知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.013 秒)

    SYSTEM AND METHOD FOR MITIGATION OF ANOMALOUS DATA IN A CONNECTED VEHICLE SYSTEM
    2.
    发明申请
    SYSTEM AND METHOD FOR MITIGATION OF ANOMALOUS DATA IN A CONNECTED VEHICLE SYSTEM 审中-公开

    公开(公告)号：US20190258242A1

    公开(公告)日：2019-08-22

    申请号：US15902342

    申请日：2018-02-22

    申请人： General Motors LLC

    发明人： Paul A. AVERY ,  David H. Clifford

    IPC分类号： G05D1/00 ,  H04N7/18 ,  G06K9/62 ,  G06K9/00 ,  G05D1/02

    摘要： At least one transceiver is configured to wirelessly receive data from a source node that is external to a vehicle, the data including a unique identifier (ID) of the source node and at least one of: a first location of the source node; a first heading of the source node; a first speed of the source node; and a first object type of the source node. At least one of a camera and a sensor is configured to identify objects located around the vehicle. An anomaly module is configured to selectively indicate that an anomaly is present in the data. A distributed ledger includes a list of unique IDs associated with not-trusted source nodes. A ledger management module is configured to, in response to an indication that an anomaly is present in the data received from the source node, add the unique ID of the source node to the list.

    Identification and clustering of lane lines on roadways using reinforcement learning
    3.
    发明授权
    Identification and clustering of lane lines on roadways using reinforcement learning 有权

    公开(公告)号：US11836992B2

    公开(公告)日：2023-12-05

    申请号：US17162548

    申请日：2021-01-29

    申请人： General Motors LLC

    发明人： Mohammed H. Al Qizwini ,  Orhan Bulan ,  David H. Clifford ,  Mason D. Gemar

    IPC分类号： G06V20/56 ,  G06N3/08 ,  G06V20/10 ,  G06F18/214

    CPC分类号： G06V20/588 ,  G06F18/214 ,  G06N3/08 ,  G06V20/176

    摘要： A system comprises a processor and a memory storing instructions. The processor receives an image for processing using a reinforcement learning based agent comprising a neural network trained using a reward function. The image includes N lane lines of a roadway, where N is a positive integer. The instructions configure the processor to traverse the image using the agent at least N times from a first end of the image to a second end of the image by: incrementally moving the agent from a first side of the image to a second side of the image after each traversal; and maximizing rewards for the agent using the reward function during each traversal of the image using the agent. The instructions configure the processor to identify the N lane lines of the roadway as a single cluster of lane lines after traversing the image using the agent at least N times.

    System and method for mitigation of anomalous data in a connected vehicle system
    6.
    发明授权
    System and method for mitigation of anomalous data in a connected vehicle system 有权

    公开(公告)号：US10599140B2

    公开(公告)日：2020-03-24

    申请号：US15902342

    申请日：2018-02-22

    申请人： General Motors LLC

    发明人： Paul A. Avery ,  David H. Clifford

    IPC分类号： G06K9/00 ,  G05D1/00 ,  H04N7/18 ,  G06K9/62 ,  G05D1/02

    摘要： At least one transceiver is configured to wirelessly receive data from a source node that is external to a vehicle, the data including a unique identifier (ID) of the source node and at least one of: a first location of the source node; a first heading of the source node; a first speed of the source node; and a first object type of the source node. At least one of a camera and a sensor is configured to identify objects located around the vehicle. An anomaly module is configured to selectively indicate that an anomaly is present in the data. A distributed ledger includes a list of unique IDs associated with not-trusted source nodes. A ledger management module is configured to, in response to an indication that an anomaly is present in the data received from the source node, add the unique ID of the source node to the list.

    Method and apparatus for classifying LIDAR data for object detection
    8.
    发明授权
    Method and apparatus for classifying LIDAR data for object detection 有权

    公开(公告)号：US10346695B2

    公开(公告)日：2019-07-09

    申请号：US15605275

    申请日：2017-05-25

    申请人： GENERAL MOTORS LLC

    发明人： David H. Clifford ,  David J. Hiemenga

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06T17/00 ,  G06T7/11 ,  G01S17/89 ,  G01S17/93 ,  G01S7/48 ,  G06K9/32 ,  G06K9/46 ,  G06K9/56

    摘要： A method and apparatus for classifying light detection and ranging sensor data are provided. The method includes transforming sensor data of the LIDAR into point cloud data, selecting a cell including a subset of the point cloud data, dividing the selected cell into a plurality of voxels, calculating a difference of gradients for the plurality of voxels, performing a first pass on the plurality of voxels to identify voxels that contain an object based the difference of gradients, performing a second pass on the plurality of voxels to identify voxels that contain the object by adjusting a voxel with at least one from among a jitter parameter and a rotation parameter, and outputting a centroid average of voxels identified as containing the object.