@incollection{BorggrafeOhndorfDachwaldetal.2012,
  author    = {Borggrafe, Andreas and Ohndorf, Andreas and Dachwald, Bernd and Seboldt, Wolfgang},
  title     = {Analysis of interplanetary solar sail trajectories with attitude dynamics},
  series = {Dynamics and Control of Space Systems 2012},
  booktitle = {Dynamics and Control of Space Systems 2012},
  publisher = {Univelt Inc},
  address   = {San Diego},
  isbn      = {978-0-87703-587-9},
  pages     = {1553 -- 1569},
  year      = {2012},
  abstract  = {We present a new approach to the problem of optimal control of solar sails for low-thrust trajectory optimization. The objective was to find the required control torque magnitudes in order to steer a solar sail in interplanetary space. A new steering strategy, controlling the solar sail with generic torques applied about the spacecraft body axes, is integrated into the existing low-thrust trajectory optimization software InTrance. This software combines artificial neural networks and evolutionary algorithms to find steering strategies close to the global optimum without an initial guess. Furthermore, we implement a three rotational degree-of-freedom rigid-body attitude dynamics model to represent the solar sail in space. Two interplanetary transfers to Mars and Neptune are chosen to represent typical future solar sail mission scenarios. The results found with the new steering strategy are compared to the existing reference trajectories without attitude dynamics. The resulting control torques required to accomplish the missions are investigated, as they pose the primary requirements to a real on-board attitude control system.},
  language  = {en}
}
@incollection{DachwaldOhndorf2019,
  author    = {Dachwald, Bernd and Ohndorf, Andreas},
  title     = {Global optimization of continuous-thrust trajectories using evolutionary neurocontrol},
  series = {Modeling and Optimization in Space Engineering},
  booktitle = {Modeling and Optimization in Space Engineering},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-10501-3},
  doi       = {10.1007/978-3-030-10501-3_2},
  pages     = {33 -- 57},
  year      = {2019},
  abstract  = {Searching optimal continuous-thrust trajectories is usually a difficult and time-consuming task. The solution quality of traditional optimal-control methods depends strongly on an adequate initial guess because the solution is typically close to the initial guess, which may be far from the (unknown) global optimum. Evolutionary neurocontrol attacks continuous-thrust optimization problems from the perspective of artificial intelligence and machine learning, combining artificial neural networks and evolutionary algorithms. This chapter describes the method and shows some example results for single- and multi-phase continuous-thrust trajectory optimization problems to assess its performance. Evolutionary neurocontrol can explore the trajectory search space more exhaustively than a human expert can do with traditional optimal-control methods. Especially for difficult problems, it usually finds solutions that are closer to the global optimum. Another fundamental advantage is that continuous-thrust trajectories can be optimized without an initial guess and without expert supervision.},
  language  = {en}
}