公开(公告)号：US11227168B2

公开(公告)日：2022-01-18

申请号：US16715413

申请日：2019-12-16

Applicant: QUALCOMM Incorporated

Inventor： Tianheng Wang ,  Muryong Kim ,  Jubin Jose

IPC: G06K9/00 ,  G01S19/45 ,  G06T7/73

Abstract: To make error correction in a position estimate of a vehicle, visual lane markings on the road can be matched with lane boundaries for the road within 3-D map data. Embodiments include obtaining a “stripe” indicative of an observed lane marking captured in a from a camera image, obtaining map data for the road on which the vehicle is located, determining the plane of the road from coordinates of lane boundaries within the map data, projecting the stripe onto the plane, and comparing the projected stripe with lane boundaries within the map data and associating the visual lane markings with the closest lane boundary. Differences between the projected stripe and the associated lane boundary can then be used for error correction in the position estimate of the vehicle.

公开(公告)号：US12259464B2

公开(公告)日：2025-03-25

申请号：US17658619

申请日：2022-04-08

Applicant: QUALCOMM Incorporated

Inventor： Mandar Narsinh Kulkarni ,  Jubin Jose ,  Muryong Kim

IPC: G01S13/89 ,  G01S13/58 ,  G06F18/23 ,  G06F18/2433

Abstract: Creating and updating an accurate radar map layer for HD map using crowdsourcing may comprise a vehicle obtaining radar data and filtering the radar data on a frame-by-frame basis. In some embodiments, additional filtering may be made on a batch of frames. The vehicle can then transmit the filtered radar data responsive to a determination that a confidence of a position estimate of the vehicle exceeds a conference threshold level and/or a determination that a reliance of the position estimate of the vehicle on the radar data exceeds a reliance threshold level.

公开(公告)号：US11636693B2

公开(公告)日：2023-04-25

申请号：US17153704

申请日：2021-01-20

Applicant: QUALCOMM Incorporated

Inventor： Urs Niesen ,  Muryong Kim ,  Jubin Jose

IPC: G06V20/56 ,  G06K9/62

Abstract: Association algorithms of newly-detected lane boundaries to lane boundaries can be made more robust through the use of generated or “dummy” states. Different types of dummy states can be used to identify outlier/erroneous detections and/or new, legitimate lane boundaries. Therefore, depending on a type of dummy state a newly-detected lane boundary is associated with, the newly-detected lane boundary can be ignored, or the associated dummy state can be added to the lane boundary states of the filter.