Patents by Inventor Runhao Li

Runhao Li 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).

  • Patent number: 12344359
    Abstract: Provided is a catching device for surface rescue based on an aircraft platform, and a surface rescue method. The catching device for surface rescue based on the aircraft platform includes a throwing mechanism, a flying mechanism, a recovery mechanism, an automatic control module, and a catching net. Both the throwing mechanism and the recovery mechanism are disposed on the flying mechanism, and the automatic control module automatically controls the throwing mechanism and the recovery mechanism. After the flying mechanism flies above a drowning person, the throwing mechanism is configured to throw the catching net towards the drowning person. After the catching net nets the drowning person, the recovery mechanism can drive a bottom of the catching net to close and lift the catching net upwards to approach the flying mechanism, and the flying mechanism is configured to drag the drowning person to a safe location.
    Type: Grant
    Filed: February 26, 2025
    Date of Patent: July 1, 2025
    Assignee: Beihang University
    Inventors: Lijing Wang, Tianyang Cai, Yanzeng Zhao, Chuanlei Zhu, Haixin Xu, Yunan Zou, Runhao Li, Jiaying Zou, Jun Zhang
  • Patent number: 12322406
    Abstract: This application relates to the field of audio noise reduction, and provides a method and system for noise reduction in aircraft simulator sounds, a device, and a medium. The method includes: acquiring sound data from an aircraft simulator sound system; classifying the sound data to obtain classified audio data; performing Short-Time Fourier Transform (STFT) processing on the classified audio data to obtain spectral frames; performing noise reduction processing on the spectral frames by using a neural network, to obtain processed spectral frames, where the neural network includes a recurrent neural network and a Deep Q-network (DQN); and performing inverse STFT on the processed spectral frames to obtain denoised audio. This application can achieve low-cost and efficient noise reduction for sounds.
    Type: Grant
    Filed: November 14, 2024
    Date of Patent: June 3, 2025
    Assignee: Beihang University
    Inventors: Lijing Wang, Runhao Li, Xiaolong Wang, Yanzeng Zhao, Haixin Xu, Tianyang Cai, Yunan Zou, Jun Zhang, Jiaying Zou