公开(公告)号：US12233907B1

公开(公告)日：2025-02-25

申请号：US17320630

申请日：2021-05-14

Applicant: Zoox, Inc.

Inventor： Xin Wang ,  Yi Xu

IPC: B60W60/00 ,  B60W30/09 ,  G06N20/00 ,  G06V20/56

Abstract: Techniques for detecting door states associated with vehicles in an environment are described herein. The techniques may include receiving sensor data associated with a first vehicle in an environment and inputting the sensor data into a machine-learned model that is configured to determine a state of a door of the first vehicle. Based on the input data, an output may be received from the machine-learned model that indicates the state of the door of the first vehicle. Based on the state of the door of the first vehicle, a trajectory of a second vehicle may be controlled. The techniques may also include training the machine-learned model to detect door states of vehicles.

公开(公告)号：US12051276B1

公开(公告)日：2024-07-30

申请号：US18205651

申请日：2023-06-05

Applicant: Zoox, Inc.

Inventor： Oytun Ulutan ,  Xin Wang ,  Kratarth Goel ,  Vasiliy Karasev ,  Sarah Tariq ,  Yi Xu

IPC: G06V40/20 ,  B60W60/00 ,  G05D1/00 ,  G06F18/21 ,  G06F18/214 ,  G06F18/24 ,  G06N20/00 ,  G06T7/70 ,  G06V20/58 ,  G06V40/10

CPC classification number: G06V40/28 ,  G06F18/2148 ,  G06F18/217 ,  G06F18/24 ,  G06T7/70 ,  G06V20/582 ,  G06V40/103 ,  G06V40/23 ,  B60W60/001 ,  B60W2420/403 ,  B60W2540/041 ,  G05D1/0088 ,  G05D1/0231 ,  G06N20/00 ,  G06T2207/20081 ,  G06T2207/30196 ,  G06T2207/30252

Abstract: Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

公开(公告)号：US11710352B1

公开(公告)日：2023-07-25

申请号：US17320690

申请日：2021-05-14

Applicant: Zoox, Inc.

Inventor： Oytun Ulutan ,  Xin Wang ,  Kratarth Goel ,  Vasiliy Karasev ,  Sarah Tariq ,  Yi Xu

IPC: G06V40/20 ,  G06T7/70 ,  G06V20/58 ,  G06V40/10 ,  G06F18/24 ,  G06F18/21 ,  G06F18/214 ,  G06N20/00 ,  G05D1/02 ,  G05D1/00 ,  B60W60/00

CPC classification number: G06V40/28 ,  G06F18/217 ,  G06F18/2148 ,  G06F18/24 ,  G06T7/70 ,  G06V20/582 ,  G06V40/103 ,  G06V40/23 ,  B60W60/001 ,  B60W2420/42 ,  B60W2540/041 ,  G05D1/0088 ,  G05D1/0231 ,  G06N20/00 ,  G06T2207/20081 ,  G06T2207/30196 ,  G06T2207/30252

Abstract: Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

公开(公告)号：US12236705B1

公开(公告)日：2025-02-25

申请号：US17320678

申请日：2021-05-14

Applicant: Zoox, Inc.

Inventor： Oytun Ulutan ,  Xin Wang ,  Kratarth Goel ,  Vasiliy Karasev ,  Sarah Tariq ,  Yi Xu

IPC: G06K9/00 ,  G01S13/89 ,  G01S17/89 ,  G05D1/00 ,  G06N5/04 ,  G06N20/00 ,  G06V10/22 ,  G06V20/56 ,  G06V40/10

Abstract: Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

公开(公告)号：US12293543B1

公开(公告)日：2025-05-06

申请号：US18068329

申请日：2022-12-19

Applicant: Zoox, Inc.

Inventor： Xin Wang ,  Xinyu Xu

IPC: G06T7/73 ,  B60W40/04 ,  B60W60/00 ,  G01C21/30 ,  G06T7/11 ,  G06T7/50

Abstract: Techniques for performing computer vision operations for a vehicle using image data of an environment of the vehicle are described herein. In some cases, a vehicle (e.g., an autonomous vehicle) can determine a predicted position (including a predicted depth) and/or a predicted trajectory for an object in the vehicle environment based on data generated by projecting a map object described by the map data for a vehicle environment to image data of the vehicle environment.