Learning Partially Contracting Dynamical Systems from Demonstrations

An algorithm for learning the dynamics of point-to-point motions from demonstrations using an autonomous nonlinear dynamical system, named contracting dynamical system primitives (CDSP), is presented. The motion dynamics are approximated using a Gaussian mixture model (GMM) and its parameters are learned subject to constraints derived from partial contraction analysis. Systems learned using the proposed method generate trajectories that accurately reproduce the demonstrations and are guaranteed to converge to a desired goal location. Additionally, the learned models are capable of quickly and appropriately adapting to unexpected spatial perturbations and changes in goal location during reproductions. The CDSP algorithm is evaluated on shapes from a publicly available human handwriting dataset and also compared with two state-of-the-art motion generation algorithms. Furthermore, the CDSP algorithm is also shown to be capable of learning and reproducing point-to-point motions directly from real-world demonstrations using a Baxter robot.

[1]  Carlos Martínez,et al.  Easy robot programming concepts: An industrial perspective , 2013, 2013 IEEE International Conference on Automation Science and Engineering (CASE).

[2]  Jean-Jacques E. Slotine,et al.  On Contraction Analysis for Nonlinear Systems Analyzing stability differentially leads to a new perspective on nonlinear dynamic systems , 1999 .

[3]  Jean-Jacques E. Slotine,et al.  On Contraction Analysis for Non-linear Systems , 1998, Autom..

[4]  Soon-Jo Chung,et al.  Observer Design for Stochastic Nonlinear Systems via Contraction-Based Incremental Stability , 2015, IEEE Transactions on Automatic Control.

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

[6]  Aude Billard,et al.  Learning motions from demonstrations and rewards with time-invariant dynamical systems based policies , 2018, Auton. Robots.

[7]  Jongeun Choi,et al.  The Inverse Problem of Continuous-Time Linear Quadratic Gaussian Control With Application to Biological Systems Analysis , 2014, HRI 2014.

[8]  Michael I. Jordan,et al.  Optimal feedback control as a theory of motor coordination , 2002, Nature Neuroscience.

[9]  Ashwin P. Dani,et al.  Learning Contracting Nonlinear Dynamics From Human Demonstration for Robot Motion Planning , 2015, HRI 2015.

[10]  Jan Peters,et al.  Probabilistic Movement Primitives , 2013, NIPS.

[11]  Klaus Neumann,et al.  Neurally imprinted stable vector fields , 2013, ESANN.

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

[13]  Jochen J. Steil,et al.  Open-source benchmarking for learned reaching motion generation in robotics , 2015, Paladyn J. Behav. Robotics.

[14]  Ales Ude,et al.  Task adaptation through exploration and action sequencing , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[15]  Ashwin P. Dani,et al.  Learning periodic motions from human demonstrations using transverse contraction analysis , 2016, 2016 American Control Conference (ACC).

[16]  Ron Alterovitz,et al.  Closed-loop global motion planning for reactive execution of learned tasks , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[18]  Siddhartha S. Srinivasa,et al.  Movement primitives via optimization , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Darwin G. Caldwell,et al.  A task-parameterized probabilistic model with minimal intervention control , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Jun Morimoto,et al.  Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives , 2010, IEEE Transactions on Robotics.

[21]  Cong Wang,et al.  Fast planning of well conditioned trajectories for model learning , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Ashwin P. Dani,et al.  Human Intention Inference Using Expectation-Maximization Algorithm With Online Model Learning , 2017, IEEE Transactions on Automation Science and Engineering.

[23]  Aude Billard,et al.  Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions , 2014, Robotics Auton. Syst..

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

[25]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[26]  Nicolas Mansard,et al.  Optimality in robot motion , 2014, Commun. ACM.

[27]  A. Garulli,et al.  Positive Polynomials in Control , 2005 .

[28]  Maya Cakmak,et al.  Keyframe-based Learning from Demonstration , 2012, Int. J. Soc. Robotics.

[29]  Stefan Schaal,et al.  Learning coupling terms for obstacle avoidance , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[30]  Klaus Neumann,et al.  Neural learning of stable dynamical systems based on data-driven Lyapunov candidates , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  Maja J. Mataric,et al.  Robot life-long task learning from human demonstrations: a Bayesian approach , 2017, Auton. Robots.

[32]  Nicolas Mansard,et al.  Optimization as motion selection principle in robot action , 2015, Commun. ACM.

[33]  David A. Cohn,et al.  Active Learning with Statistical Models , 1996, NIPS.

[34]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[35]  Stefan Schaal,et al.  Dynamics systems vs. optimal control--a unifying view. , 2007, Progress in brain research.

[36]  Jean-Jacques E. Slotine,et al.  On partial contraction analysis for coupled nonlinear oscillators , 2004, Biological Cybernetics.