Neural networks algorithms for ornithopter trajectory optimization

Trajectory optimization has recently been addressed to compute energy-efficient routes for ornithopter navigation, but its online application remains a challenge. To overcome the high computation time of traditional approaches, this paper proposes algorithms that recursively generate trajectories based on the output of neural networks. To this end, we create a novel data set composed by energy-efficient trajectories obtained by running a competitive planner. We present two methods to compute low-cost trajectories: a classification approach to learn maneuvers and an alternative regression method that predicts new states. Both approaches are tested in several scenarios, including the landing case. The effectiveness and efficiency of the proposed algorithms are demonstrated through simulation, which show that neural networks can be used to compute the flight path of the ornithopter in real time.