Machine learning system and method for orbital trajectory planning

1. An orbital trajectory planning system, comprising:

a first computer processor environment configured to preprocess data for providing to a physics-based n-body simulation model, the first computer processor environment including a graphical user interface (GUI) for receiving input from a user;

a second computer processor environment running at least partially trained neural network software that has been trained to perform nonlinear mapping of the output of the n-body simulation model to a result related to a proposed trajectory for a spacecraft, the second computer processor environment receiving input information from the first computer processor environment; and

a third computer processor environment configured to receive data related to the output from the neural network of the second computer processor environment, the third computer processor environment providing user useable output through a GUI running on the third computer processor environment.

2. The orbital trajectory planning system of claim 1 , wherein the first and third computer processor environments are running on the same computer.

3. The orbital trajectory planning system of claim 1 , wherein the first, second, and third computer processor environments are running on the same computer.

4. The orbital trajectory planning system of claim 1 , wherein the second computer processor environment may run one or more of more than one configuration of neural network software.

5. The orbital trajectory planning system of claim 1 , wherein the neural network software comprises a multilayer perceptron network.

6. The orbital trajectory planning system of claim 1 , wherein the neural network software comprises a reinforcement learning neural network.

7. The orbital trajectory planning system of claim 1 , wherein the neural network is trained based on trajectory data from a real-world measurement data.

8. The orbital trajectory planning system of claim 1 , wherein the neural network is trained based on a reward function that includes mean distance to a target error.

9. The orbital trajectory planning system of claim 1 , wherein the neural network is trained based on percentage of completion of objectives within a specified time period.

10. The orbital trajectory planning system of claim 1 , wherein he inputs to the neural network include position, velocity vectors of the spacecraft relative to target objects.

11. The orbital trajectory planning system of claim 1 , wherein the inputs to the neural network include additional factors of perturbation.

12. The orbital trajectory planning system of claim 1 , wherein the neural network output includes parameters related to a recommended trajectory of the spacecraft.

13. The orbital trajectory planning system of claim 1 , wherein the preprocessing includes at least simulating spacecraft flight trajectories.

14. A method of planning an orbital trajectory for a spacecraft, comprising:

receiving input from a user through a graphical user interface (GUI) running on a first computer environment;

preprocessing data, by the first computer processor environment;

receiving input information, by a second computer processor environment, from the first computer processor environment;

running at least partially trained neural network software, by a second computer processor environment, that has been trained to perform nonlinear mapping of the output of an n-body simulation model to a result related to a proposed trajectory for a spacecraft;

receiving data, by a third computer processor environment, the data being related to the output from the neural network of the second computer processor environment; and

providing post processing, by a third computer processor environment, the post processing based on inputs received from a user through a GUI running on the third computer processor environment.

15. The method of claim 14 , wherein the first and third computer processor environments are running on the same computer.

16. The method of claim 14 , wherein the first, second, and third computer processor environments are running on the same computer.

17. The method of claim 14 , wherein the second computer processor environment may run one or more of more than one configuration of neural network software.

18. The method of claim 14 , wherein the neural network software comprises a multilayer perceptron network.

19. The method of claim 14 , wherein the neural network software comprises a reinforcement learning neural network.

20. The method of claim 14 , wherein the neural network is trained based on trajectory data from a real-world measurement data.

21. A system of planning an orbital trajectory for a spacecraft, comprising:

a means for receiving input from a user through a graphical user interface (GUI) running on a first computer environment;

a means for preprocessing data, b the first computer processor environment;

a means for receiving input information, by a second computer processor environment, from the first computer processor environment;

a means for running at least partially trained neural network software, by a second computer processor environment, that has been trained to perform nonlinear mapping of the output of an n-body simulation model to a result related to a proposed trajectory for a spacecraft;

a means for receiving data, by a third computer processor environment, the data being related to the output from the neural network of the second computer processor environment; and

a means for providing post processing, by a third computer processor environment, the post processing based on inputs received from a user through a GUI running on the third computer processor environment.