公开(公告)号：US11909950B1

公开(公告)日：2024-02-20

申请号：US17448326

申请日：2021-09-21

Applicant: Amazon Technologies, Inc.

Inventor： Karl Bernard Swanson ,  Gregory Cartagena ,  Jing Ma ,  Olugbenga Osibodu ,  Albert William Saunders, IV ,  Stephen A. Caldara ,  William Joseph Klein ,  Dincer Bozkaya ,  Sara Jean Woo

IPC: G01C3/00 ,  H04N17/00 ,  G01S17/894 ,  H04N13/239 ,  G01S7/497 ,  G01C3/08 ,  G01S17/42 ,  G01C3/06 ,  G01S17/48 ,  G01C3/04 ,  G01C3/20 ,  G01S7/40

CPC classification number: H04N17/002 ,  G01C3/00 ,  G01C3/04 ,  G01C3/06 ,  G01C3/08 ,  G01C3/20 ,  G01S7/497 ,  G01S17/42 ,  G01S17/48 ,  G01S17/894 ,  H04N13/239 ,  G01S7/40

Abstract: Systems and methods for evaluating the performance of three-dimensional (3D) sensors can include, for example, obtaining, via a 3D sensor in a testing apparatus, range information of a scene within a field-of-view (FOV) of the 3D sensor. The scene includes a plurality of targets disposed within the testing apparatus. Each of the plurality of targets is located at a different distance from the 3D sensor in the testing apparatus. A validation of the performance of the 3D sensor at the different distances is performed at a same point in time, based on the range information. An indication of a result of the validation is provided.

公开(公告)号：US12259229B1

公开(公告)日：2025-03-25

申请号：US17745648

申请日：2022-05-16

Applicant: Amazon Technologies, Inc.

Inventor： Sergey M. Nikitin ,  Sara Jean Woo ,  Jing Ma

IPC: G01B11/22 ,  B25J9/16 ,  G01B11/25

Abstract: Systems, techniques, and devices for performing long range depth estimation are described. Multiple images of a scene are captured via at least three imaging sensors of a camera device. A first imaging sensor is separated from a second imaging sensor by a first baseline, and a third imaging sensor is separated from the first imaging sensor by a second baseline larger than the first baseline. A first point cloud is generated based on a first image and a second image captured by the first imaging sensor and the second imaging sensor, respectively. A second point cloud is generated based on the first image and a third image captured by the first imaging sensor and the third imaging sensor, respectively. Depth information of the scene is generated based on the first point cloud and the second point cloud.

公开(公告)号：US12220813B1

公开(公告)日：2025-02-11

申请号：US17361843

申请日：2021-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Dincer Bozkaya ,  Sara Jean Woo ,  William Joseph Klein ,  Jing Ma ,  Gregory Cartagena ,  Justin Croyle ,  Gabriel Hebert ,  Fahrudin Alagic ,  Stephen A. Caldara

IPC: B25J19/02 ,  B25J9/16 ,  G01C21/00 ,  G01C25/00 ,  G06Q10/087

Abstract: Systems and techniques for performing a calibration test of an obstacle detection sensor of a drive unit are described. An example system includes a calibration region and at least one drive unit. The calibration region is disposed in an environment and includes a calibration apparatus. The at least one drive unit is operable to autonomously move throughout the environment. The at least one drive unit includes a sensor configured to detect one or more objects within the environment. The at least one drive unit is configured to autonomously transition to the calibration region upon detecting at least one predetermined condition, and perform a calibration test of the first sensor at the calibration region using the calibration apparatus.