Recent research has shown that guiding sampling-based planners with sampling distributions, learned from previous experiences via density estimation, can significantly decrease computation times for motion planning. We propose an algorithm that can estimate the density from the experiences of a robot with different kinematic structure, on the same task. The method allows to generalize collected data from one source manipulator to similarly designed target manipulators, significantly reducing the computation time for new queries for the target manipulator. We evaluate the algorithm in two experiments, including a constrained manipulation task with five different collaborative robots, and show that transferring information can significantly decrease planning time.


    Access

    Download


    Export, share and cite



    Title :

    Kinematic transfer learning of sampling distributions for manipulator motion planning



    Conference:

    2022 ; Philadelphia, USA



    Publication date :

    2022-05-01



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Kinematic Modeling and Motion Planning of the Mobile Manipulator Agri.Q for Precision Agriculture

    Giovanni Colucci / Andrea Botta / Luigi Tagliavini et al. | BASE | 2022

    Free access

    Kinematic motion planning with regional planning constraints

    CHEREPINSKY IGOR / DING XUCHU / SANE HARSHAD S | European Patent Office | 2018

    Free access

    KINEMATIC MOTION PLANNING WITH REGIONAL PLANNING CONSTRAINTS

    CHEREPINSKY IGOR / DING XUCHU / SANE HARSHAD S | European Patent Office | 2020

    Free access

    Kinematics Modeling and Motion Planning of Continuum Manipulator

    Zhu, Yi / Zeng, Haibin / Zou, Shuangquan et al. | Springer Verlag | 2023


    Active manipulator motion planning for planetary landform awareness

    Leng, Shu / Hu, Haochen / Yu, Meng et al. | SAGE Publications | 2019