Patents by Inventor Yufang WEN

Yufang WEN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250083301
    Abstract: The present invention provides an indoor mobile robot glass detection and map updating method based on depth image inpainting. The method comprises: first screening, based on laser radar intensity data, a region in which glass is suspected to be present; determining, based on an RGB image of the suspected region and by using a convolutional neural network, whether glass is really present; if glass is really present, extracting a glass region boundary, determining a defect point of a depth image, and performing depth information supplementing on the defect point based on the glass region boundary; and finally, performing plane sampling on the depth image, inpainting and updating a missing glass obstacle in an original map, and outputting a grid map for planning. Therefore, a problem, that the existing mapping algorithms and devices are prone to glass perception failure due to the characteristics of glass transmission, refraction, polarization, etc., affecting the map integrity and navigation safety, is solved.
    Type: Application
    Filed: September 18, 2024
    Publication date: March 13, 2025
    Inventors: Yong TAO, Yufang WEN, He GAO, Lian DUAN, Dongming HAN
  • Patent number: 11969892
    Abstract: A method for selecting a grasp posture of a dual-arm robot includes: setting a fitness value range, an iteration quantity threshold, and a fitness function; calculating the fitness value of the population, determining whether the population is within the value range, ending an iteration if the population is within the value range or continuing to determine whether a quantity of iterations reaches the iteration quantity threshold if the population is not within the value range, ending the iteration if the quantity of iterations reaches the iteration quantity threshold or performing crossover and mutation operations if the quantity of iterations does not reach the iteration quantity threshold, and dynamically selecting a gene retention strategy based on an iteration depth and a fitness value to retain a gene; updating a gene population representing a grasping position and performing determining cyclically; and obtaining an optimal target corresponding to dual arms after the iteration.
    Type: Grant
    Filed: August 4, 2023
    Date of Patent: April 30, 2024
    Assignee: BEIHANG UNIVERSITY
    Inventors: Yong Tao, Jiahao Wan, Haitao Liu, He Gao, Yufang Wen, Lian Duan, Shishu Huang
  • Publication number: 20240051126
    Abstract: A method for selecting a grasp posture of a dual-arm robot includes: setting a fitness value range, an iteration quantity threshold, and a fitness function; calculating the fitness value of the population, determining whether the population is within the value range, ending an iteration if the population is within the value range or continuing to determine whether a quantity of iterations reaches the iteration quantity threshold if the population is not within the value range, ending the iteration if the quantity of iterations reaches the iteration quantity threshold or performing crossover and mutation operations if the quantity of iterations does not reach the iteration quantity threshold, and dynamically selecting a gene retention strategy based on an iteration depth and a fitness value to retain a gene; updating a gene population representing a grasping position and performing determining cyclically; and obtaining an optimal target corresponding to dual arms after the iteration.
    Type: Application
    Filed: August 4, 2023
    Publication date: February 15, 2024
    Applicant: BEIHANG UNIVERSITY
    Inventors: Yong TAO, Jiahao WAN, Haitao LIU, He GAO, Yufang WEN, Lian DUAN, Shishu HUANG