公开(公告)号：US11747155B2

公开(公告)日：2023-09-05

申请号：US17593618

申请日：2020-10-24

Applicant: GOERTEK INC.

Inventor： Xueqiang Wang ,  Yifan Zhang ,  Libing Zou ,  Baoming Li

IPC: G01C21/34 ,  G05B13/02

CPC classification number: G01C21/3446 ,  G05B13/027

Abstract: A global path planning method and device for an unmanned vehicle are disclosed. The method comprises: establishing an object model through a reinforcement learning method, wherein the object model includes: a state of the unmanned vehicle, an environmental state described by a map picture, and an evaluation index of a path planning result; building a deep reinforcement learning neural network based on the object model established, to obtain a stable neural network model; inputting the map picture of the environment state and the state of the unmanned vehicle into the deep reinforcement learning neural network after trained, and generating a motion path of the unmanned vehicle. According to the present disclosure, the environment information in the scene is marked through the map picture, and the map features are extracted through the deep neural network, thereby simplifying the modeling process of the map scene.

公开(公告)号：US11573576B2

公开(公告)日：2023-02-07

申请号：US16633315

申请日：2019-08-14

Applicant: GOERTEK INC.

Inventor： Xueqiang Wang ,  Mengmeng Wang ,  Lu Bai ,  Xiangdong Zhang

IPC: G05D1/10 ,  B64C39/02 ,  G05D1/06

Abstract: The present disclosure provides a method for controlling a drone, a drone, and a system. The method for controlling a drone comprises: determining operating parameters of a moving platform according to field-of-view images containing the moving platform collected at any two different moments and flight parameters of the drone; calculating a time-varying tracking position of the moving platform based on the operating parameters; controlling the drone to track the moving platform according to the time-varying tracking position of the moving platform; and controlling the drone to perform a landing operation according to a relative position of the moving platform and the drone during tracking. The technical solutions according to the present disclosure have high landing accuracy, rely less on device performance and have high versatility.

公开(公告)号：US12045061B2

公开(公告)日：2024-07-23

申请号：US17309922

申请日：2020-09-10

Applicant: GOERTEK INC.

Inventor： Xueqiang Wang ,  Yifan Zhang ,  Libing Zou ,  Fuqiang Zhang

IPC: G05D1/00 ,  G06N3/04 ,  G06N3/08 ,  G06N7/01

CPC classification number: G05D1/0221 ,  G05D1/0088 ,  G05D1/0214 ,  G05D1/0289 ,  G05D1/0297 ,  G06N3/04 ,  G06N3/08 ,  G06N7/01

Abstract: A multi-AGV motion planning method, device and system are disclosed. The method of the present disclosure comprises: establishing an object model through reinforcement learning; building a neural network model based on the object model, performing environment settings including AGV group deployment, and using the object model of the AGV in a set environment to train the neural network model until a stable neural network model is obtained; setting an action constraint rule; and after the motion planning is started, inputting the state of current AGV, states of other AGVs and permitted actions in a current environment into the neural network model after trained, obtaining the evaluation indexes of a motion planning result output by the neural network model, obtaining an action to be executed of the current AGV according to the evaluation indexes, and performing validity judgment on the action to be executed using the action constraint rule.

公开(公告)号：US20230402949A1

公开(公告)日：2023-12-14

申请号：US18449141

申请日：2023-08-14

Applicant: GOERTEK INC.

Inventor： Yifan ZHANG ,  Pengbo Feng ,  Xueqiang Wang ,  Tao Han

IPC: H02P25/034 ,  H02P7/025

CPC classification number: H02P25/034 ,  H02P7/025

Abstract: Disclosed are a voice coil motor, a method and a device for controlling the voice coil motor. The voice coil motor includes an outer coil module and an inner coil module inside the outer coil module, an air gap for the inner coil module to move is formed between the inner coil module and the outer coil module. The method includes: driving the outer coil module to generate an outer coil electromagnetic force; determining an inner coil current instruction according to an expectation force instruction and force feedback information sent by an executing mechanism of the voice coil motor; driving the inner coil module of the voice coil motor to generate an inner coil electromagnetic force according to the inner coil current instruction; and enabling the executing mechanism to generate a motor acting force according to the outer coil electromagnetic force and the inner coil electromagnetic force.

公开(公告)号：US20240038278A1

公开(公告)日：2024-02-01

申请号：US18266401

申请日：2021-10-20

Applicant: Goertek Inc.

Inventor： LIBING ZOU ,  Yifan Zhang ,  Xueqiang Wang ,  Fuqiang Zhang

IPC: G11B27/34 ,  G11B27/031 ,  G06T7/33

CPC classification number: G11B27/34 ,  G11B27/031 ,  G06T7/337 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/20081 ,  G06T2207/20056

Abstract: A method and device for timing alignment of audio signals. The method includes: generating frequency domain images respectively for an audio signal to be aligned and a template audio signal (S110); inputting the frequency domain images into a twin neural network of a timing offset prediction model respectively, to obtain two frequency domain features output by the twin neural network (S120); fusing the two frequency domain features to obtain a fused feature (S130); inputting the fused features into a prediction network of the timing offset prediction model to obtain a timing offset output by the prediction network (S140); and performing timing alignment processing on the audio signal to be aligned according to the timing offset (S150). The technical solution is more robust, and especially in a noisy environment, features extracted by a deep neural network are more intrinsic and more stable. An end-to-end timing offset prediction model is more accurate and faster.

公开(公告)号：US11740780B2

公开(公告)日：2023-08-29

申请号：US17594145

申请日：2020-10-30

Applicant: GOERTEK INC.

Inventor： Libing Zou ,  Yifan Zhang ,  Fuqiang Zhang ,  Xueqiang Wang

IPC: G06F3/0487 ,  G06V10/82 ,  G06V40/16 ,  G06V40/18 ,  G06F3/01 ,  G06F3/0354 ,  G06F3/038 ,  G06F3/14

CPC classification number: G06F3/0487 ,  G06F3/012 ,  G06F3/013 ,  G06F3/038 ,  G06F3/03543 ,  G06F3/1423 ,  G06V10/82 ,  G06V40/161 ,  G06V40/18

Abstract: A multi-screen display system and a mouse switching control method are disclosed. The mouse switching control method is applied to a multi-screen display system comprising a main display screen and at least one extended display screen, and comprises: obtaining user images collected by cameras installed on the main display screen and the extended display screen respectively; inputting the user images into a neural network model, and predicting a screen that a user is currently paying attention to using the neural network model to obtain a prediction result; and controlling to switch a mouse to the screen that a user is currently paying attention to according to the prediction result. The system and mouse switching control method are based on self-learning of visual attention, predict the current screen operated by the user, automatically switch the mouse to the corresponding screen position, and improve the user experience.