Optimizing low-thrust gravity assist interplanetary trajectories using evolutionary neurocontrollers

The combination of low-thrust propulsion and gravity assists allows designing high-energy missions. However the optimization of such trajectories is no trivial task. In this paper, we present a novel method that is based on evolutionary neurocontrollers. The main advantage of using a neurocontroller is the generation of a control law with a limited number of decision variables. On the other hand the evolutionary algorithm allows to look for globally optimal solutions more efficiently than a systematic search. In addition, a steepest ascent algorithm is introduced that acts as a navigator during the planetary encounter, providing the neurocontroller with the optimal insertion parameters. Results are presented for a Mercury rendezvous with a Venus gravity assist and for a Pluto flyby with a Jupiter gravity assist.