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

    Research from Changchun Normal University Yields New Findings on Robotics (A Syn chronous Localization Method for Multiple Mobile Robots Based on Visual SLAM Alg orithm in the Context of the Internet of Things)

    83-84页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Research findings on robotics are discussed in a new report. According to news reporting originating from Changchun Normal Univer sity by NewsRx correspondents, research stated, “Aiming at the problem that trad itional methods cannot meet the problem of synchronous positioning of multi-mobi le robots in different motion states, a synchronous positioning method of multi- mobile robots based on visual simultaneous localization and mapping (SLAM) algor ithm is proposed.” The news journalists obtained a quote from the research from Changchun Normal Un iversity: “Analyze the general model of SLAM problem, realize visual SLAM featur e detection through scale invariant feature transform algorithm, and match image features based on active vision. A multi-mobile robot motion state estimation m odel is constructed, an octree model is used to construct a multi-robot synchron ous localization map, and the camera pose tracking is realized by using the orie nted fast accelerated segment test and rotated binary robust independent element ary features points that are not in the target bounding box.”

    New Findings from Purdue University in the Area of Machine Learning Published (F erroelectric capacitors and field-effect transistors as in-memory computing elem ents for machine learning workloads)

    84-85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 new report. According to news reporting out of Purdue Univ ersity by NewsRx editors, research stated, “This study discusses the feasibility of Ferroelectric Capacitors (FeCaps) and Ferroelectric Field-Effect Transistors (FeFETs) as In-Memory Computing (IMC) elements to accelerate machine learning ( ML) workloads.” Funders for this research include Semiconductor Research Corporation.

    University of Milano Bicocca Reports Findings in Machine Learning (Vibrational s pectroscopy coupled with machine learning sheds light on the cellular effects in duced by rationally designed TLR4 agonists)

    85-85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 Machine Learning is th e subject of a report. According to news originating from Milano, Italy, by News Rx correspondents, research stated, “In this work, we present the potential of F ourier transform infrared (FTIR) microspectroscopy to compare on whole cells, in an unbiased and untargeted way, the capacity of bacterial lipopolysaccharide (L PS) and two rationally designed molecules (FP20 and FP20Rha) to activate molecul ar circuits of innate immunity. These compounds are important drug hits in the d evelopment of vaccine adjuvants and tumor immunotherapeutics.” Our news journalists obtained a quote from the research from the University of M ilano Bicocca, “The biological assays indicated that FP20Rha was more potent tha n FP20 in inducing cytokine production in cells and in stimulating IgG antibody production post-vaccination in mice. Accordingly, the overall significant IR spe ctral changes induced by the treatment with LPS and FP20Rha were similar, lipids and glycans signals being the most diagnostic, while the effect of the less pot ent molecule FP20 on cells resulted to be closer to control untreated cells.”

    New Findings from Nanjing University of Information Science and Technology (NUIS T) Update Understanding of Robotics (Dsnet: Double Strand Robotic Grasp Detectio n Network Based On Cross Attention)

    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 reporting out of Nanjing, People’s Republic of China, by NewsRx editors, research stated, “In this letter, we propose a Double Strand robotic grasp detection Network (DSNet), that combines a transformer bran ch and a U-Net branch within an encoder-decoder structure. The DSNet is designed to reconcile differences between these two approaches and provide access to bot h local and global resources.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC).

    'Methods And Apparatus For Machine Learning System For Edge Computer Vision And Active Reality' in Patent Application Approval Process (USPTO 20240135319)

    87-90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 FRIEDL, Jonah (Kirkland, WA, US); GRESCHLER, David (Kirkland, WA, US); VOGEL, Jo n (Kirkland, WA, US), filed on January 4, 2024, was made available online on Apr il 25, 2024, according to news reporting originating from Washington, D.C., by N ewsRx correspondents. This patent application is assigned to NOMAD Go Inc. (Kirkland, Washington, Unit ed States). The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “The management of an inventory relies heavily o n human-based calculations and actions. Some known systems allow humans to effic iently manage their inventory of items at massive scales using cameras placed in warehouses or retail spaces. Furthermore, some known systems require strict org anization and single appearances per item without distinguishing the packaging o f items sharing the same stock keeping unit (SKU) or the various ways items are stored. Moreover, some known systems use fixed cameras with computer vision and can require multiple cameras that are limited to specific areas and views with m ultiple blind spots. Additionally, such known technologies often rely on manual data input, which can be tedious, time consuming, and lead to inaccuracies.

    Researchers Submit Patent Application, 'System And Method For Estimating The Pos e Of A Localizing Apparatus Using Reflective Landmarks And Other Features', for Approval (USPTO 20240135703)

    90-95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 HEHN, Markus (Zurich, CH); WIDMER, Lino (Zurich, CH), filed on December 13, 2021, was made available onlin e on April 25, 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: “Indoor navigation of robots, for example drones, is an imp ortant problem, e.g., in the field of automatic warehousing. Such robots are loc alizing agents. To facilitate indoor navigation, the robot, e.g., the drone, nee ds to know its current position with respect to its environment. Contrary to out door environments in which GNSS (Global Navigation Satellite Systems) can be emp loyed, providing a high localization accuracy, GNSS in indoor environments is of ten not reliable due to signal attenuation and multi-path effects. Existing RF l ocalization technologies for indoor and outdoor spaces also struggle with signal attenuation and multi-path effects limiting the usability in complex environmen ts, for instance, in the presence of a significant amount of metal.

    Patent Issued for Obstacle recognition method for autonomous robots (USPTO 11966 229)

    96-99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 Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Eb rahimi Afrouzi, Ali (Henderson, NV, US), Mehrnia, Soroush (Helsingborg, SE), fil ed on May 22, 2023, was published online on April 23, 2024. The assignee for this patent, patent number 11966229, is AI Incorporated (Toront o, Canada). Reporters obtained the following quote from the background information supplied by the inventors: “Autonomous robots are being used with increasing frequency to carry out routine tasks such as vacuuming, mopping, cutting grass, polishing fl oors, etc. During operation, a robot may encounter objects that may act as an ob struction to the operation of the robot. For example, objects such as cords, wir es, clothing, and toys may become stuck in the wheels or other moving parts of t he robot as it drives close to or over the objects. Interaction with such object s may cause the robot to malfunction or prevent the robot from completing a task . A method for avoiding entanglement with objects may be useful.”

    Researchers Submit Patent Application, 'Systems and Methods for Producing a Prod uct', for Approval (USPTO 20240135324)

    99-103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 CLARK, Teressa (Raritan, N J, US); FITZGERALD, Michael (Oakhurst, NJ, US); HAGHSHENAS, Keeyan (Jersey City, NJ, US); HU, Zhichao (Piscataway, NJ, US); JOYCE, Jason (Stewartsville, NJ, US) ; PAPPAS, Iraklis (Pennsauken, NJ, US); QIAN-PENA, Junfang Katy (Piscataway, NJ, US); WIREMAN, Evan (Allentown, NJ, US); WOLF, John (New Brunswick, NJ, US); ZEN G, Lingfei (Short Hills, NJ, US), filed on February 17, 2022, was made available online on April 25, 2024. The patent’s assignee is Colgate-Palmolive (New York, New York, United States). News editors obtained the following quote from the background information suppli ed by the inventors: “Many attributes relate to a product. For example, products are formed of compositions, such as chemical compositions. Chemical composition s typically include many different ingredients. Each of the ingredients has a pa rticular value, such as a chemoinformatic value, associated with the ingredient. Further, one or more properties (e.g., a pH, a consumer perception) of the chem ical composition may have unique values, for example, based on the ingredients w ithin the composition. The value of the property of the chemical composition may change due to the interaction of the ingredients within the composition. Produc ts may also have attributes in addition to its ingredients, such as sensory attr ibutes of the product and/or packaging of the product. Sensory attributes may in clude consistencies of the product, text of the packaging of the product, and co lors of the product and packaging of the product. Such sensory attributes may be influential in the purchase of the product, and, therefore, may result in the m arket value of the product.

    Patent Issued for Systems and methods for object processing using a vacuum gripp er that provides object retention by shroud inversion (USPTO 11964386)

    104-107页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Alexandria, Virginia, NewsRx jour nalists report that a patent by the inventors Geyer, Christopher (Arlington, MA, US), Mason, Matthew T. (Pittsburgh, PA, US), Nelson, Gabriel (Wilmington, MA, U S), Rose, Aidan (Waban, MA, US), Yap, Jason (Newton, MA, US), filed on July 15, 2021, was published online on April 23, 2024. The patent’s assignee for patent number 11964386 is Berkshire Grey Operating Com pany Inc. (Bedford, Massachusetts, United States). News editors obtained the following quote from the background information suppli ed by the inventors: “The invention generally relates to programmable motion sys tems and relates in particular to end effectors for programmable motion devices (i.e., robotic systems) for use in object processing such as object sortation an d object distribution.

    Researchers Submit Patent Application, 'Interactive Concept Editing In Computer- Human Interactive Learning', for Approval (USPTO 20240135098)

    107-110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 AMERSHI, Saleema A. (Seatt le, WA, US); BOTTOU, Leon (Kirkland, WA, US); GRANGIER, David G. (Kirkland, WA, US); SIMARD, Patrice Y. (Bellevue, WA, US), filed on December 1, 2023, was made available online on April 25, 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: “A collection of data that is extremely large can be diffic ult to search and/or analyze. For example, in the case of the Web, a large fract ion of the data is unstructured and value is locked in the data itself. It is no t enough to store the web page of a service provider. For this information to be useful, it needs to be understood. A string of digits could be a model number, a bank account, or a phone number depending on context. For instance, in the con text of a ski product, the string “Length: 170,175,180 cm” refers to 3 different ski lengths, not a ski length of 1700 kilometers. An incorrect interpretation o f the data may result in useless information.