首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Research on Robotics Detailed by Researchers at Seoul National University of Sci ence and Technology (Real-Time Performance Benchmarking of RISC-V Architecture: Implementation and Verification on an EtherCAT-Based Robotic Control System)

    47-48页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on robotics have been pr esented. According to news reporting originating from Seoul, South Korea, by New sRx correspondents, research stated, "RISC-V offers a modular technical approach combined with an open, royalty-free instruction set architecture (ISA). However, despite its advantages as a fundamental building block for many embedded syste ms, the escalating complexity and functional demands of real-time applications h ave made adhering to response time deadlines challenging." Our news reporters obtained a quote from the research from Seoul National Univer sity of Science and Technology: "For real-time applications of RISC-V, real-time performance analysis is required for various ISAs. In this paper, we analyze th e real-time performance of RISC-V through two real-time approaches based on proc essor architectures. For real-time operating system (RTOS) applications, we adop ted FreeRTOS and evaluated its performance on HiFive1 Rev B (RISC-V) and STM3240 G-EVAL (ARM M). For real-time Linux, we utilized Linux with the Preempt-RT patch and tested its performance on VisionFive 2 (RISC-V), MIO5272 (x86-64), and Rasp berry Pi 4 B (ARM A). Through these experiments, we examined the response times on the real-time mechanisms of each operating system. Additionally, in the Preem pt- RT experiments, scheduling latencies were evaluated by means of the cyclictes t. These are very important parameters for implementing real-time applications c omprised of multi-tasking. Finally, in order to show the real-time capabilities of RISC-V practically, we implemented motion control of a six-axis collaborative robot, which was performed on the VisionFive 2. This implementation provided a comparative result of RISC-V's performance against the x86-64 architecture. Ulti mately, the results indicated that the real-time performance of RISC-V for real- time applications was feasible."
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Study Findings Have Been Reported by Researchers at Shanxi Agricultural University (Predicting Individual Tree Mortality of * * Larix gmeli nii* * var. * * Principis-rupprechtii* * in Temperate Forests Using Machine Lear ning ...)

    48-49页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news reporting from Taiyuan, People's Republic o f China, by NewsRx journalists, research stated, "Accurate prediction of individ ual tree mortality is essential for informed decision making in forestry." Funders for this research include Shanxi Province Basic Research Program, Youth Science Research Project; Shanxi Province Key Research And Development Program; National Natural Science Foundation of China. The news editors obtained a quote from the research from Shanxi Agricultural Uni versity: "In this study, we proposed machine learning models to forecast individ ual tree mortality within the temperate * * Larix gmelinii* * var. * * principis -rupprechtii* * forests in Northern China. Eight distinct machine learning techn iques including random forest, logistic regression, artificial neural network, g eneralized additive model, support vector machine, gradient boosting machine, k- nearest neighbors, and naive Bayes models were employed, to construct an ensembl e learning model based on comprehensive dataset from this specific ecosystem. Th e random forest model emerged as the most accurate, demonstrating 92.9% accuracy and 92.8% sensitivity, making it the best model among tho se tested. We identified key variables impacting tree mortality, and the results showed that a basal area larger than the target trees (BAL), a diameter at 130 cm (DBH), a basal area (BA), an elevation, a slope, NH4-N, soil moisture, crown density, and the soil's available phosphorus are important variables in the * * Larix Principis-rupprechtii* * individual mortality model. The variable importan ce calculation results showed that BAL is the most important variable with an im portance value of 1.0 in a random forest individual tree mortality model."
      原文链接:
    • NETL
    • NSTL

    New Robotics Data Have Been Reported by Researchers at University of Applied Sci ences (Fatigue Behaviour of Automatically Hfmi-treated Welds)

    49-50页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Robotics is now availab le. According to news reporting originating from Munich, Germany, by NewsRx corr espondents, research stated, "Due to notches, welds are most critical regarding fatigue failure within cyclic loaded constructions. Therefore, various post-weld -treatment techniques like post-weld treatment by high-frequency mechanical impa ct (HFMI) treatment have been invented to improve the fatigue strength of welded details." Financial support for this research came from Central Innovation Programme for S MEs (ZIM) funded by the Federal Ministry of Economics and Climate Protection (BM WK) (Zentralen Innovationsprogramms Mittelstand (ZIM) Bundesministerium fr Wirts chaft und Klimaschutz (BMWK)). Our news editors obtained a quote from the research from the University of Appli ed Sciences, "The benefit, resulting from HFMI treatment, has already been prove n by numerous studies. Since a manual HFMI treatment must be performed by a skil led and trained person to ensure an acceptable treatment quality, an automated a pplication of HFMI treatment is supposed to result in a more reliable and consis tent treatment result, which does not depend on the operator. Furthermore, a rob otic application of HFMI treatment enables an economic implementation of HFMI tr eatment of automated welded constructions like offshore wind energy converters a nd various mechanical components, as these parts do not have to be taken out of the production chain to manually perform HFMI treatment."
      原文链接:
    • NETL
    • NSTL

    Researchers from Technische Universitat Chemnitz Discuss Research in Robotics (D istributed agency in HRI-an exploratory study of a narrative robot design)

    50-50页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on robotics have been published. According to news reporting from Chemnitz, Germany, by NewsRx j ournalists, research stated, "We explore an alternative approach to the design o f robots that deviates from the common envisionment of having one unified agent. " Financial supporters for this research include Volkswagen Foundation. Our news reporters obtained a quote from the research from Technische Universita t Chemnitz: "What if robots are depicted as an agentic ensemble where agency is distributed over different components? In the project presented here, we investi gate the potential contributions of this approach to creating entertaining and j oyful human-robot interaction (HRI), which also remains comprehensible to human observers. We built a service robot-which takes care of plants as a Plant-Wateri ng Robot (PWR)-that appears as a small ship controlled by a robotic captain acco mpanied by kinetic elements. The goal of this narrative design, which utilizes a distributed agency approach, is to make the robot entertaining to watch and fos ter its acceptance. We discuss the robot's design rationale and present observat ions from an exploratory study in two contrastive settings, on a university camp us and in a care home for people with dementia, using a qualitative video-based approach for analysis. Our observations indicate that such a design has potentia l regarding the attraction, acceptance, and joyfulness it can evoke."
      原文链接:
    • NETL
    • NSTL

    Recent Studies from Donghua University Add New Data to Machine Learning (Predict ing the Thermal Protective Performance of Flame-retardant Fabric Based On Machin e Learning)

    51-51页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning. According to news originating from Shanghai, People's Republic of Chi na, by NewsRx correspondents, research stated, "PurposeThe purpose of this study is to predict the thermal protective performance (TPP) of flame-retardant fabri c more economically using machine learning and analyze the factors affecting the TPP using model total of 13 machine learning models were trained by collecting 414 datasets of typical flame-retardant fabric from current literature. The optimal performance model was used for feature importance ranking and correlation variable analysis through model visualization. FindingsFive models with better performance were scr eened, all of which showed R2 greater than 0.96 and root mean squared error less than 3.0." Funders for this research include Fundamental Research Funds for the Central Uni versities, International Cooperation Fund of Science and Technology Commission o f Shanghai Municipality.
      原文链接:
    • NETL
    • NSTL

    Faculty of Electrical Engineering Researcher Targets Robotics (Improving the Qua lity of Industrial Robot Control Using an Iterative Learning Method with Online Optimal Learning and Intelligent Online Learning Function Parameters)

    52-53页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New study results on robotics have been published . According to news reporting originating from Hanoi, Vietnam, by NewsRx corresp ondents, research stated, "It is inevitable that the characteristics of a robot system change inaccurately or cannot be accurately determined during movement an d are affected by external disturbances." Our news reporters obtained a quote from the research from Faculty of Electrical Engineering: "There are many adaptive control methods, such as the exact linear ization method, sliding control, or neural control, to improve the quality of tr ajectory tracking for a robot's motion system. However, those methods require a great deal of computation to solve the constrained nonlinear optimization proble m. This article first presents some techniques for determining the online learni ng function parameters of an intelligent controller, including two circuits: the inner circuit is an uncertain function component estimator to compensate for th e robot's input, and the outer circuit is an iterative learning controller and d oes not use a mathematical model of the robot with optimal online learning funct ion parameters. The optimal condition is based on the model in the time domain t o determine the learning function parameters that change adaptively according to the sum of squared tracking errors of each loop. As for the intelligent online learning function parameters, they closely follow the general model to stabilize the robot system, based on the principle of intelligent estimation of the uncer tainty component and total noise. This method is built on Taylor series analysis for the state vector and does not use a mathematical model of the system at all ."
      原文链接:
    • NETL
    • NSTL

    Dalian Minzu University Reports Findings in Machine Learning (Significant durati on prediction of seismic ground motions using machine learning algorithms)

    52-52页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news reporting from Liaoning, People's Republic of Chin a, by NewsRx journalists, research stated, "This study aims to predict the signi ficant duration (D5-75, D5-95) of seismic motion by employing machine learning a lgorithms. Based on three parameters (moment magnitude, fault distance, and aver age shear wave velocity), two additional parameters(fault top depth and epicente r mechanism parameters) were introduced in this study." The news correspondents obtained a quote from the research from Dalian Minzu Uni versity, "The XGBoost algorithm is utilized for characteristic parameter optimiz ation analysis to obtain the optimal combination of four parameters. We compare the prediction results of four machine learning algorithms (random forest, XGBoo st, BP neural network, and SVM) and develop a new method of significant duration prediction by constructing two fusion models (stacking and weighted averaging). The fusion model demonstrates an improvement in prediction accuracy and general ization ability of the significant duration when compared to single algorithm mo dels based on evaluation indicators and residual values." According to the news reporters, the research concluded: "The accuracy and ratio nality of the fusion model are validated through comparison with existing resear ch."
      原文链接:
    • NETL
    • NSTL

    Nanjing University of Aeronautics and Astronautics Reports Findings in Robotics (Computational design of ultra-robust strain sensors for soft robot perception a nd autonomy)

    53-54页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting originating in Nanjing, People's Repu blic of China, by NewsRx journalists, research stated, "Compliant strain sensors are crucial for soft robots' perception and autonomy. However, their deformable bodies and dynamic actuation pose challenges in predictive sensor manufacturing and long-term robustness." The news reporters obtained a quote from the research from the Nanjing Universit y of Aeronautics and Astronautics, "This necessitates accurate sensor modelling and well-controlled sensor structural changes under strain. Here, we present a c omputational sensor design featuring a programmed crack array within micro-crump les strategy. By controlling the user-defined structure, the sensing performance becomes highly tunable and can be accurately modelled by physical models. Moreo ver, they maintain robust responsiveness under various demanding conditions incl uding noise interruptions (50% strain), intermittent cyclic loadin gs (100,000 cycles), and dynamic frequencies (0-23 Hz), satisfying soft robots o f diverse scaling from macro to micro. Finally, machine intelligence is applied to a sensor-integrated origami robot, enabling robotic trajectory prediction (<4% error) and topographical altitude awareness (<10% error)."
      原文链接:
    • NETL
    • NSTL

    University of Alberta Researcher Updates Knowledge of Support Vector Machines (U sing Explainable AI for Enhanced Understanding of Winter Road Safety: Insights w ith Support Vector Machines and SHAP)

    54-55页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on . According to news reporting originating from Edmonton, Canada, by NewsRx corresp ondents, research stated, "This study investigates the utility of machine learni ng (ML) in understanding and mitigating winter road risks." The news editors obtained a quote from the research from University of Alberta: "Despite their capability in managing complex data structures, ML models often l ack interpretability. We address this issue by integrating Shapley Additive Expl anations (SHAP) with a Support Vector Machine (SVM) model. Utilizing a comprehen sive dataset of 231 snowstorm events collected in the city of Edmonton across tw o winter seasons, the SVM model achieved an accuracy rate of 87.2%. Following model development, a SHAP summary plot was employed to identify the c ontribution of individual features to collision predictions-an insight not achie vable through ML alone."
      原文链接:
    • NETL
    • NSTL

    Research from University of Aveiro Has Provided New Data on Support Vector Machi nes (Service-Aware Hierarchical Fog-Cloud Resource Mappingfor e-Health with Enha nced-Kernel SVM)

    55-56页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in support vector machines. According to news reporting out of Aveiro, Portugal, by NewsRx editors, research stated, "Fog-cloud-based hierarchical task-scheduling methods are embracing significant challenges to support e-Health applications due to th e large number of users, high task diversity, and harsher service-level requirem ents." Financial supporters for this research include Fct/mctes Through National Funds And When Applicable Co-funded Eu Funds. Our news reporters obtained a quote from the research from University of Aveiro: "Addressing the challenges of fog-cloud integration, this paper proposes a new service/network-aware fog-cloud hierarchical resource-mapping scheme, which achi eves optimized resource utilization efficiency and minimized latency for service -level critical tasks in e-Health applications. Concretely, we develop a service /network-aware task classification algorithm. We adopt support vector machine as a backbone with fast computational speed to support real-time task scheduling, and we develop a new kernel, fusing convolution, cross-correlation, and auto-cor relation, to gain enhanced specificity and sensitivity. Based on task classifica tion, we propose task priority assignment and resource-mapping algorithms, which aim to achieve minimized overall latency for critical tasks and improve resourc e utilization efficiency."
      原文链接:
    • NETL
    • NSTL