A data-driven indirect method for nonlinear optimal control

Nonlinear optimal control problems are challenging to solve due to the prevalence of local minima that prevent convergence and/or optimality. This paper describes nearest-neighbors optimal control (NNOC), a data-driven framework for nonlinear optimal control using indirect methods. It determines initial guesses for new problems with the help of precomputed solutions to similar problems, retrieved using k-nearest neighbors. A sensitivity analysis technique is introduced to linearly approximate the variation of solutions between new and precomputed problems based on their variation of parameters. Experiments show that NNOC can obtain the global optimal solution orders of magnitude faster than standard random restart methods, and sensitivity analysis can further reduce the solving time almost by half. Examples are shown on two optimal control problems in vehicle control.

[1]  Dario Izzo,et al.  Machine Learning of Optimal Low-Thrust Transfers Between Near-Earth Objects , 2017, HAIS.

[2]  Junfeng Li,et al.  Fuel-Optimal Low-Thrust Trajectory Optimization Using Indirect Method and Successive Convex Programming , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[3]  Fanghua Jiang,et al.  Improving Low-Thrust Trajectory Optimization by Adjoint Estimation with Shape-Based Path , 2017 .

[4]  Marc Toussaint,et al.  Fast motion planning from experience: trajectory prediction for speeding up movement generation , 2013, Auton. Robots.

[5]  Ryan P. Russell,et al.  Primer Vector Theory Applied to Global Low-Thrust Trade Studies , 2006 .

[6]  C. Karen Liu,et al.  Differential dynamic programming with nonlinear constraints , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Steven M. LaValle,et al.  Generating Uniform Incremental Grids on SO(3) Using the Hopf Fibration , 2010, WAFR.

[8]  R. Epenoy,et al.  New smoothing techniques for solving bang–bang optimal control problems—numerical results and statistical interpretation , 2002 .

[9]  H. Maurer,et al.  Sensitivity Analysis and Real-Time Control of Parametric Optimal Control Problems Using Boundary Value Methods , 2001 .

[10]  Kris Hauser,et al.  Learning Trajectories for Real- Time Optimal Control of Quadrotors , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Dario Izzo,et al.  Real-time optimal control via Deep Neural Networks: study on landing problems , 2016, ArXiv.

[12]  Christos Ampatzis,et al.  Machine Learning Techniques for Approximation of Objective Functions in Trajectory Optimisation , 2009 .

[13]  J. Betts.  Survey of Numerical Methods for Trajectory Optimization , 1998 .

[14]  Kris Hauser,et al.  Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[15]  John L. Junkins,et al.  New Results for Time-Optimal Three-Axis Reorientation of a Rigid Spacecraft , 2009 .

[16]  Jing Li,et al.  Time‐optimal reorientation of the rigid spacecraft using a pseudospectral method integrated homotopic approach , 2015 .

[17]  Jorge J. Moré,et al.  User Guide for Minpack-1 , 1980 .

[18]  Raffaello D'Andrea,et al.  Quadrocopter performance benchmarking using optimal control , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Hexi Baoyin,et al.  Practical Techniques for Low-Thrust Trajectory Optimization with Homotopic Approach , 2012 .

[20]  George M. Siouris,et al.  Applied Optimal Control: Optimization, Estimation, and Control , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  Danica Kragic,et al.  Data-Driven Grasp Synthesis—A Survey , 2013, IEEE Transactions on Robotics.

[22]  Marco Sciandrone,et al.  Machine learning for global optimization , 2010, Computational Optimization and Applications.

[23]  Alberto Bemporad,et al.  The explicit solution of model predictive control via multiparametric quadratic programming , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[24]  Fanghua Jiang,et al.  Capture of near-Earth objects with low-thrust propulsion and invariant manifolds , 2015 .

[25]  Dario Izzo,et al.  Machine learning and evolutionary techniques in interplanetary trajectory design , 2018, Springer Optimization and Its Applications.

[26]  Sami Haddadin,et al.  Learning quadrotor maneuvers from optimal control and generalizing in real-time , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[27]  Gerd Hirzinger,et al.  Trajectory planning for optimal robot catching in real-time , 2011, 2011 IEEE International Conference on Robotics and Automation.

[28]  Francesco Topputo,et al.  Deep Learning for Autonomous Lunar Landing , 2018 .

[29]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[30]  Kris Hauser,et al.  A data-driven indirect method for nonlinear optimal control , 2019 .

[31]  David G. Lowe,et al.  Scalable Nearest Neighbor Algorithms for High Dimensional Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Kris Hauser.  Learning the Problem-Optimum Map: Analysis and Application to Global Optimization in Robotics , 2017, IEEE Transactions on Robotics.

[33]  Pieter Abbeel,et al.  Predicting initialization effectiveness for trajectory optimization , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[34]  J. Junkins,et al.  Analytical Mechanics of Space Systems , 2003 .