公开(公告)号：US20240160211A1

公开(公告)日：2024-05-16

申请号：US18088625

申请日：2022-12-26

Applicant: Industrial Technology Research Institute

Inventor： Ruei-Jhih Hong ,  Yong-Ren Li ,  Ta-Cheng Ma

IPC: G05D1/02

CPC classification number: G05D1/0212 ,  G05D1/0246 ,  G05D2201/0216

Abstract: An automated guided vehicle (AGV) includes an image capturing device, a storage device, a fetching device, a driving device and a processor. The processor is configured to execute: controlling the AGV to move from a starting position to a target position according to a navigation coordinate system, the target position corresponding to the object to be fetched; capturing a depth image from the object to be fetched through the image capturing device; performing image recognition on the depth image to obtain reference pixel information; converting the reference pixel information to the navigation coordinate system according to a coordinate mapping algorithm to obtain a calibrated position; and determining an object-fetching route according to the target position and the calibrated position, and controlling the AGV to move according to the object-fetching route to fetch the object to be fetched.

公开(公告)号：US11636612B2

公开(公告)日：2023-04-25

申请号：US17114540

申请日：2020-12-08

Applicant: Industrial Technology Research Institute

Inventor： Yong-Ren Li ,  Chao-Hui Tu ,  Ching-Tsung Cheng ,  Ruei-Jhih Hong

IPC: G06T7/50 ,  G06T7/70 ,  G05D1/02 ,  G06N3/08

Abstract: An AGV navigation device is provided, which includes a RGB-D camera, a plurality of sensors and a processor. When an AGV moves along a target route having a plurality of paths, the RGB-D camera captures the depth and color image data of each path. The sensors (including an IMU and a rotary encoder) record the acceleration, the moving speed, the direction, the rotation angle and the moving distance of the AGV moving along each path. The processor generates training data according to the depth image data, the color image data, the accelerations, the moving speeds, the directions, the moving distances and the rotation angles, and inputs the training data into a machine learning model for deep learning in order to generate a training result. Therefore, the AGV navigation device can realize automatic navigation for AGVs without any positioning technology, so can reduce the cost of automatic navigation technologies.