Title：Robot sampling motion planning method and system based on spectrogram model guidance
Country：中国
Patent No.：202110573761.6
Legal Status：Under review
Inventor：Chongkun Xia, Bin Liang,Xueqian Wang, Houde Liu, Songping Mai
Assignee：International Graduate School at Shenzhen, Tsinghua University
Address：Tsinghua Campus, Xili University Town, Nanshan District, Shenzhen City 518061, Guangdong Province
Filing Date：2021-05-25
Issue Date：
Abstract：
The invention discloses a robot sampling motion planning method and system based on spectrogram model guidance. The method comprises the following steps: S1, representing and learning mapping distribution of a non-obstacle area of a Cartesian space in a robot configuration space through spectrogram clustering; and training related spectrogram models through samples in the feature space; s2, providing a sample generator with a guiding strategy for a standard sampling planning algorithm by using the trained spectrogram model, and generating a sample required by sampling planning; and S3, guiding the planning exploration process to be unfolded in a non-obstacle area of the configuration space. According to the method and system, collision detection is reduced or avoided, and the actual operation efficiency of sampling motion planning is improved.
Patent Certificate：
PDF/Jpg