IEEE Transactions on Systems Man and Cybernetics Systems · 2019 · 97 citations · 27 references
EngineeringRobotics EngineeringMachine LearningStatistical LearningUncertainty QuantificationControl Of Dynamical SystemsControl SystemsControl TheoryDynamic ControlModel Predictive ControlSetpoint TrackingDynamical Systems StabilityEnergy ConsumptionEvent-triggered ControlModel ComplexityNonholonomic ControlNonholonomic SystemsPredictive ControlTrajectory Tracking Control
The event-triggered model predictive control (MPC) reduces energy consumption for updating control sequences while maintaining the originality of the MPC, which copes with hard constraints on dynamical systems. In the presence of large uncertainties, however, the standard event-triggered MPC may generate too frequent event occurrences. To compensate for unknown uncertainties, this paper applies a statistical learning to event-triggered MPC. The stability and the feasibility of the proposed control system are analyzed in regard to the statistical learning influences, such as the number of training samples, model complexity, and learning parameters. Accordingly, the event-triggering policy is established to guarantee the stability. We evaluate the proposed algorithm for the tracking problem of a nonholonomic model perturbed by uncertainties. In comparison with the standard event-triggered control scheme, the simulation results of the proposed method show better tracking performance with less frequent event triggers.
27
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
The Nature of Statistical Learning Theory
Stephan R. Sain, Vladimir Vapnik · Technometrics · 1996 · 4.1K citations
Parallelized Stochastic Gradient Descent
Martin Zinkevich, Markus Weimer, Lihong Li et al. · 2010 · 1.1K citations