Constrained Optimal Control for a Class of Nonlinear Systems with Uncertainties
Approximate dynamic programming formulation (ADP) implemented with an Adaptive Critic (AC) based neural network (NN) structure has evolved as a powerful technique for solving the Hamilton-Jacobi-Bellman (HJB) equations. As interest in the ADP and the AC solutions are escalating, there is a dire need to consider enabling factors for their possible implementations. A typical AC structure consists of two interacting NNs which is computationally expensive. In this paper, a new architecture, called the “Cost Function Based Single Network Adaptive Critic (J-SNAC)” is presented that eliminates one of the networks in a typical AC structure. This approach is applicable to a wide class of nonlinear systems in engineering. Many real-life problems have controller limits. In this paper, a non-quadratic cost function is used that incorporates the control constraints. Necessary equations for optimal control are derived and an algorithm to solve the constrained-control problem with J-SNAC is developed. A benchmark nonlinear system is used to illustrate the working of the proposed technique. Extensions to optimal control-constrained problems in the presence of uncertainties are also considered. © 2011 AACC American Automatic Control Council.
J. Ding and S. N. Balakrishnan, "Constrained Optimal Control for a Class of Nonlinear Systems with Uncertainties," Proceedings of the American Control Conference, Institute of Electrical and Electronics Engineers (IEEE), Jan 2011.
Proceedings of the American Control Conference (2011, San Francisco, CA)
Mechanical and Aerospace Engineering
Article - Conference proceedings
© 2011 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Jan 2011