Learning Augmented Joint-Space Task-Oriented Dynamical Systems: A Linear Parameter Varying and Synergetic Control Approach

In this letter, we propose an asymptotically stable joint-space dynamical system (DS) that captures desired behaviors in joint-space while converging toward a task-space attractor in both position and orientation. To encode joint-space behaviors while meeting the stability criteria, we propose a DS constructed as a linear parameter varying system combining different behavior synergies and provide a method for learning these synergy matrices from demonstrations. Specifically, we use dimensionality reduction to find a low-dimensional embedding space for modulating joint synergies, and then estimate the parameters of the corresponding synergies by solving a convex semidefinite optimization problem that minimizes the joint velocity prediction error from the demonstrations. Our proposed approach is empirically validated on a variety of motions that reach a target in position and orientation, while following a desired joint-space behavior.

[1]  E. Nadaraya.  On Estimating Regression , 1964 .

[2]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

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

[4]  Klaus Neumann,et al.  Learning robot motions with stable dynamical systems under diffeomorphic transformations , 2015, Robotics Auton. Syst..

[5]  Aude Billard,et al.  A probabilistic Programming by Demonstration framework handling constraints in joint space and task space , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Johan Löfberg,et al.  YALMIP : a toolbox for modeling and optimization in MATLAB , 2004 .

[7]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[8]  W. Wolovich,et al.  A computational technique for inverse kinematics , 1984, The 23rd IEEE Conference on Decision and Control.

[9]  Darwin G. Caldwell,et al.  Learning and Reproduction of Gestures by Imitation , 2010, IEEE Robotics & Automation Magazine.

[10]  Masaaki Honda,et al.  Kinematic construction of the trajectory of sequential arm movements , 1999, Biological Cybernetics.

[11]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[12]  Aude Billard,et al.  A Dynamical System Approach for Softly Catching a Flying Object: Theory and Experiment , 2016, IEEE Transactions on Robotics.

[13]  Aude Billard,et al.  Coordinated multi-arm motion planning: Reaching for moving objects in the face of uncertainty , 2016, Robotics: Science and Systems.

[14]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[15]  Shingo Shimoda,et al.  Synergetic Learning Control Paradigm for Redundant Robot to Enhance Error-Energy Index , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[16]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[17]  Qian Tan,et al.  Weighted augmented Jacobian matrix with a variable coefficient method for kinematics mapping of space teleoperation based on human–robot motion similarity , 2016 .

[18]  G. S. Watson,et al.  Smooth regression analysis , 1964 .

[19]  Darwin G. Caldwell,et al.  Learning Competing Constraints and Task Priorities from Demonstrations of Bimanual Skills , 2017, ArXiv.

[20]  Aude Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[21]  Eric O. Postma,et al.  Dimensionality Reduction: A Comparative Review , 2008 .

[22]  Stefan Schaal,et al.  Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning , 2002, Applied Intelligence.

[23]  Bruno Siciliano,et al.  A solution algorithm to the inverse kinematic problem for redundant manipulators , 1988, IEEE J. Robotics Autom..

[24]  Aude Billard,et al.  A unified framework for coordinated multi-arm motion planning , 2018, Int. J. Robotics Res..

[25]  Andrea Lockerd Thomaz,et al.  Stylized motion generalization through adaptation of velocity profiles , 2010, 19th International Symposium in Robot and Human Interactive Communication.

[26]  Jun Morimoto,et al.  Orientation in Cartesian space dynamic movement primitives , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[27]  Alireza Karimi,et al.  Fixed-structure LPV discrete-time controller design with induced l2-norm and performance , 2016, Int. J. Control.

[28]  Aude Billard,et al.  Learning complex sequential tasks from demonstration: A pizza dough rolling case study , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[29]  Peters Jan,et al.  Jointly learning trajectory generation and hitting point prediction in robot table tennis , 2016 .

[30]  Aude Billard,et al.  Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations , 2015, IEEE Transactions on Robotics.

[31]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[32]  Wen Yu,et al.  Human behavior learning for robot in joint space , 2015, Neurocomputing.

[33]  Helge J. Ritter,et al.  Gaussian Mixture Model for 3-DoF orientations , 2017, Robotics Auton. Syst..

[34]  Sylvain Calinon,et al.  A tutorial on task-parameterized movement learning and retrieval , 2015, Intelligent Service Robotics.

[35]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[36]  S. Buss.  Introduction to Inverse Kinematics with Jacobian Transpose , Pseudoinverse and Damped Least Squares methods , 2004 .

[37]  H. Cruse,et al.  The human arm as a redundant manipulator: The control of path and joint angles , 2004, Biological Cybernetics.