Trajectory generation in guided spaces using NTG algorithm and artificial neural networks

Abstract

This paper presents the preliminary results of nonlinear trajectory generation (NTG) using artificial neural networks (ANNs) as analytical data approximators. NTG framework designed at Caltech by Mark Milam et al. (2003) solves constrained nonlinear dynamic optimization problems in real time. A successful application of NTG on real-life problems with sampled data depends upon an accurate approximation scheme. Such an approximator is desired to have a compact architecture, a minimum number of design parameters, and a smooth continuously-differentiable input/output mapping. ANNs as universal approximators are known to possess these features, thus considered here as appropriate candidates for this task. The proposed cooperation of NTG and ANN is illustrated on an optimal control problem of generating realtime low observable trajectories for unmanned air vehicles in the presence of multiple radars.