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 'Data Augmentation For Model Training In Autonomous Sy stems And Applications' Published Online (USPTO 20240312123)

    210-215页
    查看更多>>摘要：According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Anwar, Malik Aqeel (Atlanta, GA, US); Choe, Tae Eun (Belmont, CA, US); Fid ler, Sanja (Toronto, CA); Park, Minwoo (Santa Clara, CA, US); Wang, Zian (Toront o, CA), filed on February 29, 2024, was made available online on September 19, 2 024. The assignee for this patent application is NVIDIA Corporation (Santa Clara, Cal ifornia, United States). Reporters obtained the following quote from the background information supplied by the inventors: "Many partial (SAE L2), conditional (L3), and high (L4) drivin g automation systems include perception systems (sometimes referred to as percep tion modules) that are trained using datasets containing thousands to millions o f images. For example, to develop a vision-based perception system, individual i mages are collected while a vehicle is driven in various environments and under various conditions. These images are then inspected by humans and annotated with tags representing objects or agents found in the image. The resulting images an d corresponding tags are then used to update parameters of trained machine learn ing models implemented by the perception systems to classify later-encountered o bjects or agents.
      原文链接:
    • NETL
    • NSTL

    'Systems And Methods For Autonomous Road Sealing' in Patent Application Approval Process (USPTO 20240308080)

    215-217页
    查看更多>>摘要：A patent application by the inventors Brown, Robertson (Amherstburg, CA); Denzinger, Peter (Lasalle, CA); Pineda, Bran don (Windsor, CA); Scarlett, Dean (Lakeshore, CA); Sirizzotti, Michael (Windsor, CA), filed on March 15, 2023, was made available online on September 19, 2024, according to news reporting originating from Washington, D.C., by NewsRx corresp ondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: " "The present invention relates to systems and methods for autonomously identifyi ng and filling cracks in pavement. More particularly, the invention relates to s ystems and methods for identifying cracks in the pavement and for programming a robot to autonomously fill the cracks. "Current methods for identifying and filling cracks in pavement are performed ma nually. This can be a time-consuming process, which involve inherent safety risk s for workers. Moreover, crack filling needs to be performed during the day when there is enough daylight for the workers to see the pavement."
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Systems, methods and apparatuses for calibrating sensors mount ed on a device (USPTO 12092771)

    217-220页
    查看更多>>摘要：According to news reporting originatin g from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors At las, Matt (San Diego, CA, US), Couture, Simon (San Diego, CA, US), Halpern, Avi (San Diego, CA, US), Hrabe, Thomas (San Diego, CA, US), filed on March 30, 2021, was published online on September 17, 2024. The assignee for this patent, patent number 12092771, is Brain Corporation (San Diego, California, United States). Reporters obtained the following quote from the background information supplied by the inventors: "Technological Field "The present application relates generally to robotics, and more specifically to systems and methods for calibrating robotic sensors.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Microservices anomaly detection (USPTO 12095797)

    221-224页
    查看更多>>摘要：From Alexandria, Virginia, NewsRx jour nalists report that a patent by the inventors Badrinathan, Hariharan (Tamilnadu, IN), Behl, Sunny (Irving, TX, US), filed on August 28, 2023, was published onli ne on September 17, 2024. The patent's assignee for patent number 12095797 is Citibank N.A. (New York, New York, United States). News editors obtained the following quote from the background information suppli ed by the inventors: "In a computer networked environment, an instrumentation se rvice can evaluate various measured metrics using anomaly detection techniques f or anomalies in individual nodes of the network or communications among nodes. A nomaly detection techniques may lead to over-counting (e.g., false positives) or undercounting (e.g., false negatives) of anomalies. Over-counting may result i n the service making too many detections and sending too many notices of anomali es to a system administrator. The system administrator may be overwhelmed with a lerts regarding false positive anomalies and may be unable to check each, thereb y nullifying the efforts of the service. Conversely, under-counting of anomalies may result in issues in the networked environment remaining unchecked. Either r esult may lead to an increase in issues as ignored anomalies exacerbate any rema ining problems in the environment."
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Obstacle Recognition Method For Autonomous Robots' Pu blished Online (USPTO 20240310851)

    224-227页
    查看更多>>摘要：According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Ebrahimi Afrouzi, Ali (Henderson, NV, US); Ebrahimi Afrouzi, Amin (Encinit as, CA, US); Fitzgerald, Andrew Francis (Penfield, NY, US); Highfill, Brian (Cas tro Valley, CA, US); Robinson, Lukas (York, CA), filed on January 16, 2024, was made available online on September 19, 2024. The assignee for this patent application is Al Incorporated (Toronto, Canada). Reporters obtained the following quote from the background information supplied by the inventors: "Autonomous or semi-autonomous robotic devices are increasingl y used within consumer homes and commercial establishments. Such robotic devices may include a drone, a robotic vacuum cleaner, a robotic lawn mower, a robotic mop, or other robotic devices. To operate autonomously or with minimal (or less than fully manual) input and/or external control within an environment, methods such as mapping, localization, object recognition, and path planning methods, am ong others, are required such that robotic devices may autonomously create a map of the environment, subsequently use the map for navigation, and devise intelli gent path and task plans for efficient navigation and task completion."
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Adaptive Region-Based Object Sampling For Object Dete ction' Published Online (USPTO 20240312188)

    227-231页
    查看更多>>摘要：According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors NARAYANAN, Venkatraman (Farmington Hills, MI, US); RAVI KUMAR, Varun (San Diego, CA, US); YOGAMANI, Senthil Kumar (Headford, IE), filed on March 17, 2023, was made available online on September 19, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: "A light detection and ranging (LIDAR) system scans (e.g., acr oss azimuth and elevation) an environment using one or more lasers and calculate s distances between the LIDAR system and objects in the environment based on las er light reflected by the objects (e.g., using a time-of-flight (TOF) or indirec t time-of-flight technique). Data from a LIDAR system captured at a given time c an be referred to herein as a "LIDAR capture." A LIDAR capture can include spati al data including three-dimensional coordinates (e.g., a point cloud) representi ng objects in the environment. The three-dimensional coordinates can be derived from the calculated distances between the LIDAR system and the objects at a numb er of respective azimuth and elevation angles.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Occlusion-aware prediction of human behavior (USPTO 12094252)

    231-234页
    查看更多>>摘要：Humanising Autonomy Limited (London, U nited Kingdom) has been issued patent number 12094252, according to news reporti ng originating out of Alexandria, Virginia, by NewsRx editors. The patent's inventors are Bose, Raunaq (London, GB), El Youssoufi, Wassim (Lond on, GB), Everard, James Over (Manningtree, GB), Nooteboom, Leslie Cees (London, GB), Noy, Dominic (London, GB), Pindeus, Maya Audrey Lara (London, GB), Pradeep, Yazhini Chitra (London, GB). This patent was filed on December 13, 2021 and was published online on September 17, 2024. From the background information supplied by the inventors, news correspondents o btained the following quote: "When making predictions about human behavior with computer vision-based technology, a frequent issue is that a human being in vide o frames may be occluded, as humans are often temporarily hidden from cameras be hind other objects or other people in the environment. Occlusion poses challenge s in understanding what behavior a person is likely to exhibit in the near futur e, as key points used to drive machine learning analysis of behavior are not vis ible in images input into models. Yet further, where a person is fully occluded, challenges are posed in determining whether someone is the same person when the y re-appear from the occlusion, as tracking may rely on the occluded key points. When using existing systems, occlusions often cause improper assumptions, which lead to improper predictions. For example, if a person is behind a wall and the ir legs are occluded, existing systems might assume that the person is not movin g while they actually are or assume that the person is a different person when t he occlusion is removed."
      原文链接:
    • NETL
    • NSTL

    'Nut Plate Grippers And Related Methods' in Patent Application Approval Process (USPTO 20240308089)

    234-237页
    查看更多>>摘要：A patent application by the inventor C ochrane, Jason (Melbourne, AU), filed on March 13, 2023, was made available onli ne on September 19, 2024, according to news reporting originating from Washingto n, 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 informa tion supplied by the inventors: "Nut plates may be utilized within a structure t o secure two components of the structure to one another. Nut plates historically have been manually installed while held in place during an assembly process in which the two components are secured to one another. While effective, this proce ss is labor-intensive. The overall shape of the nut plates makes it difficult to reliably and reproducibly position the nut plates at a desired location during the assembly process. Thus, there exists a need for nut plate grippers, for end effectors that include the nut plate grippers, for robots that include the end e ffectors, for installation systems that include the robots, and/or for related m ethods."
      原文链接:
    • NETL
    • NSTL

    'System and Method for Modification, Personalization and Customizable Filtering of Search Results and Search Result Ranking in an Internet-Based Search Engine' in Patent Application Approval Process (USPTO 20240311435)

    237-242页
    查看更多>>摘要：A patent application by the inventor B alasia, Brian (Royal Oak, MI, US), filed on May 24, 2024, was made available onl ine on September 19, 2024, according to news reporting originating from Washingt on, 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 informa tion supplied by the inventors: "The current state of the art in online search e ngines, generally involving word-based or phrase-based searching, is reasonably advanced in its ability to retrieve documents (e.g., web pages, images, files, e tc.) that are responsive to the terms of a query, typically searched and retriev ed using keywords contained in the query. While such search engines typically re turn results that accurately correspond to the search terms (keywords) of the qu ery, the search results may not reflect the user's underlying interests and goal s.
      原文链接:
    • NETL
    • NSTL

    'Heart on My Sleeve': From Memorization to Duty

    242-243页
    查看更多>>摘要：According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from os f.io: "Can a machine learning model infringe on a copyright-do machine learning models store protected content? This work-in-progress law review Article focuses on em pirical data developed, in part, to answer that question: yes. "A set of unconditional image generators, diffusion models (n = 14), are trained on small slices of a dataset consisting of celebrities' faces. The synthetic da ta output from these generators is then compared to training data using a variet y of similarity metrics. "As the empirical data shows, the question is not can models contain copyrighted works, but do models contain copyright works.
      原文链接:
    • NETL
    • NSTL