公开(公告)号：US12059967B2

公开(公告)日：2024-08-13

申请号：US16920095

申请日：2020-07-02

Applicant: ABB E-mobility B.V.

Inventor： Gregory A. Cole ,  William J. Eakins ,  Stefan J. Raaijmakers

IPC: B60L53/00 ,  B60L53/37 ,  G06T7/73 ,  G06T7/90 ,  G06V10/143 ,  G06V20/00 ,  G06V20/10

CPC classification number: B60L53/37 ,  G06T7/73 ,  G06T7/90 ,  G06V10/143 ,  G06V20/00 ,  G06V20/10 ,  G06T2207/20024 ,  G06T2207/30248

Abstract: A plug connection system that autonomously charges an electric vehicle (EV) is provided. The method includes: adjusting configuration settings of an image capturing device; capturing an image using the image capturing device, wherein a portion of the image comprises an optically distinctive object associated with a charging portal of the EV, and wherein the image comprises a plurality of pixels; applying a pixel value threshold associated with a pixel metric to the image to filter the plurality of pixels of the image to a first subset of pixels; determining, based on filtering the plurality of pixels to the first subset of pixels, a location of the optically distinctive object associated with the charging portal of the EV within the image; and providing information to maneuver a robotic arm to a physical position associated with the location of the optically distinctive object within the image.

公开(公告)号：US12062208B2

公开(公告)日：2024-08-13

申请号：US17331222

申请日：2021-05-26

Applicant: ABB E-mobility B.V.

Inventor： Matthew Hetrich ,  Gregory A. Cole

IPC: B60L53/37 ,  G06T7/70 ,  G06T7/73 ,  G06V10/75 ,  G06V10/82 ,  H04N23/695

CPC classification number: G06T7/74 ,  B60L53/37 ,  G06T7/70 ,  G06T7/73 ,  G06V10/757 ,  G06V10/82 ,  H04N23/695 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30244 ,  G06T2207/30252

Abstract: An automated charging system for an electric vehicle is disclosed that includes a plug with a built-in camera assembly. The camera assembly captures images of a charging port of the electric vehicle, which are processed by one or more processors to estimate the location of the charging port relative to the plug. A multi-stage localization architecture is described that includes a gross localization procedure and a fine localization procedure. The gross localization procedure can implement a first convolutional neural network (CNN) to estimate a position of an object in the image. The fine localization procedure can implement a second CNN to estimate a position and orientation of the object. Actuators for moving the plug in a three-dimensional space can be controlled by the multi-stage localization architecture.