, the experiments of the quadruped robot SDUQuad-144 climbs over significant obstacles such as 38 cm high steps and 22.5 cm high stairs are designed to verify the feasibility of the proposed method.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1657-1677"},"PeriodicalIF":8.3,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6008637","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}

{"title":"NDT-6D for color registration in agri-robotic applications","authors":"Himanshu Gupta,&nbsp;Achim J. Lilienthal,&nbsp;Henrik Andreasson,&nbsp;Polina Kurtser","doi":"10.1002/rob.22194","DOIUrl":"https://doi.org/10.1002/rob.22194","url":null,"abstract":"<p>Registration of point cloud data containing both depth and color information is critical for a variety of applications, including in-field robotic plant manipulation, crop growth modeling, and autonomous navigation. However, current state-of-the-art registration methods often fail in challenging agricultural field conditions due to factors such as occlusions, plant density, and variable illumination. To address these issues, we propose the NDT-6D registration method, which is a color-based variation of the Normal Distribution Transform (NDT) registration approach for point clouds. Our method computes correspondences between pointclouds using both geometric and color information and minimizes the distance between these correspondences using only the three-dimensional (3D) geometric dimensions. We evaluate the method using the GRAPES3D data set collected with a commercial-grade RGB-D sensor mounted on a mobile platform in a vineyard. Results show that registration methods that only rely on depth information fail to provide quality registration for the tested data set. The proposed color-based variation outperforms state-of-the-art methods with a root mean square error (RMSE) of 1.1–1.6 cm for NDT-6D compared with 1.1–2.3 cm for other color-information-based methods and 1.2–13.7 cm for noncolor-information-based methods. The proposed method is shown to be robust against noises using the TUM RGBD data set by artificially adding noise present in an outdoor scenario. The relative pose error (RPE) increased <math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>~</mo>\u0000 </mrow>\u0000 <annotation> $unicode{x0007E}$</annotation>\u0000 </semantics></math>14% for our method compared to an increase of <math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>~</mo>\u0000 </mrow>\u0000 <annotation> $unicode{x0007E}$</annotation>\u0000 </semantics></math>75% for the best-performing registration method. The obtained average accuracy suggests that the NDT-6D registration methods can be used for in-field precision agriculture applications, for example, crop detection, size-based maturity estimation, and growth modeling.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1603-1619"},"PeriodicalIF":8.3,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22194","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5990122","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}

{"title":"AI-enabled farm-friendly automatic machine for washing, image-based sorting, and weight grading of citrus fruits: Design optimization, performance evaluation, and ergonomic assessment","authors":"Subir Kumar Chakraborty,&nbsp;A. Subeesh,&nbsp;Rahul Potdar,&nbsp;Narendra Singh Chandel,&nbsp;Dilip Jat,&nbsp;Kumkum Dubey,&nbsp;Pramod Shelake","doi":"10.1002/rob.22193","DOIUrl":"https://doi.org/10.1002/rob.22193","url":null,"abstract":"<p>The modernization of postharvest operations and penetration of emerging technologies in horticultural processing have provided intelligent solutions for reducing postharvest losses. Work environmental and occupational health issues require immediate attention as the awkward posture and continuous drudgery-prone on-farm sorting and grading activities may lead to musculoskeletal disorders. The main objective of this study was to develop an automatic farm-friendly machine for real-time citrus fruit washing, image-based sorting, and weight grading; designed optimally and equipped with an embedded system comprising a lightweight convolutional neural network (CNN) model. Also included in this study was a thorough ergonomic assessment of the developed machine in a real work environment. The parametric choice of the fruit washing and singulation system was performed by employing computational fluid dynamics modeling and response surface methodology designed optimization. It was observed that under steady-state conditions, the water jet would arrive at a velocity of 11.36 m/s which would eventually suit a singulation conveyor with a slope of 25°. A noninvasive grading and sorting approach for citrus fruits is presented in this paper that leverages deep learning to classify the fruits into “accept” and “reject” classes. The custom lightweight CNN model “SortNet” has shown excellent classification results with an overall accuracy of 97.6%. The ergonomic evaluation shows that the average body part discomfort score in case of operating an automatic fruit grading machine was much lower (12.3 ± 2.0) than the traditional method (30.9 ± 3.3). Further, in the case of machine operation, the percentage load on the muscles ranged from 28.67 to 34.31 reflecting that subjects can work for longer duration on the machine without fatigue as compared with the traditional manual operation.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1581-1602"},"PeriodicalIF":8.3,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6170567","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}

{"title":"Obstacle avoidance tracking control with antiswing and tracking errors constraint for underactuated automated lifting robots with load hoisting/lowering","authors":"Zhiwen Tan,&nbsp;Ke Zhang,&nbsp;Huaitao Shi,&nbsp;Lu Chen,&nbsp;Guowei Li","doi":"10.1002/rob.22192","DOIUrl":"https://doi.org/10.1002/rob.22192","url":null,"abstract":"<p>The existing automated lifting robot technology focuses merely on motion control and ignores the surrounding environment. In practice, obstacles inevitably exist in the movement path of the automated lifting robot, which affects construction safety. Furthermore, due to the underactuated characteristics of the automated lifting robot, the load can be difficult to control when it swings violently, which undoubtedly poses huge challenges to obstacle avoidance trajectory planning and controller design. In this paper, an obstacle avoidance trajectory and its tracking controller with antiswing and tracking errors constraint are proposed. To ensure accurate load positioning and effective obstacle avoidance, the proposed control method introduces a four-segment polynomial trajectory interpolation curve to construct an obstacle avoidance trajectory based on analyzing the geometric relationship between variables. To improve the transient coupling control performance of the system, combined with the passive analysis of the automated lifting robot system, this method constructs a potential function that limits the tracking error and a coupling signal that enhances the coupling relationship between the system variables. Barbalat's lemma and Lyapunov techniques are used to analyze the stability of the system. Simulation and experimental results show that the proposed control method can significantly suppress or even eliminate load oscillation, accurately locate the load, avoid obstacles, improve the safety and efficiency of the working automated lifting robot, and have strong robustness to changes in system parameters and the addition of external disturbances.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1562-1580"},"PeriodicalIF":8.3,"publicationDate":"2023-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5794102","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}

{"title":"Complete coverage path planning for wheeled agricultural robots","authors":"Danial Pour Arab,&nbsp;Matthias Spisser,&nbsp;Caroline Essert","doi":"10.1002/rob.22187","DOIUrl":"https://doi.org/10.1002/rob.22187","url":null,"abstract":"<p>In the agricultural industry, an evolutionary effort has been made over the last two decades to achieve precise autonomous systems to perform typical in-field tasks, including harvesting, mowing, and spraying. One of the main objectives of an autonomous system in agriculture is to improve the efficiency while reducing the environmental impact and cost. Due to the nature of these operations, complete coverage path planning (CCPP) approaches play an essential role to find an optimal path which covers the entire field while taking into account land topography, operation requirements, and robot characteristics. The aim of this paper is to propose a CCPP approach defining the optimal movements of mobile robots over an agricultural field. First, a method based on tree exploration is proposed to find all potential solutions satisfying some predefined constraints. Second, a similarity check and selection of optimal solutions method is proposed to eliminate similar solutions and find the best solutions. The optimization goals are to maximize the coverage area and to minimize overlaps, nonworking path length, and overall travel time. To explore a wide range of possible solutions, our approach is able to consider multiple entrances for the robot. For fields with a complex shape, different dividing lines to split them into simple polygons are also considered. Our approach also computes the headland zones and covers them automatically which leads to a high coverage rate of the field.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 6","pages":"1460-1503"},"PeriodicalIF":8.3,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22187","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6158407","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}