期刊,Robotics & Machine Learning Daily News 2024年卷Oct.8期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

New Robotics Study Findings Have Been Reported by Investigators at Anhui Univers ity of Science and Technology (Design of a Robotic Gripper for Casting Sorting R obots With Rigid-flexible Coupling Structures)

106-106页

查看更多>>摘要：Investigators discuss new findings in Robotics. According to news reporting from Huainan, People's Republic of China, by NewsRx journalists, research stated, "In order to solve the problem of the in sufficient adaptability of the current small- and medium-sized casting sorting r obot gripper, we have designed a casting sorting robot bionic gripper with rigid -flexible coupling structures based on the robot topology theory. The second-ord er Yeoh model was used to statically model the clamping belt in the gripper to d erive the relationship between the external input air pressure and the bending a ngle of the driving layer, and the feasibility of multiangle bending of the driv ing layer was verified by finite element analysis." Financial support for this research came from Natural Science Foundation of Anhu i Province. The news correspondents obtained a quote from the research from the Anhui Univer sity of Science and Technology, "The maximum gripping diameter of the gripper is 140 mm, and in order to test the adaptive gripping ability of the gripper, a pr ototype of the casting sorting robot gripper is prepared, and the pneumatic cont rol system and human-machine interface of the gripper are designed. After severa l experimental analyses, the designed casting sorting robot gripper is character ized by strong adaptability and high robustness, with a maximum load capacity of 930 g and a maximum wrap angle of 296 degrees, which can complete the gripping operation within 1 s, and the comprehensive gripping success rate reaches 96.4% ."

原文链接:

NETL
NSTL

Findings from Huaiyin Institute of Technology in the Area of Computational Intel ligence Described (Feature Autonomous Screening and Sequence Integration Network for Medical Image Classification)

107-107页

查看更多>>摘要：Investigators discuss new findings in Machine Learning-Computational Intelligence. According to news reporting out o f Huai'an, People's Republic of China, by NewsRx editors, research stated, "This article proposes a feature self-selection and sequence integration network, nam ely FASSI-Net, for medical image classification, which can extract representativ e deep features and contextual semantic information. In this network, FASSI-Net uses a new feature selection and integration module (FSIM) to compress the depth features, which uses a sequence model to replace the Flatten layer." Our news journalists obtained a quote from the research from the Huaiyin Institu te of Technology, "This strategy introduces two sets of multi-scale convolutions , where a cross-attention mechanism assigns two sets of weights (i.e., vertical and horizontal weights) to each convolution. We then calculate the Euclidean dis tance between different scale feature points to measure the correlation between them. Specifically, the feature points are divided into useful features and redu ndant features. In addition, a feature dimension compression (CRI) module is con structed to reconstruct the redundant feature structure, and the residual struct ure is used to extract the representative features from the redundant features. Meantime, a sequence model is introduced to compress the deep features and obtai n the context relationship between feature points."

原文链接:

NETL
NSTL

North-West University Reports Findings in Machine Translation (Machine translati on training data for English-Tshivenda)

107-108页

查看更多>>摘要：New research on Machine Translation is the subject of a report. According to news reporting out of Potchefstroom, Sout h Africa, by NewsRx editors, research stated, "This data article describes a mac hine translation training data set for translation between English and Tshivenda . The data set contains parallel, aligned English-Tshivenda data as well as mono lingual Tshivenda data." Our news journalists obtained a quote from the research from North-West Universi ty, "The data was collected from both web crawling of multilingual South African government sites and matched documents from translators or publishing sources. Additional unique data was translated from English into Tshivenda by professiona l translators to increase the total corpus size. This article contains informati on about the collection and translation of the data as well as how alignments an d corpus cleanup were done. The wordcounts of the corpus are also given."

原文链接:

NETL
NSTL

Findings from Shandong University Broaden Understanding of Robotics (Flingflow: Llm-driven Dynamic Strategies for Efficient Cloth Flattening)

108-109页

查看更多>>摘要：Investigators publish new report on Ro botics. According to news reporting originating from Jinan, People's Republic of China, by NewsRx correspondents, research stated, "The proficiency of robots in cloth manipulation is crucial for their potential widespread deployment in hous ehold service contexts, with the task of unfolding cloth being particularly indi spensable. Unlike rigid objects, cloth has a high-dimensional state space, which poses significant challenges for robotic operations." Funders for this research include High speed and high precision industrial robot , National Natural Science Foundation of China (NSFC), Meituan Academy of Roboti cs Shenzhen. Our news editors obtained a quote from the research from Shandong University, "T his paper presents a robotic framework that integrates dynamic and static operat ions for cloth unfolding. Dynamic operations are introduced in a single-arm scen ario, employing gravity to expedite flattening. Initially, we define the classif ication of cloth states and operational skills. Subsequently, in skill selection , a Large Language Model (LLM) is utilized to make decisions based on the curren t state, selecting skills appropriate for the given situation. For the determina tion of operation points, a cloth region segmentation network extracts key featu res of the cloth, and the final operation points are determined through geometri c analysis of the masks. Experiments on a real robot demonstrate that our method can successfully unfold cloths of various initial conditions, colors, sizes, te xtures, shapes and materials, achieving over 95$\ %$ coverage-defined as the ratio of the current are a of the fabric to its fully expanded area-thereby proving the effectiveness o f the combined dynamic and static operation strategy."

原文链接:

NETL
NSTL

New Research on Machine Learning from Satbayev University Summarized (Using Pseu do-Color Maps and Machine Learning Methods to Estimate Long-Term Salinity of Soi ls)

109-110页

查看更多>>摘要：A new study on artificial intelligence is now available. According to news reporting out of Almaty, Kazakhstan, by New sRx editors, research stated, "Soil salinity assessment methods based on remote sensing data are a common topic of scientific research. However, the developed m ethods, as a rule, estimate relatively small areas of the land surface at certai n moments of the season, tied to the timing of ground surveys." Funders for this research include Committee of Science of The Ministry of Scienc e And Higher Education of The Republic of Kazakhstan. Our news correspondents obtained a quote from the research from Satbayev Univers ity: "Considerable variability of weather conditions and the state of the earth surface makes it difficult to assess the salinity level with the help of remote sensing data and to verify it within a year. At the same time, the assessment of salinity on the basis of multiyear data allows reducing the level of seasonal f luctuations to a considerable extent and revealing the statistically stable char acteristics of cultivated areas of land surface. Such an approach allows, in our opinion, the processes of mapping the salinity of large areas of cultivated lan ds to be automated considerably. The authors propose an approach to assess the s alinization of cultivated and non-cultivated soils of arid zones on the basis of long-term averaged values of vegetation indices and salinity indices. This appr oach allows revealing the consistent relationships between the characteristics o f spectral indices and salinization parameters. Based on this approach, this pap er presents a mapping method including the use of multiyear data and machine lea rning algorithms to classify soil salinity levels in one of the regions of South Kazakhstan."

原文链接:

NETL
NSTL

New Robotics Study Results from University of Tennessee at Knoxville Described ( A Review of Robotic Arm Joint Motors and Online Health Monitoring Techniques)

110-111页

查看更多>>摘要：Investigators publish new report on ro botics. According to news reporting originating from Knoxville, Tennessee, by Ne wsRx correspondents, research stated, "The employment of robots in numerous emer ging applications, e.g., disaster rescue, nuclear waste remediation, and space e xploration, is of paramount importance due to their improved safety, flexibility , and productivity. Due to the harsh environmental conditions, the robotic arm j oint motors and power electronic drives are vulnerable to electrical faults and mainly contribute to joint failures." Funders for this research include U.S. National Science Foundation. Our news editors obtained a quote from the research from University of Tennessee at Knoxville: "To substantially improve the reliability and robustness of the r obot arms utilized in remote, hazardous, and safety-critical environments, auton omous fault-tolerant and fail-active operation for these robotic arms experienci ng joint failures should be developed. In the literature, many strategies have b een proposed for fault prognosis, diagnosis, and health monitoring of electric m otors and drives using online data analytics of the fault signature information. Thus, this paper presents an extensive up-to-date review of joint motor types, common fault types, and robot joint fault prognostics, diagnostics, and health m anagement. First, various joint motors are introduced and compared, considering their performance advantages, disadvantages, and wide applications. Furthermore, joint motors for collaborative robotic applications are summarized and compared as illustrative examples. After that, fault types are reviewed with a further c lassification by fault locations, namely, stator windings, rotors, and bearings. In addition, health monitoring techniques are classified into methods for stato r winding, rotor, and bearing faults."

原文链接:

NETL
NSTL

Studies from Chongqing University Provide New Data on Robotics (Online Evaluatio n for Learning Feasible Robotic Grasps With Physical Constraints)

111-112页

查看更多>>摘要：Fresh data on Robotics are presented i n a new report. According to news reporting originating in Chongqing, People's R epublic of China, by NewsRx journalists, research stated, "Existing grasp planni ng networks often learn from labeled images with grasp examples to eliminate the need for training through physical grasp attempts. As a result, trained network s lack an understanding of the physical constraints involved in successful grasp s, leading to infeasible predictions and inaccurate evaluation." Financial supporters for this research include National Key Research & Development Program of China, National Natural Science Foundation of China (NSFC ), Science and Technology Program of Liaoning Province.

原文链接:

NETL
NSTL

New Findings on Biomarkers Described by Investigators at Harbin Institute of Tec hnology (Vision-based Autonomous Robots Calibration for Large-size Workspace Usi ng Aruco Map and Single Camera Systems)

112-113页

查看更多>>摘要：New research on Diagnostics and Screen ing-Biomarkers is the subject of a report. According to news reporting origina ting in Harbin, People's Republic of China, by NewsRx journalists, research stat ed, "The low positioning accuracy of industrial robots limits their application in industry. Vision-based kinematic calibration, known for its rapid processing and economic efficiency, is an effective solution to enhance this accuracy." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Fundamental Research Funds for the Central Universities, Pos tdoctoral Fellowship Program of CPSF. The news reporters obtained a quote from the research from the Harbin Institute of Technology, "However, most of these methods are constrained by the camera's f ield of view, limiting their effectiveness in large workspaces. This paper propo ses a novel calibration framework composed of monocular vision and computer visi on techniques using ArUco markers. Firstly, a robot positioning error model was established by considering the kinematic error based on the Modified Denavit-Har tenberg model. Subsequently, a calibrated camera was used to create an ArUco map as an alternative to traditional single calibration targets. The map was constr ucted by stitching images of ArUco markers with unique identifiers, and its accu racy was enhanced through closed-loop detection and global optimization that min imizes reprojection errors. Then, initial hand-eye parameters were determined, f ollowed by acquiring the robot's end-effector pose through the ArUco map. The Le venberg-Marquardt algorithm was employed for calibration, involving iterative re finement of hand-eye and kinematic parameters. Finally, experimental validation was conducted on the KUKA kr500 industrial robot, with laser tracker measurement s as the reference standard."

原文链接:

NETL
NSTL

Study Findings on Robotics Are Outlined in Reports from Wuhan University of Tech nology (A Multi-population Cooperative Coevolution Artificial Bee Colony Algorit hm for Partial Multi-robotic Disassembly Line Balancing Problem Considering ...)

113-114页

查看更多>>摘要：024 OCT 08 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Research findings on Robotics are discussed in a new report. According to news reporting originating in Wuhan, People's Republic of China, by NewsRx journalists, research stated, "Existing literature on the ro botic disassembly line balancing problem often assume that robots are always in good working condition. But in fact, due to the inevitable aging of the machines , robots may break down unexpectedly." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), China Scholarship Council. The news reporters obtained a quote from the research from the Wuhan University of Technology, "And the original task assignment would become infeasible, which may lead to unplanned shutdowns of the disassembly line. To tackle this situatio n, a partial multi-robotic disassembly line balancing problem considering preven tive maintenance scenarios (PMRDLBP-PM) is proposed. The objectives of the PMRDL BP-PM not only encompass the traditional goals of robotic disassembly line balan cing problem, such as cycle time and disassembly profitability, but also take in to account the potential additional time and cost incurred from the reconfigurat ion of workstations necessitated by changes in task allocation. Then, a multipo pulation cooperative coevolution artificial bee colony (MPCCABC) algorithm is de veloped. Specifically, to enhance the quality of the initial population and ensu re population diversity, the population is divided into four subpopulations, inc luding three high-quality subpopulations generated by heuristic rules based on o ptimization objectives, and one randomly generated subpopulation. And an adaptiv e progressive neighborhood search strategy is proposed to improve search efficie ncy by adjusting the complexity of neighborhood operations based on search feedb ack. Moreover, a cooperative co-evolution strategy with historical information i s adopted to supplement historical optimal information in subpopulation informat ion exchange, increasing computing resource utilization and accelerating converg ence speed. Finally, three instances are conducted to test the validity of the p roposed model and algorithm."

原文链接:

NETL
NSTL

Recent Findings in Machine Learning Described by Researchers from Korea Food Res earch Institute [Innovative strategies for protein content de termination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning ...]

114-115页

查看更多>>摘要：2024 OCT 08 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-A new study on artificial intelligence is now ava ilable. According to news originating from the Korea Food Research Institute by NewsRx correspondents, research stated, "In this study, we explored the applicat ion of Short-Wave Infrared (SWIR) hyperspectral imaging combined with Competitiv e Adaptive Reweighted Sampling (CARS) and advanced regression models for the non -destructive assessment of protein content in dried laver." Financial supporters for this research include Korea Institute of Planning And E valuation For Technology in Food, Agriculture, Forestry And Fisheries; Ministry of Oceans And Fisheries; Korea Food Research Institute; Ministry of Science, Ict And Future Planning; Korea Institute of Science And Technology; Korea Institute of Marine Science And Technology Promotion; Ministry of Agriculture, Food And R ural Affairs.

原文链接:

NETL
NSTL