公开(公告)号：US20250131178A1

公开(公告)日：2025-04-24

申请号：US18885497

申请日：2024-09-13

Applicant: Harbin Institute of Technology

Inventor： Huijun GAO ,  Zhengkai LI ,  Junhu CAO ,  Xinghu YU ,  Hao SUN ,  Jianbin QIU ,  Weichao SUN

IPC: G06F30/398 ,  G06F115/12 ,  G06N5/01 ,  H01L21/67

Abstract: A method for optimizing the placement process of a surface mounter using a heuristic adaptive tabu search is presented, relevant to surface-mount technology. The method includes encoding and decoding heuristic adaptive information link, where encoded information cover component allocation sequence, head sequence, heuristic algorithm selection, and pick-and-place path optimization sequence. The decoded results configure the component allocation algorithm and pick-and-place path optimization algorithm, and the optimized placement process is derived using these configured algorithms. The component allocation algorithm includes both the available feeder-oriented heuristic algorithm and the assigned feeder group-oriented heuristic algorithm, suitable for different feeder scenarios. Optimizing the selection of these algorithms achieves adaptive optimization for various production scenarios. The tabu search algorithm conducts neighborhood search operations on the adaptive information link, addressing component allocation and pick-and-place path optimization simultaneously. This approach synergistically optimizes the number of equivalent pick-up operations and pick-and-place path length, significantly enhancing production efficiency.

公开(公告)号：US20210333793A1

公开(公告)日：2021-10-28

申请号：US16931653

申请日：2020-07-17

Applicant: Harbin Institute of Technology

Inventor： Huijun GAO ,  Zhan LI ,  Xidi XUE ,  Weichao SUN ,  Xuebo YANG ,  Xinghu YU

IPC: G05D1/00 ,  G01S17/89 ,  G01S17/931 ,  G05D1/02 ,  G01C21/20

Abstract: The present invention relates to an indoor monocular navigation method based on cross-sensor transfer learning and a system thereof. Determining an preliminary autonomous navigation model according to simulated laser radar data; acquiring actual single-line laser radar data and monocular camera data of the mobile robot simultaneously in an actual environment; determining the heading angle of the mobile robot according to the actual laser radar data; determining a laser radar monocular vision navigation model, according to the generated heading angle of the mobile robot and the monocular camera data at a the same moment and by using a Resnet18 network and a pre-trained YOLO v3 network; determining a heading angle of the mobile robot at the current moment, according to the acquired monocular camera data and by using the laser radar monocular vision navigation model; performing navigation of the mobile robot.