Neural network guidance based on pursuit-evasion games with enhanced performance

This paper addresses a neural network guidance based on pursuit-evasion games, and performance enhancing methods for it. Two-dimensional pursuit-evasion games solved by the gradient-based method are considered. The neural network guidance law employs the range, range rate, line-of-sight rate, and heading error as its input variables. Additional pattern selection methods and a hybrid guidance method are proposed for the sake of the interception performance enhancement. Numerical simulations are accompanied for the verification of the neural network approximation, and of the improved interception performance by the proposed methods. Moreover, all proposed guidance laws are compared with proportional navigation.

[1]  Min-Jea Tahk,et al.  AN ITERATIVE NUMERICAL METHOD FOR A CLASS OF QUANTITATIVE PURSUIT-EVASION GAMES , 1998 .

[2]  Rufus Isaacs,et al.  Differential Games , 1965 .

[3]  Min-Jea Tahk,et al.  Real-time neural-network midcourse guidance , 2001 .

[4]  T. Raivio,et al.  On Applied Nonlinear and Bilevel Programming or Pursuit-Evasion Games , 2001 .

[5]  Min-Jea Tahk,et al.  Real-time midcourse guidance with intercept point prediction , 1998 .

[6]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[7]  Min-Jea Tahk,et al.  Co-evolutionary computation for constrained min-max problems and its applications for pursuit-evasion games , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[8]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[9]  Min-Jea Tahk,et al.  Co-evolutionary optimization of three-dimensional target evasive maneuver against a proportionally guided missile , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[10]  H. J. Pesch,et al.  Complex differential games of pursuit-evasion type with state constraints, part 2: Numerical computation of optimal open-loop strategies , 1993 .

[11]  Min-Jea Tahk,et al.  A co-evolutionary method for pursuit-evasion games with non-zero lethal radii , 2004 .

[12]  J. Shinar,et al.  Approximate solution of singularly perturbed nonlinear pursuit-evasion games , 1982 .

[13]  Min-Jea Tahk,et al.  Coevolutionary augmented Lagrangian methods for constrained optimization , 2000, IEEE Trans. Evol. Comput..

[14]  Min-Jea Tahk,et al.  A THREE-DIMENSIONAL DIFFRENTIAL GAME MISSILE GUIDANCE LAW USING NEURAL NETWORKS , 2001 .

[15]  Min-Jea Tahk,et al.  Synthesis and Investigation of the Neural Network Guidance Based on Pursuit-Evasion Games , 2001 .

[16]  Joseph Z. Ben-Asher.  Linear quadratic pursuit-evasion games with terminal velocity constraints , 1996 .

[17]  Min-Jea Tahk,et al.  Three-dimensional midcourse guidance using neural networks for interception of ballistic targets , 2002 .

[18]  Mark H Lowenberg,et al.  AIAA Guidance, Navigation and Control Conference, Montreal, Canada , 2001 .

[19]  P. K. A. Menon,et al.  Short-Range Nonlinear Feedback Strategies for Aircraft Pursuit-Evasion , 1989 .

[20]  J. Shinar,et al.  Time-Varying Linear Pursuit-Evasion Game Models with Bounded Controls , 2002 .

[21]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[22]  Min-Jea Tahk,et al.  Real-time midcourse missile guidance robust against launch conditions , 1999 .