Closing the gap: Optimizing Guidance and Control Networks through Neural ODEs

arXiv:2404.16908v1 Announce Type: new
Abstract: We improve the accuracy of Guidance & Control Networks (G&CNETs), trained to represent the optimal control policies of a time-optimal transfer and a mass-optimal landing, respectively. In both cases we leverage the dynamics of the spacecraft, described by Ordinary Differential Equations which incorporate a neural network on their right-hand side (Neural ODEs). Since the neural dynamics is differentiable, the ODEs sensitivities to the network parameters can be computed using the variational equations, thereby allowing to …

abstract accuracy arxiv cases control cs.ai cs.lg cs.ne differential dynamics gap guidance landing networks ordinary policies spacecraft through transfer type