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

    Patent Application Titled 'Automated Robotic Replenishment System' Published Online (USPTO 20240043212)

    139-143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 Challapalli, Naveen (Cambridge, MA, US); Cox, Gregory Patrick (Sleepy Hollow, NY, US); Douglas, Matthew Robert (Orlando, FL, US); Gerli, Paolo (Westborough, MA, US); Jarvis, Daniel (Holliston, MA, US); Kalra, Amit (Acton, MA, US); Lam, Brandon (Rockland, MA, US); Tewari, Ruchi (Hopkinton, MA, US); Variar, Nikhil (Needham, MA, US), filed on August 4, 2022, was made available online on February 8, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “This application relates to warehouse fulfillment systems. For example, this application relates to an automated system for replenishing storage units.
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Safe Motion Planning For Machinery Operation' Published Online (USPTO 20240042616)

    144-148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 Denenberg, Scott (Newton, MA, US); Moel, Alberto (Cambridge, MA, US); Sobalvarro, Patrick (Harvard, MA, US); VU, Clara (Cambridge, MA, US), filed on October 3, 2023, was made available online on February 8, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “Industrial machinery is often dangerous to humans. Some machinery is dangerous unless it is completely shut down, while other machinery may have a variety of operating states, some of which are hazardous and some of which are not. In some cases, the degree of hazard may depend on the location or distance of the human with respect to the machinery. As a result, many “guarding” approaches have been developed to separate humans and machines and to prevent machinery from causing harm to humans. One very simple and common type of guarding is simply a cage that surrounds the machinery, configured such that opening the door of the cage causes an electrical circuit to place the machinery in a safe state. If the door is placed sufficiently far from the machinery to ensure that the human can’t reach it before it shuts down, this ensures that humans can never approach the machinery while it is operating. Of course, this prevents all interaction between human and machine, and severely constrains use of the workspace.
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, 'Method And System For Training Of Artificial Intelligence And Machine Learning Models', for Approval (USPTO 20240046161)

    148-153页
    查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors BUFORD, John (Somerset, NJ, US); PHAM, Baoquoc (Richmond, TX, US), filed on August 5, 2022, was made available online on February 8, 2024. The patent’s assignee is JPMorgan Chase Bank N.A. (New York, New York, United States). News editors obtained the following quote from the background information supplied by the inventors: “ “This technology relates to methods and systems for training of artificial intelligence (AI) and machine learning (ML) models in order to ensure efficiency and high quality performance. “A machine learning (ML) model life cycle (MLMLC) is a complex interdisciplinary business process. Conventionally, the MLMLC is often used for developing information technology data-analysis applications in which no closed-form algorithmic solution is known but for which sufficient historical or reference data is available, and in which a solution may be operationalized against related data.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Using artificial intelligence to select and chain models for robotic process automation (USPTO 11893371)

    153-155页
    查看更多>>摘要：UiPath Inc. (New York, New York, United States) has been issued patent number 11893371, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Singh, Prabhdeep (Bellevue, WA, US). This patent was filed on March 12, 2021 and was published online on February 6, 2024. From the background information supplied by the inventors, news correspondents obtained the following quote: “Typically, a single RPA workflow is built and deployed in a single robot to perform certain tasks under certain conditions. For instance, a robot may be built and deployed that looks for certain visual components in an image, pulls certain information from an invoice, etc. However, without continuously building new rules based on changes to the current problem or understanding which activities are working properly, new changes may not be recognized, or the robot may fail altogether. Furthermore, a single robot may not be optimal for all scenarios. Accordingly, an improved approach may be beneficial.” Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “Certain embodiments of the present invention may provide solutions to the problems and needs in the art that have not yet been fully identified, appreciated, or solved by current RPA technologies. For example, some embodiments of the present invention pertain to using AI to select and/or chain models for RPA.
      原文链接:
    • NETL
    • NSTL

    'Robot And Automated Guided Vehicle Combination For Aluminum Furnace Operations' in Patent Application Approval Process (USPTO 20240042618)

    156-160页
    查看更多>>摘要：patent application by the inventors COTE, Patrice (Jonquiere, CA); DESMEULES, Jean-Francois (Jonquiere, QC); NERON, Jean-Benoit (Jonquiere, CA), filed on October 23, 2023, was made available online on February 8, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background information supplied by the inventors: “ “(a) Field “The subject matter disclosed generally relates to systems and methods for operating furnaces. More particularly, the subject matter disclosed relates to systems and methods for operating maintenance operations in relation of furnaces in a foundry.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Adjustment of card configurations for flight interruptions (USPTO 11893633)

    160-163页
    查看更多>>摘要：Capital One Services LLC (McLean, Virginia, United States) has been issued patent number 11893633, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Guo, Lisa (Herndon, VA, US), Kwok, Jennifer (New York, NY, US), Lin, Alexander (Arlington, VA, US), Miller, Daniel (Astoria, NY, US), Noah, Cameron (Bethesda, MD, US), Vadrevu, Vyjayanthi (Pflugerville, TX, US), Zhu, Xiaoguang (Great Neck, NY, US). This patent was filed on August 17, 2021 and was published online on February 6, 2024. From the background information supplied by the inventors, news correspondents obtained the following quote: “Users may use payment cards to conduct various types of transactions, and may use the payment cards during travel. When a user experiences a flight interruption, the user may potentially conduct additional transactions via the user’s payment card(s) during the flight interruption, such as to reserve a hotel room, to reserve another flight, to purchase a meal at the airport, and/or the like. If configurations of the payment card(s) do not allow one or more of the transactions to be conducted, it may contribute to causing inconvenience and/or frustration to the user during the flight interruption.”
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Systems And Methods For Artificial- Intelligence Model Training Using Unsupervised Domain Adaptation With Multi-Source Meta-Distillation' Published Online (USPTO 20240046107)

    163-167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 CHI, Zhixiang (Markham, CA); GU, Li (Markham, CA); TANG, Jin (Markham, CA); WANG, Yang (Markham, CA); YU, Yuanhao (Markham, CA); ZHONG, Tao (Markham, CA), filed on October 14, 2022, was made available online on February 8, 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) has been used in many areas. Generally, AI involves the use of a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive an environment, obtain knowledge, and use the knowledge to obtain a best result. “AI methods, machines, and systems analyze a variety of data for perception, inference, and decision making. Examples of areas for AI include robots, natural language processing, computer vision, decision making and inference, man-machine interaction, recommendation and searching, basic theories of AI, and the like.
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, 'Method for Dividing Robot Area Based on Boundaries, Chip and Robot', for Approval (USPTO 20240045433)

    167-171页
    查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors LAI, Qinwei (Zhuhai, Guangdong, CN); WANG, Yuelin (Zhuhai, Guangdong, CN); XU, Yimian (Zhuhai, Guangdong, CN), filed on November 24, 2020, was made available online on February 8, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “Existing cleaning robots plan maps and navigate by means of inertial navigation, light detection and ranging or cameras. When using a cleaning robot, a user can see division of cleaning areas from a mobile device in real time. However, the cleaning areas are randomly divided into a plurality of areas only according to their coordinate information, instead of room units. Area division is mainly used for coverage planning, but at present, it’s still impossible to mark the information of an uncleaned area in advance on a map constructed in real time by means of a visual technology, resulting in ineffective division of rooms. “In the prior art, in the patent for invention with the application number of 2015100760659 filed by LG Electronics Inc. in China on Feb. 12, 2015, a pure-image visual means is used to identify positions of doors and shapes of door frames, so as to distinguish rooms. However, the requirement for positions where a robot acquires images is relatively strict, and the robot is required to acquire images repeatedly at multiple angles, such that the predetermined accuracy is not easy to achieve during identifying the positions of the doors.”
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, 'Systems And Methods For Detecting User Created Circular Shaped Indications Using Machine Learning Models', for Approval (USPTO 20240046676)

    171-176页
    查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventor Chepel, Maksim (Hartford, CT, US), filed on August 2, 2022, was made available online on February 8, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “Traditionally, text recognition algorithms such as optical character recognition (OCR) algorithms are used to convert images of typed, handwritten, or printed text into machine-encoded text. For instance, a document such as a scanned document, a photo, an image, or any other type of file may include text. The OCR algorithms may be used to convert the document into machine-encoded text that is usable in a plurality of different applications for an enterprise organization. For instance, an enterprise organization may use text recognition algorithms to extract content from numerous different documents fairly quickly. In certain documents, a person may provide user selections such as marking a checkbox or other features to indicate their selection. For marking a checkbox or circling in an oval, standard algorithms may be used to detect the user selection. However, in some instances, the person may seek to select a design or certain text (e.g., “F” or “M” for gender) within a document. For instance, the person may circle an option (e.g., “M”), but these circles may vary between user selections (e.g., a first circular selection may be different from a second circular selection, even in the same document). These user created indications that are circling text or designs may be difficult for a system using standard algorithms to process and assess the user’s selections as they are not pre-defined beforehand. Accordingly, there remains a technical need to be able to detect user created indications.”
      原文链接:
    • NETL
    • NSTL

    AAclust: k-optimized clustering for selecting redundancy-reduced sets of amino acid scales

    176-177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: “Summary: Amino acid scales are crucial for sequence-based protein prediction tasks, yet no gold standard scale set or simple scale selection methods exist. “We developed AAclust, a wrapper for clustering models that require a pre-defined number of clusters k, such as k-means. AAclust obtains redundancy-reduced scale sets by clustering and selecting one representative scale per cluster, where k can either be optimized by AAclust or defined by the user. The utility of AAclust scale selections was assessed by applying machine learning models to 24 protein benchmark datasets. “We found that top-performing scale sets were different for each benchmark dataset and significantly outperformed scale sets used in previous studies. Notably, model performance showed a strong positive correlation with the scale set size. AAclust enables a systematic optimization of scale-based feature engineering in machine learning applications. Availability and implementation: The AAclust algorithm is part of AAanalysis, a Python-based framework for interpretable sequence-based protein prediction, which will be made freely accessible in a forthcoming publication. Supplementary information: Further details on methods and results are provided in Supplementary Material.”
      原文链接:
    • NETL
    • NSTL