Neuro-genetic adaptive attitude control

Adaptive neuro-genetic control of chaos applied to the attitude control problem

“…For this reason we proposed [2] an alternative two part architecture. This paper does not give the full details of the algorithm, as these can be found elsewhere [2].…”

“…His work is based in the classical adaptive control theory, but instead of matrices he uses neural networks [14][15][16]. In this paper, the hybrid neurogenetic method introduced in [2] is further tested and evaluated for the control of chaotic dynamic systems.…”

“…Following the introduction, Sect. 2 gives a brief description of the neuro-genetic control architecture introduced in [2]. In Sect.…”

“…The critical property of such models is the fact that, although trained on sample points from a single trajectory, the network is capable of accurate generalization on other, hitherto unseen, trajectories. Building on the effectiveness of short range prediction using neuro-models, we recently proposed an adaptive neuro-genetic control architecture, a hybrid method of adaptive control using neural networks for modelling and genetic algorithms for control [2]. The neuro-genetic control system was demonstrated with reference to the attitude control problem for a rigid body (satellite) equipped with thrusters about each principal axis in the case of large slew angles, unknown dynamic characteristics, and stable and unstable target states.…”

“…In [2], the neuro-genetic control architecture was applied to the adaptive satellite attitude control problem in various cases where no external forces act upon the system (including the case where the system is in a limit cycle). Control of many nonlinear systems poses serious difficulties for conventional control techniques, since most are applicable to linear systems, weakly nonlinear systems, or require various assumptions about the plant dynamics [3,4].…”