Time optimal low-thrust rendezvous from an asteroid belt
DOI10.5281/zenodo.6365326Zenodo6365326MaRDI QIDQ6696070FDOQ6696070
Dataset published at Zenodo repository.
Publication date: 14 March 2022
Copyright license: Creative Commons Attribution 4.0 International
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 biastowards 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=5022642.890912783sThe 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/2203.15490where we were more interested on the effects/use of the data augmentation technique called "Backward Generation of Optimal Examples" than on theaccuracy 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 alsoprovide 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)
This page was built for dataset: Time optimal low-thrust rendezvous from an asteroid belt
