ESTIMATION RELIABILITY OF HAZARD WARNING FROM A SENSOR

    公开(公告)号:US20220207389A1

    公开(公告)日:2022-06-30

    申请号:US17135705

    申请日:2020-12-28

    Abstract: Systems and methods for a model for estimation of reliability of a hazard sensor observation at a vehicle are disclosed. An example apparatus may include a hazard observation interface configured to receive one or more hazard observations from the hazard sensor of the vehicle, wherein each of the one or more hazard observations is associated with a hazard location and a hazard timestamp, a ground truth module configured to determine ground truth data from one or more weather records from a historical weather database based on the hazard location and the hazard timestamp, and a model configured to perform a comparison of the one or more hazard observations to the one or more weather records, the model trained for estimation of reliability of the hazard sensor observations based on the comparison of the one or more hazard observations to the one or more weather records.

    RECALL OF HAZARD WARNING CREATED FROM VEHICLE SENSOR DATA

    公开(公告)号:US20220205807A1

    公开(公告)日:2022-06-30

    申请号:US17135708

    申请日:2020-12-28

    Abstract: Systems and methods for a model for determining reliability of hazard sensors associated with vehicles are described. An example method includes receiving hazard observations collected from at least one hazard sensor, wherein the hazard observations is associated with hazard locations, receiving weather data associated with the hazard locations, performing a comparison of the hazard observations to the weather data, identifying a quantity of ground truth matches in which the hazard observations match the weather data based on the comparison, identifying a quantity of false negatives in which the weather data are mismatched with the hazard observations based on the comparison, and calculating a recall value from the quantity of false negatives and the quantity of ground truth matches.

    AUTONOMOUS VEHICLE NAVIGATION USING NON-CONNECTED MAP FRAGMENTS

    公开(公告)号:US20230303111A1

    公开(公告)日:2023-09-28

    申请号:US17655818

    申请日:2022-03-22

    CPC classification number: B60W60/001 B60W2556/40 B60W2555/20

    Abstract: An apparatus autonomously operates at least one system of a vehicle as the vehicle navigates along a route through at least a portion of a traversable network in a sensor-based navigation mode. The apparatus obtains a map fragment corresponding to an area along the route; and, responsive to determining that the vehicle is located within the area, autonomously operates the at least one system of the vehicle as the vehicle navigates a portion of the route within the area in a map-based navigation mode using map data of the map fragment. Responsive to determining that the vehicle has exited the area, the apparatus autonomously operates the at least one system of the vehicle as the vehicle continues to navigate along the route in the sensor-based navigation mode. The map fragment is a portion of a high definition map configured to enable map-based autonomous vehicle navigation/control.

    METHOD AND APPARATUS FOR VERIFYING REDUCED VISIBILITY EVENT WARNINGS

    公开(公告)号:US20220139192A1

    公开(公告)日:2022-05-05

    申请号:US17087826

    申请日:2020-11-03

    Abstract: A method, apparatus and computer program product for determining a reduced visibility event warning are described herein. In the context of a method, a location corresponding with a reduced visibility event warning may be identified. Information regarding visibility at one or more stationary positions based upon the location of the reduced visibility event warning may be received from one or more remote devices (e.g., sensing apparatuses). The method may determine a reduced visibility event warning confidence for the location corresponding with a reduced visibility event warning based upon the information regarding visibility. The method may cause the reduced visibility event warning to be published in an instance in which the reduced visibility event warning confidence satisfies a confidence threshold.

Patent Agency Ranking