Development of an Integrated Fuzzy-Logic-Based Missile Guidance Law Against High Speed Target

Designing Integrated Fuzzy Guidance Law for Aerodynamic Homing Missiles Using Genetic Algorithms

“…Thus, the missile acceleration is a function of both variables. 6) To implement the proposed guidance law, the direction of the predicted interception velocity, V p , must be calculated. The estimated value of the angle of this direction can be obtained directly from the interception geometry (Fig.…”

“…The literature reports that each classical guidance law has an operation region where it is superior to other guidance laws. 5) Lin et al 6) proposed an integrated fuzzybased guidance law for intercepting a high-maneuvering target. The parameters of that law are obtained by engineering experience and trial and error.…”

A Novel Neural-Fuzzy Guidance Law Design by Applying Different Neural Network Optimization Algorithms Alternatively for Each Step

“…1. Although some neural and/or fuzzy methods are also proposed for the guidance system design, the missile turning rate time constant and radome aberration error slope were not taken into account, but they play very important roles in the guidance performances [3][4][5]. In general, the radome shape must be very sharp to reduce the aerodynamic drag, but the target line-of-sight (LOS) refraction error would be increased as in Fig.1, so do the miss distance for the cases of larger missile turning rate time constants [1][2].…”

“…In general, the radome shape must be very sharp to reduce the aerodynamic drag, but the target line-of-sight (LOS) refraction error would be increased as in Fig.1, so do the miss distance for the cases of larger missile turning rate time constants [1][2]. Some fuzzy guidance laws were applied to the missile guidance law design [3][4][5], but the improvements are limited. In this paper, a novel neural-fuzzy guidance law by applying different neural network optimization algorithms alternatively in each step is proposed, the Gradient Descent (GD) [6], SCG (Scaled Conjugate Gradient) [7], and Levenberg-Marquardt (LM) [6][7] methods are applied to deal with those parameter variation effects, such as target maneuverability, missile autopilot time constant, turning rate time constant and radome slope error effects.…”

Sampling-based path planning: a new tool for missile guidance

“…However, neural networks cannot be trained with an exhaustive amount of optimal trajectories that would cover any possible configurations. Fuzzy logic techniques have also been investigated for the design of a midcourse guidance law (Lin and Chen [2000], Lin et al [2004]). Nevertheless, control constraints remain difficult to satisfy.…”