Learning manipulability ellipsoids for task compatibility in robot manipulation

Posture body variation is one of the ways in which humans skillfully and naturally augment their motion and strength capabilities along specific task-space directions in order to successfully perform complex manipulation tasks. Posture variation also has a significant role in robot manipulation, where manipulability arises as a useful criterion to analyze and control the robot dexterity as a function of its joint configuration. In this context, this paper introduces the promising idea of manipulability transfer, a method that allows robots to learn and reproduce desired manipulability ellipsoids from expert demonstrations. The proposed framework is built on a tensor-based formulation of Gaussian mixture model that takes into account that manipulability ellipsoids lie on the manifold of symmetric positive definite matrices. This geometry-aware method is used to design a manipulability-based redundancy resolution that allows the robot to modify its posture so that its manipulability ellipsoid coincides with the desired one. Experiments in simulation validate the functionality of the proposed approach, which extends the robot learning capability beyond trajectory, force and impedance learning approaches.

[1]  Alois Knoll,et al.  Task level robot programming using prioritized non-linear inequality constraints , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Carme Torras,et al.  Learning Physical Collaborative Robot Behaviors From Human Demonstrations , 2016, IEEE Transactions on Robotics.

[3]  Francesc Moreno-Noguer,et al.  3D Human Pose Tracking Priors using Geodesic Mixture Models , 2017, International Journal of Computer Vision.

[4]  Nikolaos G. Tsagarakis,et al.  On the role of robot configuration in Cartesian stiffness control , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Søren Hauberg,et al.  Model Transport: Towards Scalable Transfer Learning on Manifolds , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Pasquale Chiacchio Exploiting Redundancy in Minimum-Time Path Following Robot Control , 1990, 1990 American Control Conference.

[7]  P. Cisek,et al.  The influence of predicted arm biomechanics on decision making. , 2011, Journal of neurophysiology.

[8]  Xavier Pennec,et al.  A Riemannian Framework for Tensor Computing , 2005, International Journal of Computer Vision.

[9]  Sukhan Lee,et al.  Dual redundant arm configuration optimization with task-oriented dual arm manipulability , 1989, IEEE Trans. Robotics Autom..

[10]  Jun Nakanishi,et al.  Comparative experiments on task space control with redundancy resolution , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Michael I. Jordan,et al.  Obstacle Avoidance and a Perturbation Sensitivity Model for Motor Planning , 1997, The Journal of Neuroscience.

[12]  Suvrit Sra,et al.  A new metric on the manifold of kernel matrices with application to matrix geometric means , 2012, NIPS.

[13]  Tsuneo Yoshikawa,et al.  Manipulability of Robotic Mechanisms , 1985 .

[14]  Darwin G. Caldwell,et al.  A Method for Derivation of Robot Task-Frame Control Authority from Repeated Sensory Observations , 2017, IEEE Robotics and Automation Letters.

[15]  Peter J. Basser,et al.  Spectral decomposition of a 4th-order covariance tensor: Applications to diffusion tensor MRI , 2007, Signal Process..

[16]  Gijs Dubbelman,et al.  Intrinsic statistical techniques for robust pose estimation , 2011 .

[17]  Suvrit Sra,et al.  Conic Geometric Optimization on the Manifold of Positive Definite Matrices , 2013, SIAM J. Optim..

[18]  Giulio Sandini,et al.  Manipulability analysis , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

[19]  James W. Davis,et al.  A recursive filter for linear systems on Riemannian manifolds , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Satoshi Kagami,et al.  Manipulability optimization for trajectory generation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[21]  Sylvain Calinon,et al.  Gaussian mixture regression on symmetric positive definite matrices manifolds: Application to wrist motion estimation with sEMG , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Darwin G. Caldwell,et al.  An Approach for Imitation Learning on Riemannian Manifolds , 2017, IEEE Robotics and Automation Letters.

[23]  C. Melchiorri,et al.  Robot manipulability , 1995, IEEE Trans. Robotics Autom..

[24]  Jun-Ho Oh,et al.  Humanoid Posture Selection for Reaching Motion and a Cooperative Balancing Controller , 2016, J. Intell. Robotic Syst..

[25]  S. Chiu,et al.  Control of redundant manipulators for task compatibility , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.