Machine learning and evolutionary techniques in interplanetary trajectory design

After providing a brief historical overview on the synergies between artificial intelligence research, in the areas of evolutionary computations and machine learning, and the optimal design of interplanetary trajectories, we propose and study the use of deep artificial neural networks to represent, on-board, the optimal guidance profile of an interplanetary mission. The results, limited to the chosen test case of an Earth–Mars orbital transfer, extend the findings made previously for landing scenarios and quadcopter dynamics, opening a new research area in interplanetary trajectory planning.

[1]  Ilia S. Grigoriev,et al.  Choosing promising sequences of asteroids , 2013, Autom. Remote. Control..

[2]  Dario Izzo,et al.  Machine Learning of Optimal Low-Thrust Transfers Between Near-Earth Objects , 2017, HAIS.

[3]  P. Cage,et al.  Interplanetary trajectory optimization using a genetic algorithm , 1994 .

[4]  Michael Cupples,et al.  Interplanetary Mission Design Using Differential Evolution , 2007 .

[5]  Ping Lu,et al.  Reduced Transversality Conditions in Optimal Space Trajectories , 2013 .

[6]  G. Rauwolf,et al.  Near-optimal low-thrust orbit transfers generated by a genetic algorithm , 1996 .

[7]  Dario Izzo,et al.  Self-Adaptive Genotype-Phenotype Maps: Neural Networks as a Meta-Representation , 2014, PPSN.

[8]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[9]  Ping Lu,et al.  Celebrating Four Decades of Dedication and Excellence , 2018 .

[10]  Martin Schlueter,et al.  MIDACO software performance on interplanetary trajectory benchmarks , 2014 .

[11]  Jianjun Luo,et al.  An improved differential evolution algorithm and its applications to orbit design , 2017 .

[12]  Ruhul A. Sarker,et al.  GA with a new multi-parent crossover for solving IEEE-CEC2011 competition problems , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Dario Izzo,et al.  Constraint Handling and Multi-Objective Methods for the Evolution of Interplanetary Trajectories , 2015 .

[15]  Nikhil Padhye,et al.  Interplanetary trajectory optimization with swing-bys using evolutionary multi-objective optimization , 2007, GECCO '08.

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

[17]  Michèle Lavagna.  Multi-objective pso for interplanetary trajectory design , 2007, GECCO '07.

[18]  Stephen Kemble,et al.  MIDACO on MINLP space applications , 2013 .

[19]  Giuseppe Nicosia,et al.  Design of Robust Space Trajectories , 2011, SGAI Conf..

[20]  Dario Izzo,et al.  Learning the optimal state-feedback using deep networks , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[21]  Dario Izzo,et al.  Fast approximators for optimal low-thrust hops between main belt asteroids , 2016, 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

[22]  Dario Izzo,et al.  Interplanetary Trajectory Planning with Monte Carlo Tree Search , 2015, IJCAI.

[23]  Massimiliano Vasile,et al.  MGA trajectory planning with an ACO-inspired algorithm , 2010, ArXiv.

[24]  Jacob Englander.  Automated trajectory planning for multiple-flyby interplanetary missions , 2013 .

[25]  Dario Izzo,et al.  Evolving Solutions to TSP Variants for Active Space Debris Removal , 2015, GECCO.

[26]  Dario Izzo,et al.  Multi-rendezvous Spacecraft Trajectory Optimization with Beam P-ACO , 2017, EvoCOP.

[27]  Bruce A. Conway,et al.  Particle Swarm Optimization Applied to Space Trajectories , 2010 .

[28]  Edmondo Minisci,et al.  Analysis of Some Global Optimization Algorithms for Space Trajectory Design , 2010 .

[29]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[30]  Anastassios E. Petropoulos,et al.  Increamenting multi-objective evolutionary algorithms: Performance studies and comparisons , 2001 .

[31]  Dario Izzo,et al.  GTOC5: Results from the European Space Agency and University of Florence , 2014 .

[32]  Slawomir J. Nasuto,et al.  Search space pruning and global optimisation of multiple gravity assist spacecraft trajectories , 2007, J. Glob. Optim..

[33]  Ya-zhong Luo,et al.  Simulated annealing for solving near-optimal low-thrust orbit transfer , 2005 .

[34]  Dario Izzo,et al.  Designing Complex Interplanetary Trajectories for the Global Trajectory Optimization Competitions , 2015, 1511.00821.

[35]  Dario Izzo,et al.  Spacecraft Trajectory Optimization: Global Optimization and Space Pruning for Spacecraft Trajectory Design , 2010 .

[36]  Daniel Dueri,et al.  Customized Real-Time Interior-Point Methods for Onboard Powered-Descent Guidance , 2017 .

[37]  Gianmarco Radice,et al.  Ant Colony Algorithms for Two-Impulse Interplanetary Trajectory Optimization , 2006 .

[38]  Dario Izzo,et al.  Real-time optimal control via Deep Neural Networks: study on landing problems , 2016, ArXiv.

[39]  Bernardetta Addis,et al.  A global optimization method for the design of space trajectories , 2011, Comput. Optim. Appl..

[40]  Ossama Abdelkhalik,et al.  Hidden Genes Genetic Algorithm for Multi-Gravity-Assist Trajectories Optimization , 2011 .

[41]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[42]  D. Izzo,et al.  Global Optimisation Heuristics and Test Problems for Preliminary Spacecraft Trajectory Design , 2009 .

[43]  John Mark Bishop,et al.  Advanced global optimisation for mission analysis and design , 2004 .

[44]  Andreas Ohndorf,et al.  Global Optimization of Continuous-Thrust Trajectories Using Evolutionary Neurocontrol , 2019, Springer Optimization and Its Applications.

[45]  Marco Sciandrone,et al.  Machine learning for global optimization , 2010, Computational Optimization and Applications.

[46]  Ponnuthurai N. Suganthan,et al.  An Adaptive Differential Evolution Algorithm With Novel Mutation and Crossover Strategies for Global Numerical Optimization , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[47]  Dario Izzo,et al.  Search for a grand tour of the jupiter galilean moons , 2013, GECCO '13.

[48]  L. S. Pontryagin,et al.  Mathematical Theory of Optimal Processes , 1962 .

[49]  Christos Ampatzis,et al.  Machine Learning Techniques for Approximation of Objective Functions in Trajectory Optimisation , 2009 .

[50]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[51]  E. Blum,et al.  The Mathematical Theory of Optimal Processes. , 1963 .

[52]  Dario Izzo,et al.  Autonomous spacecraft landing through human pre-attentive vision , 2012, Bioinspiration & biomimetics.

[53]  Dario Izzo,et al.  REAL-TIME LANDING BASED ON OPTIMALITY PRINCIPLES AND VISION , 2012 .

[54]  G. Radice,et al.  Advanced Global Optimisation Tools for Mission Analysis and Design , 2004 .

[55]  Lorenzo Casalino,et al.  Enhanced Continuous Tabu Search in a Hybrid Evolutionary Algorithm for the Optimization of Interplanetary Trajectories , 2009 .

[56]  Robin G. J. Biesbroek,et al.  Optimization of Launcher Performance and Interplanetary Trajectories for Pre-Asessment Studies , 2002 .