Time optimal low-thrust rendezvous from an asteroid belt

This dataset allows to train regression models representing the optimal time of flight of a constant acceleration low-thrust trajectory aimed at a randezvous with a target orbiting station (placed at 1.3 Astronomical Units). The version 2 of the dataset should be used, correcting a data bias towards simpler transfers present in the previous version. The attributes, X, represent the modified equinoctial parameters (p,f,g,h,k,sin(L), cos(L)) of the spacecraft (SI units) at the start of the transfer. L is the true longitude. Different representations of the initial state are likely key to improving any model. The time of flight, Y, is given in units of TIME=5022642.890912783s The dataset was used for value function learning in our paper: Izzo, D. and Origer, S.: "Neural representation of a time optimal, constant acceleration rendezvous" - https://arxiv.org/abs/2203.15490 where we were more interested on the effects/use of the data augmentation technique called "Backward Generation of Optimal Examples" than on the accuracy of the resulting neural model. A MAE of ~25 days is obtained on the test set, when training from the augmented dataset (vs. ~34.08 days from the non augmented one). Both these numbers can likely be improved considerably, constituting a nice challenge for the community. The python pickles can be opened as: with open("filename.pk", "rb") as f: X, Y = pkl.load(f) else , we also provide the corresponding csv files. * training: contains 3000 items * test: contains ~1000 items * training_augmented_32_0.0001: contains 96000 items (augmented from the 3000 of training)