知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

38 records (took 0.017 seconds)

    Three-Dimensional Object Detection
    23.
    发明申请
    Three-Dimensional Object Detection 有权

    公开(公告)号：US20230127115A1

    公开(公告)日：2023-04-27

    申请号：US17971069

    申请日：2022-10-21

    Applicant: UATC, LLC

    Inventor： Ming Liang ,  Bin Yang ,  Shenlong Wang ,  Wei-Chiu Ma ,  Raquel Urtasun

    IPC: G01S17/89 ,  G06N3/08 ,  G06N3/04 ,  G01S17/931 ,  G01S7/481 ,  G05D1/02 ,  G06N3/02 ,  G06V20/64 ,  G06F18/25 ,  G06V10/764 ,  G06V10/80 ,  G06V20/56

    Abstract: Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and/or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and/or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle. For example, multi-sensor fusion can be implemented via continuous convolutions to fuse image data samples and LIDAR feature maps at different levels of resolution.

    Systems and Methods for Vehicle-to-Vehicle Communications for Improved Autonomous Vehicle Operations
    24.
    发明申请
    Systems and Methods for Vehicle-to-Vehicle Communications for Improved Autonomous Vehicle Operations 有权

    公开(公告)号：US20210152996A1

    公开(公告)日：2021-05-20

    申请号：US17066096

    申请日：2020-10-08

    Applicant: UATC, LLC

    Inventor： Sivabalan Manivasagam ,  Ming Liang ,  Bin Yang ,  Wenyuan Zeng ,  Raquel Urtasun ,  Tsu-shuan Wang

    IPC: H04W4/46 ,  G08G1/01

    Abstract: Systems and methods for vehicle-to-vehicle communications are provided. An example computer-implemented method includes obtaining, by a computing system onboard a first autonomous vehicle, sensor data associated with an environment of the first autonomous vehicle. The method includes determining, by the computing system, an intermediate environmental representation of at least a portion of the environment of the first autonomous vehicle based at least in part on the sensor data. The method includes generating, by the computing system, a compressed intermediate environmental representation by compressing the intermediate environmental representation of at least the portion of the environment of the first autonomous vehicle. The method includes communicating, by the computing system, the compressed intermediate environmental representation to a second autonomous vehicle.

    Systems and Methods for Vehicle-to-Vehicle Communications for Improved Autonomous Vehicle Operations
    25.
    发明申请
    Systems and Methods for Vehicle-to-Vehicle Communications for Improved Autonomous Vehicle Operations 有权

    公开(公告)号：US20210146959A1

    公开(公告)日：2021-05-20

    申请号：US17066108

    申请日：2020-10-08

    Applicant: UATC, LLC

    Inventor： Sivabalan Manivasagam ,  Ming Liang ,  Bin Yang ,  Wenyuan Zeng ,  Raquel Urtasun ,  Tsu-shuan Wang

    IPC: B60W60/00 ,  H04W4/46 ,  G08G1/00 ,  G06N3/08

    Abstract: Systems and methods for vehicle-to-vehicle communications are provided. An example computer-implemented method includes obtaining from a first autonomous vehicle, by a computing system onboard a second autonomous vehicle, a first compressed intermediate environmental representation. The first compressed intermediate environmental representation is indicative of at least a portion of an environment of the second autonomous vehicle and is based at least in part on sensor data acquired by the first autonomous vehicle at a first time. The method includes generating, by the computing system, a first decompressed intermediate environmental representation by decompressing the first compressed intermediate environmental representation. The method includes determining, by the computing system, a first time-corrected intermediate environmental representation based at least in part on the first decompressed intermediate environmental representation. The first time-corrected intermediate environmental representation corresponds to a second time associated with the second autonomous vehicle.

    End-To-End Interpretable Motion Planner for Autonomous Vehicles
    26.
    发明公开
    End-To-End Interpretable Motion Planner for Autonomous Vehicles 审中-公开

    公开(公告)号：US20230367318A1

    公开(公告)日：2023-11-16

    申请号：US18358443

    申请日：2023-07-25

    Applicant: UATC, LLC

    Inventor： Wenyuan Zeng ,  Wenjie Luo ,  Abbas Sadat ,  Bin Yang ,  Rachel Urtasun

    IPC: G05D1/02 ,  G05D1/00 ,  G01C21/32 ,  G01C21/34

    CPC classification number: G05D1/0212 ,  G05D1/0088 ,  G01C21/32 ,  G01C21/3453 ,  G05D2201/0213

    Abstract: Systems and methods for generating motion plans including target trajectories for autonomous vehicles are provided. An autonomous vehicle may include or access a machine-learned motion planning model including a backbone network configured to generate a cost volume including data indicative of a cost associated with future locations of the autonomous vehicle. The cost volume can be generated from raw sensor data as part of motion planning for the autonomous vehicle. The backbone network can generate intermediate representations associated with object detections and objection predictions. The motion planning model can include a trajectory generator configured to evaluate one or more potential trajectories for the autonomous vehicle and to select a target trajectory based at least in part on the cost volume generate by the backbone network.

    End-to-end interpretable motion planner for autonomous vehicles
    27.
    发明授权
    End-to-end interpretable motion planner for autonomous vehicles 有权

    公开(公告)号：US11755018B2

    公开(公告)日：2023-09-12

    申请号：US16541739

    申请日：2019-08-15

    Applicant: UATC, LLC

    Inventor： Wenyuan Zeng ,  Wenjie Luo ,  Abbas Sadat ,  Bin Yang ,  Raquel Urtasun

    IPC: G05D1/02 ,  G05D1/00 ,  G01C21/32 ,  G01C21/34

    CPC classification number: G05D1/0212 ,  G01C21/32 ,  G01C21/3453 ,  G05D1/0088 ,  G05D2201/0213

    Abstract: Systems and methods for generating motion plans including target trajectories for autonomous vehicles are provided. An autonomous vehicle may include or access a machine-learned motion planning model including a backbone network configured to generate a cost volume including data indicative of a cost associated with future locations of the autonomous vehicle. The cost volume can be generated from raw sensor data as part of motion planning for the autonomous vehicle. The backbone network can generate intermediate representations associated with object detections and objection predictions. The motion planning model can include a trajectory generator configured to evaluate one or more potential trajectories for the autonomous vehicle and to select a target trajectory based at least in part on the cost volume generate by the backbone network.

    Multi-task multi-sensor fusion for three-dimensional object detection
    29.
    发明授权
    Multi-task multi-sensor fusion for three-dimensional object detection 有权

    公开(公告)号：US11494937B2

    公开(公告)日：2022-11-08

    申请号：US16654487

    申请日：2019-10-16

    Applicant: UATC, LLC

    Inventor： Raquel Urtasun ,  Bin Yang ,  Ming Liang

    IPC: G06T7/73 ,  G06T11/60 ,  G06T7/55 ,  G01S17/89 ,  G05D1/00 ,  G05D1/02 ,  G06N20/00

    Abstract: Provided are systems and methods that perform multi-task and/or multi-sensor fusion for three-dimensional object detection in furtherance of, for example, autonomous vehicle perception and control. In particular, according to one aspect of the present disclosure, example systems and methods described herein exploit simultaneous training of a machine-learned model ensemble relative to multiple related tasks to learn to perform more accurate multi-sensor 3D object detection. For example, the present disclosure provides an end-to-end learnable architecture with multiple machine-learned models that interoperate to reason about 2D and/or 3D object detection as well as one or more auxiliary tasks. According to another aspect of the present disclosure, example systems and methods described herein can perform multi-sensor fusion (e.g., fusing features derived from image data, light detection and ranging (LIDAR) data, and/or other sensor modalities) at both the point-wise and region of interest (ROI)-wise level, resulting in fully fused feature representations.

    Three-dimensional object detection
    30.
    发明授权
    Three-dimensional object detection 有权

    公开(公告)号：US11221413B2

    公开(公告)日：2022-01-11

    申请号：US16353463

    申请日：2019-03-14

    Applicant: UATC, LLC

    Inventor： Ming Liang ,  Bin Yang ,  Shenlong Wang ,  Wei-Chiu Ma ,  Raquel Urtasun

    IPC: G01S17/89 ,  G05D1/02 ,  G06N3/08 ,  G06K9/00 ,  G06N3/04 ,  G06K9/62 ,  G01S17/931 ,  G01S7/481 ,  G06N3/02

    Abstract: Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and/or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and/or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle. For example, multi-sensor fusion can be implemented via continuous convolutions to fuse image data samples and LIDAR feature maps at different levels of resolution.

Patent Agency Ranking