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

    Investigators from Guangdong University of Technology Target Robotics (Leg-kilo: Robust Kinematic-inertial-lidar Odometry for Dynamic Legged Robots)

    86-86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 originating from Guangzhou, People's Republic o f China, by NewsRx correspondents, research stated, "This letter presents a robu st multi-sensor fusion framework, Leg-KILO (Kinematic-Inertial-Lidar Odometry). When lidar-based SLAM is applied to legged robots, high-dynamic motion (e.g., tr ot gait) introduces frequent foot impacts, leading to IMU degradation and lidar motion distortion." Financial support for this research came from Guangdong Basic and Applied Basic Research Foundation. Our news journalists obtained a quote from the research from the Guangdong Unive rsity of Technology, "Direct use of IMU measurements can cause significant drift,especially in the z-axis direction. To address these limitations, we tightly c ouple leg odometry, lidar odometry, and loop closure module based on graph optim ization. For leg odometry, we propose a kinematic-inertial odometry using an on- manifold error-state Kalman filter, which incorporates the constraints from our proposed contact height detection to reduce height fluctuations. For lidar odome try, we present an adaptive scan slicing and splicing method to alleviate the ef fects of high-dynamic motion. We further propose a robot-centric incremental map ping system that enhances map maintenance efficiency. Extensive experiments are conducted in both indoor and outdoor environments, showing that Leg-KILO has low er drift performance compared to other state-of-the-art lidar-based methods, esp ecially during high-dynamic motion."
      原文链接:
    • NETL
    • NSTL

    Reports Outline Robotics Findings from Yanshan University (Error Identification and Accuracy Compensation Algorithm for Improved 2rpu/upr+r+p Hybrid Robot)

    87-87页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Researchers detail new data in Robotics. Accordin g to news reporting from Qinhuangdao, People's Republic of China, by NewsRx jour nalists, research stated, "To improve the precision of the 2RPU/UPR+R+P hybrid r obot and fulfill production requirements, error compensation was explored. The r obot's fixed coordinate system was first used to analyze the workbench error map ping matrix." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news correspondents obtained a quote from the research from Yanshan Universi ty, "Next, the correlation between the joint geometric errors and the moving pla tform kinematic errors of the parallel robot module was examined. The sensitivit y of joint geometric errors to the kinematic errors across the entire workspace was determined using statistical methods. Then, a genetic algorithm was employed to identify the joint geometric errors, leading to a kinematic model that accou nts for these inaccuracies. Subsequently, the accuracy of the robot was measured,and the results showed that the accuracy of the hybrid robot was improved by 7 2% in the X-axis direction with poor accuracy. Finally, a sample p rocessing experiment was conducted by the robot."
      原文链接:
    • NETL
    • NSTL

    Findings on Machine Learning Reported by Investigators at Beijing University of Chemical Technology (Combining Machine Learning and Molecular Simulation To Expl ore Mof Materials That Contribute To Cf4/n2 Separation)

    88-89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 reporting originating from Beijing, People's Republ ic of China, by NewsRx correspondents, research stated, "Highthroughput molecul ar simulations and machine learning algorithms have been widely used to identify promising metal-organic frameworks for gas separation. However, most studies ar e limited to screening highperformance materials from existing databases, which fails to fully utilize the predictive function of machine learning." Financial support for this research came from National Key R & D P rogram of China. Our news editors obtained a quote from the research from the Beijing University of Chemical Technology, "This paper combines genetic algorithms and high-through put screening to deeply mine anion-pillared MOF (APMOF) performance feature rela tionships and predict high-performance materials that are not in the database. C onsidering the actual industrial conditions (CF4/N2 = 10/90), we chose the ratio of CF4:N2 = 1:9 to simulate the adsorption separation of gas mixtures of MOF ma terials at a temperature of 298 K and a pressure of 1 bar. First, the CF4/N2 sep aration properties of MOFs in the APMOF library were obtained based on molecular simulations. Then, the filtered data were coded according to the method of ‘bui lding block classification structural interval categorization'. Then, the machin e learning algorithm was used for model training to obtain a high-precision mode l. Finally, the tangent adaptive genetic algorithm was used to recombine the gen es of the materials, and the new MOF materials were successfully reverse-enginee red. The study found that the pore-limit diameter of APMOFs is most conducive to the separation of CF4/N2 by MOFs when the pore-limit diameter of APMOFs is with in two times the molecular dynamics diameter of CF4. 134 MOF materials were pred icted to have CF4/N2 selectivities exceeding 46.30. The use of organic ligands s uch as 4,4 ‘-bipyridyl or 1,4-bis(4-pyridyl)benzene (bpb) increases the likeliho od of these materials being high-performance for CF4/N2 separation. The combinat ion of computational screening methods and machine learning can expedite the des ign and development of new high-performance MOFs."
      原文链接:
    • NETL
    • NSTL

    Recent Findings from Taiyuan University of Science & Technology Pr ovides New Insights into Robotics (Dynamic Load Acquisition Method for a Crawler Driving Structure of a Roadheader Robot Under Random Road)

    89-89页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Robotics are disc ussed in a new report. According to news reporting from Shanxi, People's Republi c of China, by NewsRx journalists, research stated, "A method utilizing an embed ded sensing system to determine the dynamic load is proposed to address the prob lem of not being able to directly obtain the dynamic load time history of a craw ler driving structure in the harsh underground working environment of a coal min e roadheader robot. A crawler driving structure and its embedded sensing system are designed." Funders for this research include National Natural Science Foundation of China ( NSFC), Shanxi Provincial Key Research and Development Project.
      原文链接:
    • NETL
    • NSTL

    Data from Anna University Provide New Insights into Machine Learning (Effective Monitoring of Noyyal River Surface Water Quality Using Remote Sensing and Machin e Learning and Gis Techniques)

    90-90页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting out of Tamil Nadu, In dia, by NewsRx editors, research stated, "This study utilizes Geographic Informa tion System (GIS) and remote sensing techniques to predict water quality metrics in the Noyyal River. Satellite data is employed to construct statistical models,with preprocessing involving adjustments from Landsat 8 images." Our news journalists obtained a quote from the research from Anna University, "T he hybrid LASSO model demonstrates superior performance in predicting water qual ity parameters, supported by key performance metrics such as RMSE, R-squared, an d ANOVA results. The study focuses on assessing the suitability of the hybrid LA SSO model for predicting the Water Quality Index (WQI) in the Noyyal region, hig hlighting its ability to handle high-dimensional data and provide interpretable results. Prediction models employing the LASSO approach yield promising results, with Rsquared values exceeding 0.87 for temperature and pH. Incorporating spect ral indices significantly enhances model performance, with an average R-squared of 0.8. These models offer cost-effective options for monitoring water quality, revealing poor conditions in the Noyyal River and projecting deterioration for 2 023."
      原文链接:
    • NETL
    • NSTL

    Chinese Academy of Sciences Reports Findings in Artificial Intelligence (Utilizi ng artificial intelligence for precision exploration of N protein targeting phen anthridine sars-cov-2 inhibitors: A novel approach)

    91-91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 Artificial Intelligenc e is the subject of a report. According to news reporting from Kunming, People's Republic of China, by NewsRx journalists, research stated, "The persistent muta tion of the novel coronavirus presents a continual threat of infections and asso ciated illnesses. While considerable research efforts have concentrated on the f unctional proteins of SARS-CoV-2 in the development of anti-COVID-19 therapeutic s, the structural proteins, particularly the N protein, have received comparativ ely less attention." The news correspondents obtained a quote from the research from the Chinese Acad emy of Sciences, "This study focuses on the N protein, a critical structural com ponent of the virus, and employs advanced deep learning models, including EMPIRE and DeepFrag, to optimize the structures of phenanthridinebased compounds. Mor e than 10,000 small molecules, derived through deep learning, underwent high-thr oughput virtual screening, resulting in the synthesis of 44 compounds. Compound 38 showed a binding potential energy of -8.2 kcal/mol in molecular docking. Surf ace Plasmon Resonance (SPR) and Microscale Thermophoresis (MST) validation yield ed dissociation constants of 353 nM and 726 nM, confirming strong binding to the N protein. Compound 38 demonstrated antiviral activity in vitro and exhibited a nti-COVID- 19 effects by interfering with the binding of N proteins to RNA. This research underscores the potential of targeting the SARS-CoV-2 N protein for the rapeutic intervention and illustrates the efficacy of deep learning model in the design of lead compounds."
      原文链接:
    • NETL
    • NSTL

    New Robotics Study Findings Have Been Reported by Researchers at Hunan University (Adaptive Finite-time Coordination Control of a Multi-robotic Fiber Placement System With Model Uncertainties and Closed Architecture)

    92-92页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Data detailed on Robotics have been presented. Ac cording to news reporting from Changsha, People's Republic of China, by NewsRx j ournalists, research stated, "The coordination and trajectory tracking accuracy of multi-robotic fiber placement systems (MRFPSs) are critical to assure the qua lity of the fiber placement process. However, the model uncertainties and closed architecture (CA) in industrial robots significantly hinder the system from ach ieving high performance in coordination and tracking simultaneously." Financial supporters for this research include Major Project of Xiangjiang Labor atory, National Natural Science Foundation of China (NSFC), Natural Science Foun dation of Hunan Province, CGIAR.
      原文链接:
    • NETL
    • NSTL

    Reports Outline Machine Learning Study Findings from Northeast Agricultural Univ ersity (Dempster Shafer Distance-based Multiclassifier Fusion Method for Pig Co ugh Recognition)

    93-93页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators discuss new findings in Machine Lea rning. According to news reporting from Harbin, People's Republic of China, by N ewsRx journalists, research stated, "High precision pig cough recognition and lo w computational cost is of great importance for the realization of early warning of pig respiratory diseases. Numerous researchers have improved the recognition rate of pig cough sounds to a certain extent from feature selection and feature fusion perspectives." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Academic Backbone Project of Northeast Agricultural Universi ty, National Key Research & Development Program of China, Universi ty Nursing Program for Young Scholars with Creative Talents in Heilongjiang Prov ince.
      原文链接:
    • NETL
    • NSTL

    Data from Swiss Federal Institute of Technology Lausanne (EPFL) Provide New Insi ghts into Machine Learning (Accelerated Design of Nickel-cobalt Based Catalysts for Co2 Hydrogenation With Humanin-the-loop Active Machine Learning)

    94-95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 Machine Learning have been presented. According to news reporting from Sion, Switzerland, by NewsRx j ournalists, research stated, "Thermo-catalytic conversion of CO2 into more valua ble compounds, such as methane, is an attractive strategy for energy storage in chemical bonds and creating a carbon-based circular economy. However, designing heterogeneous catalysts remains a challenging, time- and resource-consuming task ." Funders for this research include FWO, EPFL, Centre Interdisciplinaire de Micros copie Electronique (CIME), FWO, European Research Council (ERC). The news correspondents obtained a quote from the research from the Swiss Federa l Institute of Technology Lausanne (EPFL), "Herein, we present an interpretable, human-in-the-loop active machine learning framework to efficiently plan catalyt ic experiments, execute them in an automated set-up, and estimate the effect of experimental variables on the catalytic activity. A dataset with 48 catalytic ac tivity tests was compiled from a design space of Ni-Co/Al2O3 catalysts with over 50 million potential combinations in only eight iterations. This small dataset was found sufficient to predict CO2 conversion, methane selectivity, and methane space-time yield with remarkable accuracy (R-2 > 0.9) f or untested catalysts and reaction conditions. New experiments and catalysts wer e selected with this methodology, leading to experimental conditions that improv ed the methane space-time yield by nearly 50% in comparison to the previously obtained maximum in the dataset. Interpretation of the model predict ions unveiled the effect of each catalyst descriptor and reaction condition on t he outcome. Particularly, the strong predicted inverse trend between the calcina tion temperature and the catalytic activity was validated experimentally, and ch aracterization implied an underlying structure-performance relationship. Finally,it is demonstrated that the deployed active learning model is excellently suit ed to predict and fit kinetic trends with a minimal amount of data."
      原文链接:
    • NETL
    • NSTL

    Studies Conducted at Tongji University on Robotics Recently Reported (T-td3: a R einforcement Learning Framework for Stable Grasping of Deformable Objects Using Tactile Prior)

    95-95页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Robotics are presented i n a new report. According to news reporting from Shanghai, People's Republic of China, by NewsRx journalists, research stated, "Human tactile perception enables rapid assessment of deformable objects and the application of appropriate force to prevent slip or excessive deformation. However, this task remains challengin g for robots." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Science & Technology Commission of Shanghai Mu nicipality (STCSM), Fundamental Research Funds for the Central Universities. The news correspondents obtained a quote from the research from Tongji University, "To address this issue, we propose the T-TD3 algorithm, which utilizes a mult i-scale fusion neural network (MSF-Net) for the fused perception of multi-scale features, including the tactile prior information obtained through preprocessing . Our approach decomposes the robot task of grasping deformable objects into thr ee subtasks: slip detection, stable grasping evaluation, and minimum grasping fo rce tracking. We develop a simulation environment called CR5GraspStable-Env usin g PyBullet and TACTO for the network training. Our work reports a success rate o f 94.81% in the robot task of grasping deformable objects in real, demonstrating an excellent sim-to-real capability."
      原文链接:
    • NETL
    • NSTL