This database was created for GTOC 11. The database stores randomly generated time optimal low thrust trajectories. The trajectories are from the asteroids provided in GTOC 11 to a random ‘Dyson Ring’ station. This database was used to train Deep Neural Network models as surrogate of conventional time optimal optimization process. It take ephemerides and output optimal low thrust transfer time directly without performing actual optimization process.
This database stores low-thrust roundtrip missions to NEAs. The generation of this database used our advanced deep learning low-thrust transfer cost approximation technique, which replace the conventional optimization process. The estimation of low thrust transfer cost is as fast as solving a Lambert problem. The search process is based on grid search.
This database stores randomly generated low-thrust(LT) trajectories between NEAs. This database can be used for training interesting machine learning models. For example, using both feasible LT samples and infeasible samples to build a DNN classification model to distinguish LT transfer feasibilities. This database is valuable – obtaining such database requires hundreds of thousands of cores hours of high-performance computing system.
This database stores nearly two billion impulsive round-trip trajectories to near Earth asteroids. This database enables numerical approach for mission analysis. The visualization of this database can be found on http://www.traplan.xyz/data.html. You may find an insecure icon on your chrome browser, this because the website is under development and I haven’t purchase a https certificate. Please simply ignore that. Please allow some minutes for the database to load.
