Journal of Field Robotics最新文献

{"title":"A Soft-Containing Gripper for High-Speed Handling of Breadcrumb-Coated Oysters","authors":"Yang Zhang,&nbsp;Zhongkui Wang,&nbsp;Keigo Kutani,&nbsp;Sadao Kawamura","doi":"10.1002/rob.22488","DOIUrl":"https://doi.org/10.1002/rob.22488","url":null,"abstract":"<p>Soft grippers have been developed for handling a diverse array of objects, particularly excelling in grasping deformable and soft food items due to their soft and flexible nature, which is essential for preventing damage. However, the development of soft grippers capable of operating at extremely high speeds, typically achieving a pick-and-place cycle in less than 1 s, remains underexplored. Addressing this gap, this study proposes a pneumatic soft gripper designed for the high-speed handling of breadcrumb-coated oysters and demonstrates its feasibility for application in food production lines. The proposed gripper consists of two soft fingers and a soft cushion positioned between them. The geometries of the soft fingers and the cushion were meticulously designed to securely contain the oyster. Finite element analysis (FEA) was employed to investigate the effects of gripper stiffness on the swaying motion, stress, and deformation experienced by the grasped soft object under high acceleration. The fabrication of the soft finger and cushion was accomplished using a liquid silicone 3D printer, and the durability of the soft finger was confirmed to exceed 1.6 million cycles, comparable to that of a suction pad. Food compatibility tests were conducted to ensure the suitability for handling food products. Feasibility tests on the automatic packaging of breadcrumb-coated oysters were performed using a parallel robot, examining five operating speeds, two applied pressures, and three oyster orientations. The results indicated that the proposed soft gripper could achieve maximum operational speeds of approximately 90 oysters/min for 16 g oysters and 80 oysters/min for 40 g oysters, thereby outperforming human workers and a commercial soft gripper. Through FEA and packaging experiments, it was determined that there exists an optimal stiffness for the soft gripper when handling the breadcrumb-coated oysters under high acceleration.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1976-1990"},"PeriodicalIF":4.2,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22488","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681149","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":"The Design of Endovascular Robots for Cardiac Interventions: A Survey","authors":"Natalia M. Alekseeva,&nbsp;Alexander G. Viller,&nbsp;Alexey M. Romanov","doi":"10.1002/rob.22480","DOIUrl":"https://doi.org/10.1002/rob.22480","url":null,"abstract":"<div>\u0000 \u0000 <p>The paper presents a survey of modern robots for percutaneous coronary interventions. It covers papers published before October 2024. The robotic systems introduced in these papers are compared by their design, tool manipulation principles, surgical tools compatibility, and human–machine interfaces, including types of feedback. The paper provides an overview of all main design approaches ever implemented in percutaneous coronary intervention robotics and critically analyzes their pros and cons. The survey covers 62 endovascular robotic systems (11 commercial and 51 academic) and 23 endovascular robotic tools, making it the most representative to date to the best of our knowledge. All of these solutions have been implemented at least as prototypes, while some of them have been tested in vivo and even reached clinical practice. In the discussion section, we critically analyze the known field experience with the use of the CorPath GRX (one of the most popular commercial systems currently used in several hospitals around the world), discuss the reasons for the insufficient spread of robotic endovascular surgery and propose a vision for changing this trend. This survey is intended primarily for engineers designing new medical robotic systems. However, it will also be of interest to endovascular surgeons to help them better understand the trade-offs of both the products already in the market and the promising solutions that will be available in the future.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1914-1962"},"PeriodicalIF":4.2,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681148","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":"Artificial Intelligence Technology for Path Planning of Automated Earthwork Machinery","authors":"Cheng Zhou,&nbsp;Yuxiang Wang,&nbsp;Rao Li,&nbsp;Tao Guan,&nbsp;Zhenyuan Liu,&nbsp;Gang Peng,&nbsp;Ke You","doi":"10.1002/rob.22479","DOIUrl":"https://doi.org/10.1002/rob.22479","url":null,"abstract":"<div>\u0000 \u0000 <p>The challenging characteristics of earthwork environments—complex, unstructured, and constantly evolving—pose significant challenges for the path planning of automated earthwork machinery. Recent advancements in artificial intelligence (AI) technology have opened new avenues to address these challenges, which are crucial for improving the intelligence level of automated earthwork machinery. However, there is a notable lack of comprehensive analyses on AI-based path planning in earthwork operations. Consequently, we provide a systematic review of four AI technologies currently employed in path planning for earthwork machinery, including (1) evolutionary computation, (2) swarm intelligence, (3) machine learning, and (4) other AI-based technologies. We analyzed the application and performance evaluation results of these technologies across various construction machinery. Through this systematic analysis, we identified several key challenges: (1) multiconstraint earthwork environments, (2) generalization across 3D unstructured sites, (3) adaptability to dynamically uncertain environments, and (4) shortage of on-site validation. We then outline potential future directions: (1) integration of generative AI with reinforcement learning, (2) use of large model technology, (3) adoption of embodied intelligence technology, and (4) conduction of more on-site experiments.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1887-1913"},"PeriodicalIF":4.2,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681293","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":"Using DNN-Compensator Coupling PD-Controller Strategy Control Two-Wheeled Robots Upright Motion Balance","authors":"Tang Zhaojia,&nbsp;Han Yu,&nbsp;Wang Ping","doi":"10.1002/rob.22483","DOIUrl":"https://doi.org/10.1002/rob.22483","url":null,"abstract":"<div>\u0000 \u0000 <p>Aiming at the problem that the two-wheeled mobile self-balancing robot (TWMSR) is challenging to control balance when TWMSR drives on uneven surface road, this study adds a DNN-compensator specially used to curb the TWMSR's toppling based on the traditional PID motion balance control system. A coupling function couples the control value between the PD-controller and the DNN-compensator. Its effect is that when the PD-controller's output value is insufficient to maintain the TWMSR's balance, the DNN-compensator will compensate the PD-controller's output. The experimental results show that using our DNN-compensator coupling PD-controller balance control strategy to control the TWMSR movement on uneven surface road can maintain the TWMSR drive stability; compared to traditional PD-controller, our control strategy braking performance is better, and the pitch angle (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 \u0000 <mrow>\u0000 <mi>φ</mi>\u0000 </mrow>\u0000 </mrow>\u0000 </semantics></math>) fluctuation range is smaller, TWMSR topple over is difficult.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1963-1975"},"PeriodicalIF":4.2,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681292","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":"Adaptive Prescribed-Time Control for Marine Surface Vehicles: A Time-Varying Gain Approach","authors":"Daohui Zeng,&nbsp;Yanhua Liang,&nbsp;Yongchao Liu,&nbsp;Jie Zhao,&nbsp;Chengtao Cai","doi":"10.1002/rob.22481","DOIUrl":"https://doi.org/10.1002/rob.22481","url":null,"abstract":"<div>\u0000 \u0000 <p>This study investigates an adaptive prescribed-time control scheme for marine surface vehicles (MSVs). Based on the introduced time-varying gain function, this article provides a sufficient condition for practical prescribed-time stability. The aim is to provide a theoretical basis for the prescribed-time controller design. The upper bound of the settling time can be accurately preset by adjusting the design parameters. Furthermore, adaptive parameter technique is utilized to handle the unknown lumped disturbances. Theory confirms that the tracking error of the MSV satisfies the conditions for practical prescribed-time stability. The superiority and effectiveness of the scheme are verified through simulation analysis.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1861-1873"},"PeriodicalIF":4.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681230","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":"Study of a Cable-Driven Hip Swimming-Assisted Exoskeleton Utilizing Adaptive Active Control Strategy","authors":"Longwen Chen,&nbsp;Dean Hu","doi":"10.1002/rob.22484","DOIUrl":"https://doi.org/10.1002/rob.22484","url":null,"abstract":"<div>\u0000 \u0000 <p>The power-assisted exoskeletons have a far-reaching research significance. The adaptive active control strategy (AACS) of the exoskeleton allows the wearers to achieve personalized assistance tailored to their specific movement patterns and physical needs. However, due to the high requirements for waterproof design and the high difficulty in underwater AACS design, the researches on underwater power-assisting exoskeletons are hardly to be seen. Therefore, this research proposes a cable-driven hip swimming-assisted exoskeleton (SAE) utilizing an AACS. SAE can generate adaptive power-assisting guiding trajectories of thighs by underwater motion intention perception (UMIP) of the wearer. To achieve UMIP, a deep learning network is presented by combining conventional neural network, bidirectional long short-term memory network, and attention mechanism (AM-Dconvbilstm). SAE guides the wearer's thighs to move along the generated guiding trajectory by UMIP through the cables to conduct hip power assisting. The feasibility of the proposed AM-Dconvbilstm on UMIP and the power-assisting effect of designed SAE are tested on three elite swimmers by recording corresponding data from IMUs and a sports watch. According to the results of generated trajectories from SAE and actual trajectories from the wearer, the proposed AM-Dconvbilstm model is verified to predict the wearer's hip motion intention accurately. The power-assisting effect of SAE is also verified according to the sports watch's heart rate and average energy consumption. All the experiment results greatly validated the feasibility of the proposed AACS and designed SAE.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1874-1886"},"PeriodicalIF":4.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681010","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 Hybrid Parameters Estimation Approach for Power Consumption Modeling of Ground Mobile Robots With Unknown Payload","authors":"Parham Haji Ali Mohamadi,&nbsp;Amin Khorasani,&nbsp;Tom Verstraten,&nbsp;Bram Vanderborght","doi":"10.1002/rob.22470","DOIUrl":"https://doi.org/10.1002/rob.22470","url":null,"abstract":"<p>Typically, batteries are the main power source for mobile robots, and the practical constraints in carrying them pose challenges in achieving efficiency, autonomy, and safety objectives in robotic missions. Moreover, dealing with battery degradation requires a precise understanding of energy consumers' behavior in the system. Therefore, establishing an energy consumption model has an important role in addressing these challenges. This study focuses on the modeling and estimation of power consumption in indoor ground mobile robots with unknown payloads. We investigate key components and parameters that influence the actuation energy consumption of ground mobile robots equipped with DC motors, particularly in the context of pure rolling without slipping. To estimate the actuation power consumption of ground mobile robots, we present a hybrid parameters estimation approach. This method includes an offline step for estimating the mass-decoupled coefficients of a power model, followed by two online steps for estimating the robot's unknown payload and its actuation power consumption. Simulation and experimental results with a differential drive robot (Turtlebot3) validate the effectiveness of the proposed approach. Additionally, the performance of the proposed power consumption estimation method is compared with two other data-driven models based on multivariate linear regression and multilayer perceptron neural networks. The results demonstrate that the proposed method provides improved power consumption estimation accuracy on the selected indicators compared to the others. We also emphasize the importance of balancing the accuracy of power consumption estimation with its associated costs in the context of the proposed approach. This extra cost includes the energy needed for additional data measurement and processing. Considering this trade-off is crucial for the practical implementation and resource optimization in robotic systems.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1840-1860"},"PeriodicalIF":4.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22470","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681229","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":"Ergonomic Evaluation of a Walk-Behind AI-Based Cotton Fertilizer Applicator","authors":"Arjun Chouriya,&nbsp;Peeyush Soni,&nbsp;Smrutilipi Hota,&nbsp;E. V. Thomas","doi":"10.1002/rob.22474","DOIUrl":"https://doi.org/10.1002/rob.22474","url":null,"abstract":"<p>The mechanization of agricultural operations greatly influences both the efficiency of farming operations and the health and safety of farm workers. Human exposure to working environments represents a significant hazard associated with machines and the environment. This research focuses on evaluating the ergonomic aspects of the newly developed artificial intelligence (AI)-based cotton fertilizer applicator, aiming to assess the potential impact on workers' health, safety, and overall exertion. Ergonomic factors such as heart rate (HR), oxygen consumption rate (OCR), energy expenditure rate (EER), physiological work cost, as well as discomfort and posture during use, were assessed at three different operating speeds of the applicator. Results showed that HRs, OCR, and EER ranged from 86 to 109 beats/min, 0.44 to 0.83 L/min, and 9.3 to 17.45 kJ/min, respectively, indicating that the physical demands on workers were within manageable limits. Discomfort was predominantly noted in the palms, attributed to the necessity of controlling the applicator with both hands. Analysis of cardiac effort revealed that 93.75%, 92.70%, and 94.67% of effort was expended during work at speeds of 0.5, 0.8, and 1 km/h, respectively, with the remainder during recovery periods. The workload on the middle deltoid muscle during field operation varied between 10.15%–14.58% for left-hand controls and 1.85%–3.5% for right-hand controls. Statistical analysis highlighted significant differences in physiological responses among participants, with ergonomic parameters closely linked to the applicator's forward speed. The study concludes using the developed AI-based cotton fertilizer applicator does not pose significant health risks to operators, suggesting its ergonomic design effectively mitigates physical strain.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1826-1839"},"PeriodicalIF":4.2,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22474","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681345","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":"Development, Integration, and Field Evaluation of a Dual-Arm Ridge Cultivation Strawberry Autonomous Harvesting Robot","authors":"Hehe Xie,&nbsp;Dongxing Zhang,&nbsp;Li Yang,&nbsp;Tao Cui,&nbsp;Xiantao He,&nbsp;Kailiang Zhang,&nbsp;Zhijie Zhang","doi":"10.1002/rob.22472","DOIUrl":"https://doi.org/10.1002/rob.22472","url":null,"abstract":"<div>\u0000 \u0000 <p>Strawberry harvesting is a labor-intensive and time-consuming task, and the shortage of labor resources and high production costs have made strawberry harvesting robots a focus of attention in both academia and industry. This paper presents a dual-arm strawberry harvesting robot suitable for ridge cultivation in polytunnels. The coordinated operation of the robot's software and hardware systems enables it to automatically harvest strawberries along the ridge. To ensure the integrity of the fragile fruit, a nondestructive end-effector was designed that can directly separate and grip the stem, avoiding contact with the fruit itself. Additionally, a method based on composite models was introduced to accurately determine the location and tilt direction of the picking points, to address the randomness in the growth direction of the stems. Furthermore, the modular five degrees-of-freedom robotic arm is better suited to the harvesting task requirements. Field evaluation results show that the robot achieves harvesting success rates between 98.4% and 57.4%, and destructive harvesting success rates vary between 98.4% and 75.0% across four scenarios of different complexities. Overall, the success rates for nondestructive and destructive harvesting reach 78.8% and 87.2%, respectively. The average harvesting cycle in the dual-arm working mode is 4.5 s per berry. Through an in-depth analysis of the results obtained, this paper also discusses the existing limitations and future research directions.</p>\u0000 </div>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1783-1798"},"PeriodicalIF":4.2,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681619","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":"Collaborative Robotics: Application of Delphi Method","authors":"Jean-Marc Salotti,&nbsp;Ephraim Suhir","doi":"10.1002/rob.22477","DOIUrl":"https://doi.org/10.1002/rob.22477","url":null,"abstract":"<p>In the domain of collaborative robotics, it is often needed to make complex multiparametric choices or assessments that combine heterogeneous criteria, such as task performance, reliability, safety, and ergonomics. The Delphi method, a process of arriving at group consensus by providing experts with rounds of questionnaires, as well as the group response before each subsequent round, can be applied to solve this type of problems. The following Delphi method efforts are addressed in our analysis with application to finding appropriate criteria and their relative weights for the evaluation of the teleoperation task of a robotic platform: (1) Contribution of experts; (2) estimates using student's distribution; and (3) decision making support using Fischer criterion. A consensus emerged among eight experts, who selected the criteria of duration, number of trajectory corrections, and feeling of the operator. Weights have been proposed for each criterion and statistical tools have been used to evaluate the consensus.</p>","PeriodicalId":192,"journal":{"name":"Journal of Field Robotics","volume":"42 5","pages":"1799-1807"},"PeriodicalIF":4.2,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/rob.22477","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144681620","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}