A neurooptimal approach for thrustinsensitive trajectory planning

Purpose The purpose of this paper is to devise a new approach to synthesize closedloop feedback guidance law for online thrustinsensitive optimal trajectory generation utilizing neural networks. Designmethodologyapproach The proposed methodology utilizes an openloop variational formulation that initially determines optimal launchascent trajectories for various scenarios of known uncertainties in the thrust profile of typical solid propellant engines. These openloop optimized trajectories will then provide the knowledge base needed for the subsequent training of a neural network. The trained network could eventually produce thrustinsensitive closedloop optimal guidance laws and trajectories in flight. Findings The proposed neurooptimal guidance scheme is effective for online closedloop optimal path planning through some measurable and computable engine and flight parameters. Originalityvalue Determination of closedloop optimal guidance law for nonlinear dynamic systems with uncertainties in system and environment has been a challenge for researchers and engineers for many years. The problem of steering a solid propellant driven vehicle is one of these challenges. Even though a few researchers have worked in the area of nonlinear optimal control and thrustinsensitive guidance, this paper proposes a new strategy for the determination of closedloop online thrust insensitive guidance laws leading to optimal flight trajectories for solid propellant launch and ascent vehicles.