Robust Sampling Based Model Predictive Control with Sparse Objective Information

We present an algorithmic framework for stochastic model predictive control that is able to optimize non-linear systems with cost functions that have sparse, discontinuous gradient information. The proposed framework combines the benefits of sampling-based model predictive control with linearization-based trajectory optimization methods. The resulting algorithm consists of a novel utilization of Tube-based model predictive control. We demonstrate robust algorithmic performance on a variety of simulated tasks, and on a real-world fast autonomous driving task.

[1]  Rolf Findeisen,et al.  Parameterized Tube Model Predictive Control , 2012, IEEE Transactions on Automatic Control.

[2]  Emilio Frazzoli,et al.  Sampling-based algorithms for optimal motion planning , 2011, Int. J. Robotics Res..

[3]  E. Todorov,et al.  A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems , 2005, Proceedings of the 2005, American Control Conference, 2005..

[4]  Sergey Levine,et al.  Deep visual foresight for planning robot motion , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Stefan Schaal,et al.  A Generalized Path Integral Control Approach to Reinforcement Learning , 2010, J. Mach. Learn. Res..

[6]  David Q. Mayne,et al.  Robust model predictive control of constrained linear systems with bounded disturbances , 2005, Autom..

[7]  Pieter Abbeel,et al.  Learning vehicular dynamics, with application to modeling helicopters , 2005, NIPS.

[8]  Vicenç Gómez,et al.  Real-Time Stochastic Optimal Control for Multi-Agent Quadrotor Systems , 2015, ICAPS.

[9]  David Q. Mayne,et al.  Robust model predictive control: advantages and disadvantages of tube-based methods ⋆ , 2011 .

[10]  Vicenç Gómez,et al.  Policy Search for Path Integral Control , 2014, ECML/PKDD.

[11]  Jan Peters,et al.  Sample-based informationl-theoretic stochastic optimal control , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[12]  James M. Rehg,et al.  Aggressive driving with model predictive path integral control , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Michael L. Littman,et al.  Open-Loop Planning in Large-Scale Stochastic Domains , 2013, AAAI.

[14]  Sebastian Thrun,et al.  Stanley: The robot that won the DARPA Grand Challenge , 2006, J. Field Robotics.

[15]  Marin Kobilarov,et al.  Cross-entropy motion planning , 2012, Int. J. Robotics Res..

[16]  S. LaValle.  Rapidly-exploring random trees : a new tool for path planning , 1998 .

[17]  Sergio Pellegrino,et al.  Trajectory Planning for CubeSat Short-Time-Scale Proximity Operations , 2014 .

[18]  Nolan Wagener,et al.  Information theoretic MPC for model-based reinforcement learning , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[19]  H. Kappen.  Path integrals and symmetry breaking for optimal control theory , 2005, physics/0505066.

[20]  Russ Tedrake,et al.  Funnel libraries for real-time robust feedback motion planning , 2016, Int. J. Robotics Res..

[21]  David Q. Mayne,et al.  TUBE-BASED ROBUST NONLINEAR MODEL PREDICTIVE CONTROL1 , 2007 .

[22]  Stefan Schaal,et al.  Learning Control in Robotics , 2010, IEEE Robotics & Automation Magazine.

[23]  Nathan Michael,et al.  Experience-driven Predictive Control with Robust Constraint Satisfaction under Time-Varying State Uncertainty , 2017, Robotics: Science and Systems.