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 Issued for Surface normals for pixel-aligned object (USPTO 12094066)

    204-207页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Snap Inc. (Santa Monica, California, U nited States) has been issued patent number 12094066, according to news reportin g originating out of Alexandria, Virginia, by NewsRx editors. The patent's inventors are Aitbayev, Madiyar (London, GB), Fulkerson, Brian (Lon don, GB), Guler, Riza Alp (London, GB), Papandreou, Georgios (London, GB), Tam, Himmy (London, GB). This patent was filed on June 16, 2022 and was published online on September 17, 2024. From the background information supplied by the inventors, news correspondents o btained the following quote: "Augmented Reality (AR) is a modification of a virt ual environment. For example, in Virtual Reality (VR), a user is completely imme rsed in a virtual world, whereas in AR, the user is immersed in a world where vi rtual objects are combined or superimposed on the real world. An AR system aims to generate and present virtual objects that interact realistically with a real- world environment and with each other. Examples of AR applications can include s ingle or multiple player video games, instant messaging systems, and the like."

    Patent Issued for Robot-assisted processing of a surface using a robot (USPTO 12 093050)

    207-209页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-RoTrade Asset Management GmbH (Leondin g, Austria) has been issued patent number 12093050, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent's inventors are Artes, Harold (Linz, AT), Conti, David (Linz, AT), Fr eudenthaler, Christoph (Linz, AT), Mascher, Erwin (Linz, AT), Vogel, Reinhard (L inz, AT). This patent was filed on October 28, 2021 and was published online on September 17, 2024. From the background information supplied by the inventors, news correspondents o btained the following quote: "In recent years, autonomous mobile robots are bein g increasingly employed, for example, to clean floor surfaces or to mow a lawn. In both cases it is crucial that the given surface be entirely processed by a su rface processing device arranged on the robot such as, for example, a brush. Sim ple devices can do without the generation and use of a map of the area of robot deployment by, for example, randomly moving over the area to be cleaned. More co mplex robots use a map of the area of robot deployment that they generate themse lves or that is provided to them in electronic form. This system makes it possib le to record the already processed surfaces.

    Patent Application Titled 'Systems and Methods for Generating Interior Designs U sing Artificial Intelligence' Published Online (USPTO 20240311533)

    209-214页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-According to news reporting originatin g from Washington, D.C., by NewsRx journalists, a patent application by the inve ntors Agrawal, Ankur (Chicago, IL, US); Arashanapalli, Shirish (Chicago, IL, US) ; Koppurapu, Vinod (Chicago, IL, US), filed on March 13, 2024, was made availabl e 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: "The furnishing industry confronts the challenge of laboriousl y designing rooms for various purposes, like hotels, student housing, short-term rentals and offices. Both designers and customers endure prolonged iterations s panning months. The traditional furniture purchasing process requires substantia l time, resources, and capital, leading to extended lead times that impede reven ue potential. In the US alone furniture accounts for 12.2 million tons (4.6% ) of household waste dumped in landfills every year impacting the environment. F urthermore, interior updates struggle to keep pace with evolving consumer expect ations and industry trends due to the high cost, lead time, and limited affordab ility of current furnishings, hindering businesses' ability to adapt swiftly."

    Patent Issued for Adaptable multifunction robotic hands (USPTO 12090637)

    214-216页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Viralint Pte Ltd. (Singapore, Singapor e) has been issued patent number 12090637, according to news reporting originati ng out of Alexandria, Virginia, by NewsRx editors. The patent's inventors are Srinivas, Kundapura Parameshwara (Singapore, SG), Won g, Soon Wei (Singapore, SG). This patent was filed on September 2, 2021 and was published online on September 17, 2024. From the background information supplied by the inventors, news correspondents o btained the following quote: "Some automated tasks, especially those in which th ere are interactions between delicate and sensitive objects, require the collabo rative work of multiple finger units in a Robotic hand equipped with end-effecto r grippers. With flexible degrees of movements and built-in features for cleanin g, pickup and placement of objects, Liquid dispensing, Gripping and rotating and sterilising features the Robotic hands are specially suited for operating in en vironments not suitable for deployment of humans for performing various tasks. M ost of the current disclosed art attempting such tasks require multiple stages o f manual inspection or human intervention and the use of multiple mechanical man ipulators to perform the task with a high possibility of errors being introduced during the process. Prior art limitations include dedicated manipulators mounte d on separate platforms, time consuming reconfiguration process before they are deployed in manufacturing or quality control process.

    Researchers Submit Patent Application, 'Reservoir Modeling And Well Placement Us ing Machine Learning', for Approval (USPTO 20240311530)

    217-221页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-From Washington, D.C., NewsRx journali sts report that a patent application by the inventors Mustapha, Hussein (Abu Dha bi, AE); Ramatullayev, Samat (Abu Dhabi, AE); Su, Shi (Abu Dhabi, AE); de Brito Dias, Daniel (Abingdon, GB), filed on February 7, 2022, was made available onlin e on September 19, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: "In conventional systems, several workflows include calibra ting model parameters to select a model that accurately represents data. For ins tance, history matching is a process of calibrating reservoir uncertainty parame ters with an objective of obtaining simulation production data as close as possi ble to historical data. The process is time-consuming and requires heavy computa tions, which pose a bottleneck for further steps in a reservoir modeling workflo w.

    'Passively Actuated Sensor System' in Patent Application Approval Process (USPTO 20240308825)

    221-225页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent application by the inventors Braun, Pat (Pittsburgh, PA, US); Heisel, Matt (Pittsburgh, PA, US); Richter, Eli jah (Glenshaw, PA, US); Seal, Jacob (Pittsburgh, PA, US); Stimmel, Thomas (Devon,PA, US); Thompson, Bruce (Pittsburgh, PA, US); Tylenda, Ben (Venetia, PA, US), filed on March 28, 2023, was made available online on September 19, 2024, accor ding to news reporting originating from Washington, D.C., by NewsRx corresponden ts. 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: "In autonomous mobile robots (AMRs), there is a need to be able to scan under the forks to detect objects during the pick and pl ace sequences. It is important for AMRs to have awareness of the environment dur ing travel and payload operations. Sensors may be obstructed by the AMR and/or payload and may be damaged by the forks when the forks are lowered to the floor."

    'System And Method For Controlling A Position Of An Articualted Robotic Arm' in Patent Application Approval Process (USPTO 20240308066)

    225-227页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent application by the inventors Bergman, Per (West Roxbury, MA, US); Blacker, Steven J. (Framingham, MA, US); El den, Robert (Cambridge, MA, US); Guerrera, Stephen (Holliston, MA, US); Klem, Er ic (Lexington, MA, US); Sokhanvar, Saeed (Belmont, MA, US), filed on May 29, 202 4, was made available online on September 19, 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 informa tion supplied by the inventors: "There are systems for the performance of medica l procedures in which a percutaneous device is inserted into a human patient wit h the guidance of an X-ray image using a mechanism held adjacent to the patient by a robotic arm and the mechanism is controlled from a remote cockpit which pro vides shielding to the operator of the system from the radiation generated in ob taining the X-ray image. The arm has typically been attached to the patient tabl e by a rail and removed from the rail and placed on the floor or placed in other storage between procedures."

    Researchers Submit Patent Application, 'Robot And Robot System', for Approval (U SPTO 20240308090)

    228-229页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-From Washington, D.C., NewsRx journali sts report that a patent application by the inventor MIYASAKA, Hidekatsu (Matsum oto-shi, JP), filed on March 15, 2024, was made available online on September 19,2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: " "The present disclosure relates to a robot and a robot system. "JP-A-11-123690 discloses a robot including a first arm and a second arm rotatab ly coupled to the first arm via a joint. The robot includes a stopper restrictin g an angle between the first arm and the second arm to a predetermined angle or more. The stopper includes a fixed-side stopper provided in the first arm and a movable-side stopper provided in the second arm. The movable-side stopper comes into contact with the fixed-side stopper, and thereby, the angle between the arm s is restricted to the predetermined angle or more. "In the robot disclosed in JP-A-11-123690, it is considered that the first arm a nd the second arm may be damaged due to an impact when the movable-side stopper comes into contact with the fixed-side stopper."

    Accurate non-invasive quantification of astaxanthin content using hyperspectral images and machine learning

    230-231页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from bi orxiv.org: "Commercial cultivation of the microalgae Haematococcus pluvialis to produce nat ural astaxanthin has gained significant traction due to the high antioxidant cap acity of this pigment and its application in foods, feed, cosmetics and nutraceu ticals. "However, monitoring of astaxanthin content in cultures remains challenging and relies on invasive, time consuming and expensive approaches. "In this study, we employed reflectance hyperspectral imaging (HSI) of H. pluvia lis suspensions within the visible spectrum, combined with a1-dimensional convo lutional neural network (CNN) to predict the astaxanthin content (ug mg-1) as qu antified by high-performance liquid chromatography (HPLC). This approach had low average prediction error (5.9%) across a gradient of astaxanthin contents and was only unreliable at very low contents (<0.6 micrograms mg-1).

    State-of-the-Art MPI Allreduce Implementations for Distributed Machine Learning: A Survey

    230-230页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from os f.io: "Efficient data communication is pivotal in distributed machine learning to mana ge the increased computational demands posed by large datasets and complex model s. "This survey explores the critical role of MPI Allreduce, a collective communica tion operation, in enhancing the scalability and performance of distributed mach ine learning. We examine traditional MPI libraries such as MPICH and Open MPI, which offer foundational support across diverse computing environments. Additiona lly, we delve into specialized implementations like NVIDIA's NCCL and Intel's on eCCL, designed to optimize performance on specific hardware platforms. Through a series of case studies, we demonstrate the impact of these optimized MPI Allred uce implementations on training times and model accuracy in real-world applicati ons, such as large-scale image classification and natural language processing.