Journal of Field Robotics最新文献

For fragile and delicate fruit in agricultural production, damageless robotic grasping is still an open problem. In this review, we aim to synthesize existing studies and provide insights on this issue. Compared with other related reviews, we focus on fragile fruit and damage problems, and cover more complete stages and technical aspects. The referenced studies were divided into two categories according to their stages, including picking and harvesting in the preharvest stage, and uploading and packaging in the postharvest stage. In this context, the systematic literature review method was adopted for literature collection and selection. The references were classified into four categories according to their technical aspects: system design, end effector, visual feedback, and tactile feedback. Additionally, recent progress in commercial products and companies was also investigated. In summary, techniques such as a dedicated end effector for fragile fruit, advanced tactile sensing, and control strategy are supposed to be further studied to achieve damageless robotic fragile fruit grasping. Furthermore, other advanced perspectives are potentially becoming future trends, such as in-hand sensing of fruit quality and dexterous manipulation for complex tasks. We hope this review can provide insights in both academia and industry to promote robotization in fruit production.

Aiming at the problem of locating the faulty bearing of robot propeller, the traditional mechanism modeling method is difficult to establish and cannot cover all unknown factors due to too many factors involved; however, models that rely on actual data are difficult to provide enough training samples due to expensive equipment and complex working conditions. Therefore, an agent model based on knowledge and data fusion is proposed to accurately capture the mapping relationship between input data and fault-bearing location. First, the mechanism model of the propeller-bearing rotor system under ideal working conditions is established, and data samples are generated. Then, a fault location agent model-building method based on incremental knowledge distillation is proposed, which integrates mechanism knowledge with actual data. Combined with the data continuously obtained in actual operation, the agent model is continuously updated and optimized to enable it to dynamically adjust under different working conditions and improve the fault location accuracy. Finally, the fault feature attribute description strategy is embedded in the agent model to make the representation of mechanism knowledge and data more consistent, so as to achieve more effective integration of the two. The experimental results show that the agent model not only significantly reduces the complexity of building the model, but also can accurately reflect the mapping relationship between data and fault-bearing location under different working conditions through only one measuring point, so as to achieve accurate diagnosis of fault-bearing location.

The research aims to study the surface characteristics analysis of cobalt-chromium alloy which is mostly used in femoral knee components using Industrial IRB 2400 Robot. Initially manual polishing from basic SiC abrasive papers to diamond slurry with a cloth polishing to achieve N2 grade of super finishing surfaces by the 11-step process. For incorporating the observation to polish the curved surface workpiece, the curve fit method is used by projecting its surface's curves on 2D planes, and thus, data on several control points for each continuous curve is obtained which gives a uniform polishing. To obtain desired grade of polishing in the least robot cycle time, 3 M Trizact belts of P1200 and P2500 equivalent grades as used for 1st two polishing stations of the Robot Finishing Cell. An industrial robot manipulator IRB2400 is used for polishing the workpiece to N2 grade. Forward kinematics helps in deciding the best use of the robot's work cell and inverse kinematics is calculated for avoiding singularities. After incorporating the data of several control points into the Depth First Search algorithm of robot programming. Surface finish results are explained using experimental observations which address the achievement of N2 super-finishing of the femoral knee component surfaces.

Flow field models with high resolution are essential for the effective navigation of marine vehicles. This paper proposes an improved Motion Tomography (MT) method for measuring and estimating the ocean flow field with unmanned surface vehicles (USVs). The MT method relies on measuring the differences between actual and predicted USV trajectories caused by ocean flows, that is, the motion-integration error. There are two main differences between the proposed MT and the traditional MT. First, the motion-integration error formulation is improved by considering the impact of the ocean flow on the heading of the USV. Second, the flow field estimation performance is improved due to the readily available USV actual trajectory information. Alongside the USV traversing within the field of interest, the information of the environmental flow field is gradually revealed with the improved flow field mapping. Due to the spatial and temporal discretization of the flow field, a parameterized flow field model is employed to address the high-dimensional solution space issue. With the estimated flow field model, the USV path is then carefully planned to maximize the sampled information along the path, known as informative path planning (IPP). We conducted sea trials in the East China Sea to validate the proposed MT method and the IPP application performance. The flow field information over a 300 m $��\; ��\times ��$ 300 m area is obtained using the proposed improved MT method and a dual-propeller USV. The USV path is then planned to sample the surface light-intensity information and automatically return in an energy-efficient way. Sea-trial results demonstrate that the measured path of the USV is highly consistent with the IPP planned path, which is not rushed away by the flow. Moreover, the energy consumption calculated based on the USV speed aligns closely with the IPP path planning predictions. Compared with the traditional MT method, the proposed approach improves energy consumption prediction accuracy by 20%. Therefore, from both the heading and speed perspectives, the results demonstrate that the proposed improved MT method can accurately estimate the ocean flow field and can improve the IPP performance.

This paper presents the design and development of a bionic blind-guiding robot based on a wheeled-legged foldable structure, aimed at assisting visually impaired individuals in navigating complex environments. The robot integrates the advantages of both legged and wheeled robots, combining high mobility and environmental adaptability with improved movement efficiency and stability. The mechanical design incorporates a foldable structure inspired by guide dogs, enabling the robot to navigate uneven terrain, climb stairs, and curl up under furniture. A comprehensive kinematic and dynamic model is established to facilitate precise control of the robot's motion. The control system employs a Virtual Model Control approach, with force distribution optimized using Quadratic Programming to ensure stable locomotion. The robot features multiple motion modes, including legged, wheeled, and wheeled-legged cooperative walking, allowing for flexible adaptation to different terrains. Human–robot interaction is enhanced through a guide saddle connection, providing tactile feedback and control options for the user. Experimental results demonstrate the robot's ability to maintain stability under varying traction forces and its effectiveness in guiding blind individuals through indoor and outdoor environments. The proposed design offers a promising solution for improving the mobility and independence of visually impaired individuals.

Manual transplanting of wash-root seedlings is a common practice among Indian farmers, but it involves significant labor and drudgery. To automate the transplanting process, this study presents a novel system that detects and centers wash-root nursery seedlings for robotic arm-assisted singulation, simulating human actions. Using pretrained architectures and data sets with 200 and 1000 images, a detection model was created. Uniquely, the study emphasizes how important it is to expand the data set to enhance model performance. Without using data augmentation approaches, the model was trained to detect and center seedlings by gathering a larger data set of 1000 photos. During laboratory evaluations, the larger data set significantly enhanced the model's detection accuracy and generalization ability, enabling precise centering of seedlings for robotic singulation. Performance was evaluated at three levels of epochs and data set ratios, with the model trained on 1000 images achieving an Average Precision of 63.4%, a High Confidence Score of 89%, and a Validation Loss of 3.19. Real-time evaluations using the selected model demonstrated exceptional centering capability, with a perfect visual rating of 100% for its ability to accurately center and singulate seedlings. This study offers a viable approach for automated transplanting in agriculture by highlighting the efficiency of using pretrained models, transfer learning, and cautious data set extension to improve robotic seedling handling.

Marine intervention tasks for retrieving large and heavy objects from vessels at sea are significantly important for maritime security. However, it remains a challenging task due to the lack of effective retrieval methods. Harsh open-sea conditions, unreliable Global Navigation Satellite System (GNSS) due to either interruptions or deliberate spoofing by other vessels, and the limitations of single robots in localizing and manipulating these objects pose significant challenges for the operations. To address these challenges, this article proposes an autonomous heterogeneous multirobot system comprising two commercial Unmanned Aerial Vehicles (UAVs) and a six-degrees-of-freedom robot arm mounted on a Unmanned Surface Vehicle (USV) to perform this complex task in a GNSS-denied marine environment. GNSS limitations for UAV localization are addressed using ultrawideband beacons specially installed on the USV. Our approach involves the robot arm initially estimating the object's position. Then the UAVs fly over the target vessel and search for the object using this information. Once the object is located, a custom-designed tethered-bar mechanism attached to the UAVs drags the object towards the workspace of the robot arm mounted on the USV. This study also introduces a decentralized framework to facilitate effective information sharing and collaboration among the robots. Field trials in maritime conditions demonstrate that by combining these elements, our system possesses significant potential for real-world maritime security and rescue applications. Videos of the field trials can be found at https://youtu.be/a_JzZf7QqWM.

Reliable sonar target tracking and image processing face significant challenges due to multiplicative speckle noise and the complexity of maneuvering target motion. Conventional approaches, such as median and Gaussian filtering for image processing and multihypothesis tracking or probability hypothesis density for target tracking, often struggle to address these issues effectively. Inspired by radar-based tracking techniques, we propose an enhanced track-oriented multihypothesis tracking algorithm incorporating track temporary storage to improve multitarget tracking performance. To suppress sonar image noise, we employ an advanced Wiener filter optimized with Kalman filtering. For target detection, a novel threshold segmentation method leveraging polygon fitting enhances the identification of salient sonar targets. The extracted target position data are then fed into an improved multitarget tracking framework based on a rectilinear–curvilinear hybrid multimodel interaction, which includes a mechanism for temporary storage of missed tracks. Simulation results demonstrate that this approach effectively mitigates multiplicative speckle noise, enhances the peak signal-to-noise ratio, and enables robust tracking of complex underwater target motion while reducing the optimal subpattern assignment error. Furthermore, experiments conducted using multibeam forward-looking sonar images in a laboratory-scale pool with a high-reverberation environment validate the proposed method's effectiveness. The present algorithms are expected to be integrated with the underwater vehicles' operating system for high-efficiency obstacle avoidance and maneuvering target tracking.