METHOD AND SYSTEM FOR MODELING PERSONALIZED CAR-FOLLOWING DRIVING STYLES WITH MODEL-FREE INVERSE REINFORCEMENT LEARNING

    公开(公告)号:US20240124003A1

    公开(公告)日:2024-04-18

    申请号:US17936459

    申请日:2022-09-29

    CPC classification number: B60W50/06 B60W60/001 B60W2520/00 B60W2554/80

    Abstract: A method may include learning reward functions for a plurality of first vehicles based on first vehicle data associated with the plurality of first vehicles using inverse reinforcement learning, associating each vehicle of the plurality of first vehicles with one cluster among a plurality of clusters based on the reward functions, determining a centroid reward function for each of the clusters based on the reward functions associated with each cluster, performing a comparison between second vehicle data associated with a second vehicle and the first vehicle data, determining a vehicle among the plurality of first vehicles having associated first vehicle data that is most similar to the second vehicle data based on the comparison, associating the second vehicle with the cluster associated with the determined vehicle, and controlling operation of the second vehicle based on the centroid reward function of the cluster associated with the second vehicle.

    METHOD AND DEVICE FOR COLLISION PREDICTING
    89.
    发明公开

    公开(公告)号:US20240109544A1

    公开(公告)日:2024-04-04

    申请号:US18081562

    申请日:2022-12-14

    Abstract: A method and device for collision predicting and readable computer storage medium. The method for collision predicting includes: obtaining a host vehicle motion track of a host vehicle; obtaining at least one host vehicle track point on the host vehicle motion track; establishing a collision prediction area around the host vehicle track point, and matching the collision prediction area to a time point where the host vehicle is located at the host vehicle track point; obtaining a target vehicle motion track of a target vehicle; obtaining at least one target vehicle track point on the target vehicle motion track, and matching the target vehicle track point to a time point where the target vehicle is located at the target vehicle track point; and calculating a projected collision time between the host vehicle and the target vehicle when a preset condition is met.

    Road condition detecting method and automotive system providing the same

    公开(公告)号:US11946948B2

    公开(公告)日:2024-04-02

    申请号:US17569858

    申请日:2022-01-06

    Abstract: An automotive system providing method for detecting a road in an abnormal state based on a measured value of an acceleration sensor mounted on a vehicle includes an acceleration sensor measuring a value of gravity acceleration acting on a vehicle; a position measuring sensor measuring a position of the vehicle; a memory in which the measured value of the gravity acceleration and the position of the vehicle at a time point at which the gravity acceleration is measured are stored; and a controller electrically connected to the acceleration sensor, the position measuring sensor and the memory and configured for determining a road corresponding to the position where the value of the gravity acceleration is measured as being in an abnormal condition when the controller concludes that a difference value between the value of the gravity acceleration measured during operation of the vehicle and a reference acceleration value added to the value of the gravity acceleration to correct the value of the gravity acceleration as a zero reference point is out of a predetermined threshold range.

Patent Agency Ranking