Optimization of very-low-thrust trajectories using evolutionary neurocontrol

Searching optimal interplanetary trajectories for low-thrust spacecraft is usually a difficult and time-consuming task that involves much experience and expert knowledge in astrodynamics and optimal control theory. This is because the convergence behavior of traditional local optimizers, which are based on numerical optimal control methods, depends on an adequate initial guess, which is often hard to find, especially for verylow-thrust trajectories that necessitate many revolutions around the sun. The obtained solutions are typically close to the initial guess that is rarely close to the (unknown) global optimum. Within this paper, trajectory optimization problems are attacked from the perspective of artificial intelligence and machine learning. Inspired by natural archetypes, a smart global method for low-thrust trajectory optimization is proposed that fuses artificial neural networks and evolutionary algorithms into so-called evolutionary neurocontrollers. This novel method runs without an initial guess and does not require the attendance of an expert in astrodynamics and optimal control theory. This paper details how evolutionary neurocontrol works and how it could be implemented. The performance of the method is assessed for three dierent

[1]  Jack Belzer,et al.  Encyclopedia of Computer Science and Technology , 2002 .

[2]  John W. Hartmann,et al.  Optimal multi-objective low-thrust spacecraft trajectories , 2000 .

[3]  Massimiliano Vasile.  A global approach to optimal space trajectory design , 2003 .

[4]  Robert C. Moore,et al.  The MESSENGER mission to Mercury: spacecraft and mission design , 2001 .

[5]  Dimitris C. Dracopoulos,et al.  Evolutionary Learning Algorithms for Neural Adaptive Control , 1997, Perspectives in Neural Computing.

[6]  L. D. Whitley,et al.  Genetic Reinforcement Learning for Neurocontrol Problems , 2004, Machine Learning.

[7]  B Ravindran,et al.  A tutorial survey of reinforcement learning , 1994 .

[8]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[9]  Robert F. Stengel,et al.  Optimal Control and Estimation , 1994 .

[10]  Lampros Tsinas,et al.  A combined neural and genetic learning algorithm , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[11]  John P. W. Stark,et al.  Spacecraft systems engineering , 1995 .

[12]  Wolfgang Seboldt,et al.  Ground-Based Demonstration of Solar Sail Technology , 2000 .

[13]  W. Seboldt,et al.  ENEAS - Exploration of Near-Earth Asteroids with a Sailcraft - Proposal for a Small Satellite Mission with the Space Science Program of Germany , 2000 .

[14]  Bernd Dachwald,et al.  LOW-THRUST TRAJECTORY OPTIMIZATION AND INTERPLANETARY MISSION ANALYSIS USING EVOLUTIONARY NEUROCONTROL , 2004 .