利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

1010 records (took 0.018 seconds)

    CONTROL AND TRAINING OF ROBOTS USING LARGE LANGUAGE MODELS
    1.
    发明公开
    CONTROL AND TRAINING OF ROBOTS USING LARGE LANGUAGE MODELS 审中-公开

    公开(公告)号：US20240351218A1

    公开(公告)日：2024-10-24

    申请号：US18302596

    申请日：2023-04-18

    Applicant: COLLABORATIVE ROBOTICS

    Inventor： Brandon Porter ,  Divyansh Garg ,  Nicholas Corso

    IPC: B25J13/00 ,  B25J9/16 ,  B25J11/00 ,  G06F40/40

    CPC classification number: B25J13/003 ,  B25J9/161 ,  B25J9/163 ,  B25J11/0005 ,  G06F40/40

    Abstract: A method may include sending a query to one of a cobot or an LLM, where the query may be formed to trigger the cobot to perform a target objective, and where the LLM may be constrained to respond to requests to cause the cobot to perform a given objective with a set of human-readable discrete tasks to accomplish the given objective. The method may also include receiving a target set of human-readable discrete tasks from the LLM, where the target set of human-readable discrete tasks may correspond to target computer-readable code that is configured to cause the cobot to perform the target objective. The method may additionally include auditing the target set of human-readable discrete tasks, and, based on the target set of human-readable discrete tasks passing the audit, authorizing the cobot to implement the target computer-readable code to perform the target objective.

    TRAINED MODEL GENERATION METHOD, TRAINED MODEL GENERATION DEVICE, TRAINED MODEL, AND HOLDING MODE INFERENCE DEVICE
    2.
    发明公开
    TRAINED MODEL GENERATION METHOD, TRAINED MODEL GENERATION DEVICE, TRAINED MODEL, AND HOLDING MODE INFERENCE DEVICE 审中-公开

    公开(公告)号：US20240351198A1

    公开(公告)日：2024-10-24

    申请号：US18686363

    申请日：2022-08-26

    Applicant: KYOCERA Corporation

    Inventor： Minami ASATANI

    IPC: B25J9/16

    CPC classification number: B25J9/163 ,  B25J9/161 ,  B25J9/1612

    Abstract: A trained model includes a class inference model, a first holding mode inference model, and a second holding mode inference model. The class inference model is configured to infer, based on an inference image of a holding target object, a classification result obtained by classifying the holding target object into a predetermined holding category. The first holding mode inference model is configured to infer, based on the classification result and the inference image, a first holding mode for the holding target object. The second holding mode inference model is configured to infer, based on the first holding mode and the inference image, a second holding mode for the holding target object. A trained model generation method includes generating a trained model by performing learning using learning data including a learning image of a learning target object corresponding to a holding target object.

    Computerized engineering tool and methodology to develop neural skills for a robotics system
    3.
    发明授权
    Computerized engineering tool and methodology to develop neural skills for a robotics system 有权

    公开(公告)号：US12115680B2

    公开(公告)日：2024-10-15

    申请号：US17775997

    申请日：2019-12-03

    Applicant: Siemens Aktiengesellschaft

    Inventor： Arquimedes Martinez Canedo

    IPC: B25J9/16 ,  G05B13/02

    CPC classification number: B25J9/1671 ,  B25J9/161 ,  G05B2219/39001 ,  G05B2219/39271

    Abstract: Computerized engineering tool and methodology to develop neural skills for computerized autonomous systems, such as a robotics system (50), are provided. A disclosed computerized engineering tool (10) may involve an integrated arrangement of respective modular functionalities arranged in a closed loop, such as may include a physics engine (14), a neural data editor (16), an experiment editor (18), a neural skills editor (20), and a machine learning environment (22). Disclosed embodiments are conducive to cost-effectively simplifying development efforts involving neural skills, such as by reducing the time involved to develop the neural skills involved in any given robotics system and by reducing the level of expertise involved to develop neural skills.

    ROBOT
    4.
    发明公开
    ROBOT 审中-公开

    公开(公告)号：US20240326241A1

    公开(公告)日：2024-10-03

    申请号：US18269588

    申请日：2021-05-27

    Applicant: QKM TECHNOLOGY (DONG GUAN) CO., LTD

    Inventor： Jinbo SHI ,  Hongmiao YU ,  Hong LIU ,  Qi SHA ,  Chunhua YU ,  Lihui CHEN ,  Hong WANG

    IPC: B25J9/16 ,  B25J18/00 ,  B25J19/00

    CPC classification number: B25J9/161 ,  B25J18/00 ,  B25J19/0054

    Abstract: Provided is a robot. The robot includes a base (1), a mechanical arm (2), and a driver controller integrated board (3). The mechanical arm (2) is movably mounted on the base (1). The driver controller integrated board (3) is disposed on the base (1), is configured to control the mechanical arm (2) to move, and includes a control module (31), a drive module (32), and a substrate (33). The control module (31) and the drive module (32) are disposed on the substrate (33), and the control module (31) is electrically connected to the drive module (32).

    APPARATUS AND METHOD
    9.
    发明公开
    APPARATUS AND METHOD 审中-公开

    公开(公告)号：US20240300091A1

    公开(公告)日：2024-09-12

    申请号：US18592797

    申请日：2024-03-01

    Applicant: Sony Interactive Entertainment Inc.

    Inventor： Paul Terence Mulligan

    IPC: B25J9/16 ,  B25J9/00 ,  B25J19/02

    CPC classification number: B25J9/161 ,  B25J9/0003 ,  B25J19/023

    Abstract: An apparatus includes: a robotic device comprising a plurality of interfaces to allow interaction with a user, the interfaces comprising one or more input interfaces to detect input to the robotic device by the user and one or more output interfaces to perform output actions, and action generating circuitry to generate output actions to be executed by the one or more output interfaces in response to action parameter data; a portable device comprising circuitry to provide a simulated interface to simulate at least a subset of the plurality of interfaces of the robotic device; and behaviour processing circuitry to generate variations of the action parameter data in response to user interaction with the plurality of interfaces of the robotic device and in response to user interaction with the simulated interface of the portable device.

Patent Agency Ranking