Skip to main content
placeholder image

Learning trajectories for robot programming by demonstration using a coordinated mixture of factor analysers

Journal Article


Abstract


  • This paper presents an approach for learning robust

    models of humanoid robot trajectories from demonstration.

    In this formulation, a model of the joint space trajectory is represented

    as a sequence of motion primitives where a nonlinear

    dynamical system is learned by constructing a hidden Markov

    model (HMM) predicting the probability of residing in each

    motion primitive. With a coordinated mixture of factor analyzers

    as the emission probability density of the HMM, we are able to

    synthesize motion from a dynamic system acting along a manifold

    shared by both demonstrator and robot. This provides signifi-

    cant advantages in model complexity for kinematically redundant

    robots and can reduce the number of corresponding observations

    required for further learning. A stability analysis shows that the

    system is robust to deviations from the expected trajectory as

    well as transitional motion between manifolds. This approach

    is demonstrated experimentally by recording human motion

    with inertial sensors, learning a motion primitive model and

    correspondence map between the human and robot, and synthesizing

    motion from the manifold to control a 19 degree-of-freedom

    humanoid robot.

Publication Date


  • 2016

Citation


  • M. Field, D. Stirling, Z. Pan & F. Naghdy, "Learning trajectories for robot programming by demonstration using a coordinated mixture of factor analysers," IEEE Transactions on Cybernetics, vol. 46, (3) pp. 706-717, 2016.

Scopus Eid


  • 2-s2.0-84926034784

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/4670

Has Global Citation Frequency


Number Of Pages


  • 11

Start Page


  • 706

End Page


  • 717

Volume


  • 46

Issue


  • 3

Place Of Publication


  • United States

Abstract


  • This paper presents an approach for learning robust

    models of humanoid robot trajectories from demonstration.

    In this formulation, a model of the joint space trajectory is represented

    as a sequence of motion primitives where a nonlinear

    dynamical system is learned by constructing a hidden Markov

    model (HMM) predicting the probability of residing in each

    motion primitive. With a coordinated mixture of factor analyzers

    as the emission probability density of the HMM, we are able to

    synthesize motion from a dynamic system acting along a manifold

    shared by both demonstrator and robot. This provides signifi-

    cant advantages in model complexity for kinematically redundant

    robots and can reduce the number of corresponding observations

    required for further learning. A stability analysis shows that the

    system is robust to deviations from the expected trajectory as

    well as transitional motion between manifolds. This approach

    is demonstrated experimentally by recording human motion

    with inertial sensors, learning a motion primitive model and

    correspondence map between the human and robot, and synthesizing

    motion from the manifold to control a 19 degree-of-freedom

    humanoid robot.

Publication Date


  • 2016

Citation


  • M. Field, D. Stirling, Z. Pan & F. Naghdy, "Learning trajectories for robot programming by demonstration using a coordinated mixture of factor analysers," IEEE Transactions on Cybernetics, vol. 46, (3) pp. 706-717, 2016.

Scopus Eid


  • 2-s2.0-84926034784

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/4670

Has Global Citation Frequency


Number Of Pages


  • 11

Start Page


  • 706

End Page


  • 717

Volume


  • 46

Issue


  • 3

Place Of Publication


  • United States