Linear Conic Optimization for Inverse Optimal Control

We address the inverse problem of Lagrangian identification based on trajecto-ries in the context of nonlinear optimal control. We propose a general formulation of the inverse problem based on occupation measures and complementarity in linear programming. The use of occupation measures in this context offers several advan-tages from the theoretical, numerical and statistical points of view. We propose an approximation procedure for which strong theoretical guarantees are available. Finally, the relevance of the method is illustrated on academic examples.

[1]  R. Rosen.  Optimality Principles in Biology , 1967, Springer US.

[2]  Stephen P. Boyd,et al.  Imputing a convex objective function , 2011, 2011 IEEE International Symposium on Intelligent Control.

[3]  R. Vinter.  Convex duality and nonlinear optimal control , 1993 .

[4]  A. Jameson,et al.  Inverse Problem of Linear Optimal Control , 1973 .

[5]  M. Petit.  Dynamic optimization. The calculus of variations and optimal control in economics and management : by Morton I. Kamien and Nancy L. Schwartz. Second Edition. North-Holland (Advanced Textbooks in Economics), Amsterdam and New York, 1991. Pp. xvii+377. ISBN0-444- 01609-0 , 1994 .

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

[7]  Colin McDiarmid,et al.  Surveys in Combinatorics, 1989: On the method of bounded differences , 1989 .

[8]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[9]  H. Whitney.  Geometric Integration Theory , 1957 .

[10]  J. Casti.  On the general inverse problem of optimal control theory , 1980 .

[11]  Emmanuel Trélat,et al.  Nonlinear Optimal Control via Occupation Measures and LMI-Relaxations , 2007, SIAM J. Control. Optim..

[12]  O. Hernández-Lerma,et al.  THE LINEAR PROGRAMMING APPROACH TO DETERMINISTIC OPTIMAL CONTROL PROBLEMS , 1996 .

[13]  Didier Henrion,et al.  Optimization on linear matrix inequalities for polynomial systems control , 2013, 1309.3112.

[14]  Didier Henrion,et al.  Inverse optimal control with polynomial optimization , 2014, 53rd IEEE Conference on Decision and Control.

[15]  B. Gaveau,et al.  Hamilton–Jacobi theory and the heat kernel on Heisenberg groups , 2000 .

[16]  Karl J. Friston.  What Is Optimal about Motor Control? , 2011, Neuron.

[17]  S. Kahne,et al.  Optimal control: An introduction to the theory and ITs applications , 1967, IEEE Transactions on Automatic Control.

[18]  Timothy Bretl,et al.  A convex approach to inverse optimal control and its application to modeling human locomotion , 2012, 2012 IEEE International Conference on Robotics and Automation.

[19]  Johan Löfberg,et al.  Pre- and Post-Processing Sum-of-Squares Programs in Practice , 2009, IEEE Transactions on Automatic Control.

[20]  Alexander Barvinok,et al.  A course in convexity , 2002, Graduate studies in mathematics.

[21]  P. Kokotovic,et al.  Inverse Optimality in Robust Stabilization , 1996 .

[22]  Takao Fujii,et al.  A complete optimally condition in the inverse problem of optimal control , 1984, The 23rd IEEE Conference on Decision and Control.

[23]  Gábor Lugosi,et al.  Introduction to Statistical Learning Theory , 2004, Advanced Lectures on Machine Learning.

[24]  Emmanuel Trélat,et al.  Robust optimal stabilization of the Brockett integrator via a hybrid feedback , 2005, Math. Control. Signals Syst..

[25]  Jean-Paul Laumond,et al.  From human to humanoid locomotion—an inverse optimal control approach , 2010, Auton. Robots.

[26]  Richard B. Vinter,et al.  The Equivalence of Strong and Weak Formulations for Certain Problems in Optimal Control , 1978 .

[27]  B. Anderson,et al.  Linear Optimal Control , 1971 .

[28]  Anton van den Hengel,et al.  Semidefinite Programming , 2014, Computer Vision, A Reference Guide.

[29]  Didier Henrion,et al.  Convex Computation of the Region of Attraction of Polynomial Control Systems , 2012, IEEE Transactions on Automatic Control.

[30]  J. Lasserre.  Moments, Positive Polynomials And Their Applications , 2009 .

[31]  F. Rampazzo,et al.  Filippov's and Filippov–Ważewski's Theorems on Closed Domains , 2000 .

[32]  Jean-Paul Gauthier,et al.  How humans fly , 2013 .

[33]  R. E. Kalman,et al.  When Is a Linear Control System Optimal , 1964 .

[34]  B. Anderson,et al.  Nonlinear regulator theory and an inverse optimal control problem , 1973 .

[35]  J. Andrew Bagnell,et al.  Maximum margin planning , 2006, ICML.

[36]  Paolo Mason,et al.  On Inverse Optimal Control Problems of Human Locomotion: Stability and Robustness of the Minimizers , 2013 .

[37]  Ruggero Frezza,et al.  Linear Optimal Control Problems and Quadratic Cost Functions Estimation , 2004 .

[38]  F. Thau.  On the inverse optimum control problem for a class of nonlinear autonomous systems , 1967, IEEE Transactions on Automatic Control.

[39]  M. Bardi,et al.  Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations , 1997 .

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

[41]  Vladimir Gaitsgory,et al.  Linear Programming Approach to Deterministic Infinite Horizon Optimal Control Problems with Discounting , 2009, SIAM J. Control. Optim..

[42]  E. Todorov.  Optimality principles in sensorimotor control , 2004, Nature Neuroscience.

[43]  Timothy Bretl,et al.  Kinematic and dynamic control of a wheeled mobile robot , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[44]  Jean-Paul Laumond,et al.  An Optimality Principle Governing Human Walking , 2008, IEEE Transactions on Robotics.

[45]  Didier Henrion,et al.  Linear conic optimization for nonlinear optimal control , 2014, 1407.1650.