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

    Researchers Submit Patent Application, 'System And Method For Determining Target Feature Focus In Image-Based Overlay Metrology', for Approval (USPTO 20240020353)

    133-136页
    查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors Lavert, Etay (Milpitas, CA, US); Manassen, Amnon (Haifa, IL); Safrani, Avner (Misgav, IL); Sanko, Dimitry (Vallejo, CA, US); Simon, Yossi (Milpitas, CA, US), filed on January 16, 2023, was made available online on January 18, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “Image-based overlay metrology may typically include determining relative offsets between two or more layers on a sample based on relative imaged positions of features of an overlay target in the different layers of interest. The accuracy of the overlay measurement may thus be sensitive to image quality associated with imaged features on each sample layer, which may vary based on factors such as a depth of field or location of the plane (e.g., focal position) with respect to the sample. Accordingly, overlay metrology procedures typically include tradeoffs between image quality at particular sample layers and throughput. For example, it may be the case that overlay measurements based on separate images of each sample layer may provide the highest quality images of overlay target features. However, capturing multiple images per target may reduce throughput. By way of another example, overlay measurements based on a single image capturing features on multiple layers may provide relatively higher throughput, but may require reference measurements based on external tools or full-wafer measurements to provide a desired measurement accuracy. Therefore, it would be desirable to provide a system and method for curing defects such as those identified above.”
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Artificial intelligence (AI) based anomaly signatures warning recommendation system and method (USPTO 11874652)

    136-140页
    查看更多>>摘要：Noodle Analytics Inc. (San Francisco, California, United States) has been issued patent number 11874652, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Balasubramanian, Ravishankar (Bengaluru, IN), Ravikant (Rajasthan, IN). This patent was filed on December 15, 2021 and was published online on January 16, 2024. From the background information supplied by the inventors, news correspondents obtained the following quote: “Embodiments of the present invention generally relate to surveillance systems and methods for monitoring assets in connected systems, and more particularly to Artificial Intelligence (AI)-based warning recommendation systems for such environments. “Typical industrial plants are connected systems with inter-dependency of operations between upstream and downstream assets within a processing or a production line. Unplanned downtime within a production or processing line is of concern across these industrial plants, and is often a result of errant behavior of an upstream or downstream equipment. Non-limiting examples of causes for unplanned downtime include failure of critical asset, quality specification of end product in line not being met, input/output specification of component not met in a connected system, operational limits (e.g. process, human-safety, equipmentsafety, etc.) outside recommended range, and the like. Unplanned downtime can lead to production loss and/or energy wastage.
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Method for Controlling Displacement of a Robot' Published Online (USPTO 20240017411)

    140-144页
    查看更多>>摘要：According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Bjorkman, Mattias (Vasteras, SE); Clever, Debora (Zwingenberg, DE); Enayati, Nima (Mannheim, DE); Haulin, Jonas (Shanghai, CN); Norrlof, Mikael (Norrkoping, SE); Spampinato, Giacomo (Vasteras, SE); Wahrburg, Arne (Weiterstadt, DE), filed on September 27, 2023, was made available online on January 18, 2024. The assignee for this patent application is ABB Schweiz AG (Baden, Switzerland). Reporters obtained the following quote from the background information supplied by the inventors: “Every robot has an inherent coordinate system, in which each coordinate is associated to a specific actuator, and isolated operation of that actuator will modify only the coordinate associated to it. In articulated robots, these inherent coordinates are angular coordinates, and a position in Cartesian space the robot will assume when the actuators are set to the coordinates specified by a given inherent coordinate vector can be calculated quite straightforwardly when dimensions of the robot’s links are known. Finding out an inherent coordinate vector associated to a desired position in Cartesian space is a more complicated problem, which, depending on the design of the robot and the position chosen, may have a single solution, several ones, or none at all. Things get still more complicated if not only the position of a reference point of the robot, e.g., a tool center point, in Cartesian space, is considered, but also the spatial orientation of a tool or other object attached to said reference point. In general, it is therefore impractical for a human user to control displacement of a robot by specifying a target pose directly in the robot’s inherent coordinate system. Instead, the user will specify a target pose in some more convenient coordinate system, and the task of finding an inherent coordinate vector which will yield this pose, and of setting the actuators of the robot to their respective coordinate values specified by the inherent coordinate vector is left to a dedicated controller.
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Model Training Method And Apparatus' Published Online (USPTO 20240020541)

    144-150页
    查看更多>>摘要：According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors GAO, Yong (Shenzhen, CN); GUO, Huifeng (Shenzhen, CN); GUO, Wei (Beijing, CN); HE, Xiuqiang (Shenzhen, CN); LIU, Wenzhi (Shenzhen, CN); TANG, Ruiming (Shenzhen, CN), filed on September 28, 2023, was made available online on January 18, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “Artificial intelligence (AI) is a theory, a method, a technology, and an application system that simulates, extends, and expands human intelligence by using a digital computer or a machine controlled by the digital computer, to perceive an environment, obtain knowledge, and achieve an optimal result based on the knowledge. In other words, artificial intelligence is a branch of computer science and attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is to research design principles and implementation methods of various intelligent machines, so that the machines have perception, inference, and decisionmaking functions.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Custom time series models in computer analytics systems (USPTO 11875275)

    150-153页
    查看更多>>摘要：Splunk Inc. (San Francisco, California, United States) has been issued patent number 11875275, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Ghosh, Koulick (San Francisco, CA, US), Tsironis, George (San Francisco, CA, US). This patent was filed on February 21, 2023 and was published online on January 16, 2024. From the background information supplied by the inventors, news correspondents obtained the following quote: “Network systems are a set of interconnected devices that together provide computing functionality. For example, networks may include storage devices, end-user terminals, application servers, routers, and other devices. Network systems can continually produce massive volumes of data. Because of the amount of data, models are executed by computers to analyze the data and detect information about the users and hardware that directly or indirectly cause the data. For example, anomaly detection is used for systems to detect fraud, security threats, and the existence of faulty data. Because of the complicated nature of models, as well as the level of understanding required to create a model that can be interpreted by a computer, enterprise system creators define a fixed set of models which are provided with the enterprise system.”
      原文链接:
    • NETL
    • NSTL

    SLEDGe: Inference of ancient whole genome duplications using machine learning

    153-154页
    查看更多>>摘要：According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from biorxiv.org: “Ancient whole-genome duplication–previous genome duplication events that have since been eroded via diploidization, are increasingly identified throughout eukaryotes. One of the constraints against large-scale studies of ancient eukaryotic WGD is the relatively large, high-quality datasets often needed to definitively establish ancient WGD events; alternatively, the more low-input method interpretation of genome-wide synonymous substitution rates (Ks plots) is prone to bias and inconsistency. We improve upon the shortcomings of the current Ks plot method by building a Ks plot simulator. “This data-agnostic approach simulates common distributions found in Ks plots in the presence or absence of ancient WGD signatures. “In conjunction with a machine-learning classifier, this approach can quickly assess the likelihood that transcriptomic and genomic data bear WGD signatures. On independently-generated synthetic data and real plant transcriptomic data, SLEDGE is capable of correctly identifying ancient WGD in 93-100% of samples.
      原文链接:
    • NETL
    • NSTL