利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

26 条记录 (耗时 0.014 秒)

    APPARATUS AND METHODS FOR SEMI-AUTONOMOUS CLEANING OF SURFACES
    2.
    发明申请
    APPARATUS AND METHODS FOR SEMI-AUTONOMOUS CLEANING OF SURFACES 审中-公开

    公开(公告)号：US20200329937A1

    公开(公告)日：2020-10-22

    申请号：US16859476

    申请日：2020-04-27

    申请人： Avidbots Corp.

    发明人： Faizan SHEIKH ,  Pablo Roberto Molina CABRERA ,  Todd WILLICK ,  Julien D'ALESSIO-DOUCET ,  Kenneth LEE

    IPC分类号： A47L11/282 ,  A47L11/40

    摘要： An apparatus includes a frame, a drive assembly supported by the frame, an electronic system supported by the frame, and a cleaning assembly coupled to the frame. The drive assembly is configured to move the frame along a surface. The cleaning assembly is configured to engage the surface to transfer detritus from the surface to a storage volume supported by the frame. The electronic system has at least a processor and a memory. The processor is configured to define a path along which the drive assembly travels and is configured to redefined a path along which the drive assembly travels based on at least one signal received from at least one sensor.

    Apparatus and methods for semi-autonomous cleaning of surfaces
    4.
    发明授权
    Apparatus and methods for semi-autonomous cleaning of surfaces 有权

    公开(公告)号：US10206550B2

    公开(公告)日：2019-02-19

    申请号：US16030426

    申请日：2018-07-09

    申请人： Avidbots Corp.

    发明人： Faizan Sheikh ,  Pablo Roberto Molina Cabrera ,  Todd Willick ,  Julien D'Alessio-Doucet ,  Kenneth Lee

    IPC分类号： A47L11/282 ,  A47L11/40

    摘要： An apparatus includes a frame, a drive assembly supported by the frame, an electronic system supported by the frame, and a cleaning assembly coupled to the frame. The drive assembly is configured to move the frame along a surface. The cleaning assembly is configured to engage the surface to transfer detritus from the surface to a storage volume supported by the frame. The electronic system has at least a processor and a memory. The processor is configured to define a path along which the drive assembly travels and is configured to redefined a path along which the drive assembly travels based on at least one signal received from at least one sensor.

    Self-cleaning squeegee system and methods of using the same
    6.
    发明授权
    Self-cleaning squeegee system and methods of using the same 有权

    公开(公告)号：US11517170B2

    公开(公告)日：2022-12-06

    申请号：US16519942

    申请日：2019-07-23

    申请人： Avidbots Corp

    发明人： Pablo Roberto Molina Cabrera ,  Ian Gardiner

    IPC分类号： A47L11/40 ,  A47L13/11 ,  A47L13/502

    摘要： A system for a self-cleaning squeegee that is integrated with a semi-autonomous cleaning device includes a frame coupled to the cleaning device. A squeegee is coupled to the frame and oriented such that an edge of the squeegee is in close proximity to a surface, e.g., a floor, for cleaning. A manifold configured to receive a cleaning fluid is coupled to the frame and oriented such that the cleaning fluid can be dispersed onto at least a portion of the squeegee. A connecting member is used to couple the manifold to an external fluid distribution system that provides the cleaning fluid. The self-cleaning squeegee system can thus disperse pressurized cleaning fluid, e.g., water or a mixture of water and soap, via the manifold to clean the surface of a squeegee. In this manner, the self-cleaning squeegee system can clean squeegees on the cleaning device without the need for human intervention.

    SYSTEM AND METHOD OF UNSUPERVISED STEREO MATCHING WITH SURFACE NORMAL ASSISTANCE FOR INDOOR APPLICATIONS
    9.
    发明公开
    SYSTEM AND METHOD OF UNSUPERVISED STEREO MATCHING WITH SURFACE NORMAL ASSISTANCE FOR INDOOR APPLICATIONS 审中-公开

    公开(公告)号：US20240320845A1

    公开(公告)日：2024-09-26

    申请号：US18593932

    申请日：2024-03-03

    申请人： Avidbots Corp

    发明人： Xiule FAN ,  Ali Jahani AMIRI ,  Baris FIDAN ,  Soo JEON

    IPC分类号： G06T7/593

    CPC分类号： G06T7/593 ,  G06T2207/10012 ,  G06T2207/20081 ,  G06T2207/20084

    摘要： A system and method for unsupervised stereo matching with surface normal assistance for indoor applications. According to the disclosure, a deep neural network with a feature extraction module, a normal branch, and a disparity branch is disclosed. The extraction module and the normal branch are trained first in a supervised manner for surface normal prediction. The predicted surface normal is then incorporated into the disparity branch, which is trained later in an unsupervised manner for disparity estimation. The latter unsupervised learning approach can reduce our method's dependence on a large amount of ground truth data that is difficult to collect. Experimental results indicate that our proposed method can predict accurate surface normal at textureless regions. With the help of the surface normal, the predicted disparity at these challenging areas is more accurate, which leads to improved quality of stereo matching in indoor scenarios.