Journal of Field Robotics最新文献

{"title":"Cover Image, Volume 40, Number 5, August 2023","authors":"Haipeng Wang,&nbsp;Yang Yang,&nbsp;Xinghong Ye,&nbsp;Zhiguo He,&nbsp;Pengcheng Jiao","doi":"10.1002/rob.22226","DOIUrl":"https://doi.org/10.1002/rob.22226","url":null,"abstract":"<p>The cover image is based on the Research Article <i>Combustion-enabled underwater vehicles (CUVs) in dynamic fluid environment</i> by Haipeng Wang et al., https://doi.org/10.1002/rob.22167\u0000 \u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 5","pages":"i"},"PeriodicalIF":8.3,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22226","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6058080","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":"HMI-assisted visual interface-cum-embedded system for measurement of tractor–implement performance parameters","authors":"Prateek Shrivastava,&nbsp;V. K. Tewari,&nbsp;Chanchal Gupta,&nbsp;Arjurn Chouriya","doi":"10.1002/rob.22221","DOIUrl":"10.1002/rob.22221","url":null,"abstract":"<p>A human–machine interface (HMI)-based visual interface along with an embedded system was developed to real-time measure, display, and store the various tractor–implement performance parameters, that is, geoposition, depth, speed, slip, fuel consumption, draft, and power take-off (PTO) torque. The developed system consists of various commercially available (global positioning system, rotary potentiometer, tension/compression load cell, Hall-effect sensor, flow meter, and strain gauge) sensors/transducers to measure the performance parameters. A strain-gauge-based special type of transducer was also developed for measuring the PTO torque acting on the implement and the output of the transducer was transferred to the virtual interface-based data acquisition system using radio frequency-based modules. Along with the sensors, the developed system is composed of a microcontroller to process the data received from sensors, an HMI-assisted smart touch screen to display the output, and a secure digital card module to store the processed data. The developed visual interface of the embedded system comprises multiple operator-friendly touch screens and each screen was designed with a graphical user interface for the visual presentation of the tractor–implement performance parameters. The system was installed in the TAFE Samrat 4410 tractor and tested under various field operations. Sensors employed in the system were calibrated for obtaining precise measurement, and excellent linearity with a high correlation between actual and measured variables. Under various field operations (plowing and tillering), a maximum error of 15% (except PTO torque) was found between parameters measured with the developed system and manual/predicted measurement. The field results fortify the acceptable accuracy of the developed system. The developed system will be helpful for researchers or students to study the matching of tractor–implement combinations.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"41 7","pages":"2147-2168"},"PeriodicalIF":4.2,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45522442","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":"Influence of screw blades on the performance of a screw-drive granary robot","authors":"Hangjia Jin,&nbsp;Yanhui Lu,&nbsp;Wenfu Wu,&nbsp;Feng Han","doi":"10.1002/rob.22220","DOIUrl":"10.1002/rob.22220","url":null,"abstract":"<p>A granary robot with screw-drive mechanisms can perfectly adapt to a loose grain terrain. The design of the helical wheels is significant for the driving performance of this robot. Because this robot moves due to the action of the blade on the grain, the parameters of the helical blade are especially important among all factors. Therefore, to determine the effect of blades on the performance of a screw-drive granary robot, a screw robot–corn coupling model is established based on the coupling of the discrete element method and multibody dynamics. The model can analyze the interaction of the screw wheel with the grain particles. Then a robot with two helical wheels is designed, manufactured, and tested to verify the accuracy of the coupling model. The cosimulation created with this model has good accuracy compared with the experiment, and the mean relative errors of sinkage, velocity, and slip ratio are 3.43%, 1.21%, and 13.87%, respectively. Finally, the effects of the height, axial length, helix angle, and number of screw blades on the driving performance of the robot are studied with single-factor simulations. The trends of the torque, slip, and drawbar efficiency varying with these parameters of the screw blade are obtained, which can provide critical insights for the preliminary design of a screwed granary robot.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"41 7","pages":"2133-2146"},"PeriodicalIF":4.2,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42006364","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":"Corrigendum for “Research on robotic manipulator fault detection and diagnosis technology based on machine vision in complex environments”","authors":"Jinghui Pan,&nbsp;Lili Qu,&nbsp;Kaixiang Peng","doi":"10.1002/rob.22222","DOIUrl":"https://doi.org/10.1002/rob.22222","url":null,"abstract":"<p>In the published article, the affiliation for the author “Lili Qu” is appearing as “School of Automation, South China University of Technology Guangzhou College, Guangzhou, China” which should be read as “School of Mechatronic Engineering and Automation, Foshan University, Foshan 528231, China.”</p><p>The authors regret this error.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 5","pages":"1323"},"PeriodicalIF":8.3,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22222","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5761624","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":"An autonomous spraying robot architecture for sucker management in large-scale hazelnut orchards","authors":"Martina Lippi,&nbsp;Matteo Santilli,&nbsp;Renzo Fabrizio Carpio,&nbsp;Jacopo Maiolini,&nbsp;Emanuele Garone,&nbsp;Valerio Cristofori,&nbsp;Andrea Gasparri","doi":"10.1002/rob.22217","DOIUrl":"10.1002/rob.22217","url":null,"abstract":"<p>In this work, motivated by the precision agriculture (PA) paradigm, we address the problem of managing hazelnut suckering plants on a per-plant basis in a large-scale orchard. Suckering plants, or shortly, suckers, are basal shoots that grow at the base of a tree and compete with the tree itself for nutrients and water. Generally, in large-scale orchards, suckers are treated with the application of herbicide through spraying tractors that continuously spray the crops while navigating the whole orchard. This approach however does not consider the individual needs of each plant and it is definitely not environmentally-friendly since a lot of unnecessary solution is being drained in the soil. For this reason, we propose a novel fully autonomous sucker management architecture that is able to detect the presence of suckers for each plant, by relying on a You Only Look Once (YOLO)-based recognition system, reconstruct them in three-dimension and estimate the amount of herbicide solution needed for the specific plant, based on a data-driven approach. The herbicide solution is applied using a ground robot equipped with an RGB-D camera and a spraying system. This approach allows to significantly reduce pollution and waste. Experimental results both for individual components and for the entire architecture in a real-world (1:1 scale) hazelnut orchard located in Caprarola, Italy, are provided to corroborate the proposed architecture.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"41 7","pages":"2114-2132"},"PeriodicalIF":4.2,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47939343","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":"Nonlinear model predictive control for hydrobatics: Experiments with an underactuated AUV","authors":"Sriharsha Bhat,&nbsp;Chariklia Panteli,&nbsp;Ivan Stenius,&nbsp;Dimos V. Dimarogonas","doi":"10.1002/rob.22218","DOIUrl":"https://doi.org/10.1002/rob.22218","url":null,"abstract":"<p>Hydrobatic autonomous underwater vehicles (AUVs) can be efficient in range and speed, as well as agile in maneuvering. They can be beneficial in scenarios such as obstacle avoidance, inspections, docking, and under-ice operations. However, such AUVs are underactuated systems—this means exploiting the system dynamics is key to achieving elegant hydrobatic maneuvers with minimum controls. This paper explores the use of model predictive control (MPC) techniques to control underactuated AUVs in hydrobatic maneuvers and presents new simulation and experimental results with the small and hydrobatic SAM AUV. Simulations are performed using nonlinear model predictive control (NMPC) on the full AUV system to provide optimal control policies for several hydrobatic maneuvers in Matlab/Simulink. For implementation on AUV hardware in robot operating system, a linear time varying MPC (LTV-MPC) is derived from the nonlinear model to enable real-time control. In simulations, NMPC and LTV-MPC shows promising results to offer much more efficient control strategies than what can be obtained with PID and linear quadratic regulator based controllers in terms of rise-time, overshoot, steady-state error, and robustness. The LTV-MPC shows satisfactory real-time performance in experimental validation. The paper further also demonstrates experimentally that LTV-MPC can be run real-time on the AUV in performing hydrobatic maneouvers.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1840-1859"},"PeriodicalIF":8.3,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22218","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5688051","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":"Neural network-based optical flow versus traditional optical flow techniques with thermal aerial imaging in real-world settings","authors":"Tran Xuan Bach Nguyen,&nbsp;Kent Rosser,&nbsp;Asanka Perera,&nbsp;Philip Moss,&nbsp;Javaan Chahl","doi":"10.1002/rob.22219","DOIUrl":"https://doi.org/10.1002/rob.22219","url":null,"abstract":"<p>The study explores the feasibility of optical flow-based neural network from real-world thermal aerial imagery. While traditional optical flow techniques have shown adequate performance, sparse techniques do not work well during cold-soaked low-contrast conditions, and dense algorithms are more accurate in low-contrast conditions but suffer from the aperture problem in some scenes. On the other hand, optical flow from convolutional neural networks has demonstrated good performance with strong generalization from several synthetic public data set benchmarks. Ground truth was generated from real-world thermal data estimated with traditional dense optical flow techniques. The state-of-the-art Recurrent All-Pairs Field Transform for the Optical Flow model was trained with both color synthetic data and the captured real-world thermal data across various thermal contrast conditions. The results showed strong performance of the deep-learning network against established sparse and dense optical flow techniques in various environments and weather conditions, at the cost of higher computational demand.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1817-1839"},"PeriodicalIF":8.3,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22219","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"5659444","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":"FastFusion: Deep stereo-LiDAR fusion for real-time high-precision dense depth sensing","authors":"Haitao Meng,&nbsp;Changcai Li,&nbsp;Chonghao Zhong,&nbsp;Jianfeng Gu,&nbsp;Gang Chen,&nbsp;Alois Knoll","doi":"10.1002/rob.22216","DOIUrl":"https://doi.org/10.1002/rob.22216","url":null,"abstract":"<p>Light detection and ranging (LiDAR) and stereo cameras are two generally used solutions for perceiving 3D information. The complementary properties of these two sensor modalities motivate a fusion to derive practicable depth sensing toward real-world applications. Promoted by deep neural network (DNN) techniques, recent works achieve superior performance on accuracy. However, the complex architecture and the sheer number of DNN parameters often lead to poor generalization capacity and non-real-time computing. In this paper, we present FastFusion, a three-stage stereo-LiDAR deep fusion scheme, which integrates the LiDAR priors into each step of classical stereo-matching taxonomy, gaining high-precision dense depth sensing in a real-time manner. We integrate stereo-LiDAR information by taking advantage of a compact binary neural network and utilize the proposed cross-based LiDAR trust aggregation to further fuse the sparse LiDAR measurements in the back-end of stereo matching. To align the photometrical of the input image and the depth of the estimation, we introduce a refinement network to guarantee consistency. More importantly, we present a graphic processing unit-based acceleration framework for providing a low-latency implementation of FastFusion, gaining both accuracy improvement and real-time responsiveness. In the experiments, we demonstrate the effectiveness and practicability of FastFusion, which obtains a significant speedup over state-of-the-art baselines while achieving comparable accuracy on depth sensing. The video demo for real-time depth estimation of FastFusion on the real-world driving scenario is available at https://youtu.be/nP7cls2BA8s.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"40 7","pages":"1804-1816"},"PeriodicalIF":8.3,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"6191662","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":"Development of a real-time work-related postural risk assessment system of farm workers using a sensor-based artificial intelligence approach","authors":"Lakhwinder Pal Singh,&nbsp;Praveen Kumar,&nbsp;Shiv Kumar Lohan","doi":"10.1002/rob.22215","DOIUrl":"10.1002/rob.22215","url":null,"abstract":"<p>In recent years, the promotion of farm mechanization has been directed toward reducing the human discomfort and fatigue associated with various agricultural work-related activities. During these activities, many factors (like force, awkward posture, vibration, repetition, etc.) play a significant role in causing musculoskeletal disorders. Second, ergonomic risk assessment of physical work is conventionally conducted through observation and direct/indirect physiological measurements. However, these methods are time-consuming and require human subjects to perform the motion to obtain detailed body movement data. In the present study, a semiautomatic rapid entire body assessment (REBA) evaluation tool is developed for real-time assessment of agricultural work-related musculoskeletal disorders risk of farm workers using Kinect V2 sensor-based artificial intelligence approach. It allows the investigator speedy detect of awkward postures leading to critical conditions and to reduce subjective bias. It is useful to analyze online as well as offline posture analysis, it detects the critical areas of the body posture, which may lead to the musculoskeletal disorders of agricultural workers, and suggest aptly to correct the posture. The Kinect V2 REBA assessment score was found with a factual significant match with the reference expert evaluation as reflected by the Landis and Koch scale <i>k</i> = 0.673 (<i>p</i> &lt; 0.001), 95% confidence interval (CI) for the left side, and <i>k</i> = 0.644 (<i>p</i> &lt; 0.001), 95% CI for the right side of the body respectively.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"41 7","pages":"2100-2113"},"PeriodicalIF":4.2,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43965621","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":"A sensor-based assistive technology for lower-limb-disabled agricultural workers and abled female workers for tractor clutch and brake operation","authors":"Smrutilipi Hota,&nbsp;V. K. Tewari,&nbsp;Laxmi Kant Dhruw,&nbsp;Abhilash K. Chandel","doi":"10.1002/rob.22214","DOIUrl":"10.1002/rob.22214","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 <p>Agricultural mechanization although reduces the food demand and supply gap through improved and smart technologies, it also risks the lower-limb disability of workers due to accidents that restrict them to participate in agricultural operations due to the unavailability of appropriate assistive technologies. The lack of use of ergonomics further minimizes the inclusion of female workers in farming operations. Therefore, this study is focused on the development of a sensor-based wireless hand control system for tractor clutch and brake operation to assist lower-limb-disabled agricultural workers and abled females in tractor operation. Actuation force and speed of conventional clutch and brake pedals were evaluated using an integrated foot transducer and used as a reference for the design of the system (clutch: 92–310 N, 36–43 mm/s; brake: 106–329 N, 57–63 mm/s). The hand control system consists of a transmitter and a receiver node incorporating a single-board computer, matrix keypad, voltage regulators, relay switches, wireless communication through radio frequency modules, and electric linear actuators connected with the pedals through L-shaped clips, nuts, bolts, and chains. The response time of the developed system was determined as 100 ms and the stopping distance of the tractor using the hand control system ranged from 44.0 to 190.7 cm at a forward speed of 2.1–7.9 km/h. The ergonomic evaluation measured using the K₄b² oxygen analyzer identified the foot control usage in tractors as high energy consuming (9.7–15.1 kJ/min) compared with the hand control usage (7.3–14.1 kJ/min). Electromyography-root mean square (EMG-RMS) of upper limb muscle, extension digitorum was found to be highest (14.76–45.29 µV) and was significantly affected by forward speed, gender, subjects, and type of control (<i>p</i> &lt; 0.01) whereas, EMG-RMS of other selected upper limb muscles, middle deltoid, flexor carpi radialis, and brachioradialis was not significantly affected by the type of control (foot or hand). Muscle workload of all the muscles was observed within the recommended limit (&lt;30%) during the tractor operation with the developed hand control system. The developed hand control system provides options to bypass foot-based actuation requirement for lower limb disabled as well as female workers. The novel design requires minimal workplace and operating forces and is inclusive of operator ergonomics.</p>\u0000 </section>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"41 7","pages":"2082-2099"},"PeriodicalIF":4.2,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41262335","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}