Interplanetary Trajectory Planning with Monte Carlo Tree Search

Planning an interplanetary trajectory is a very complex task, traditionally accomplished by domain experts using computer-aided design tools. Recent advances in trajectory optimization allow automation of part of the trajectory design but have yet to provide an efficient way to select promising planetary encounter sequences. In this work, we present a heuristic-free approach to automated trajectory planning (including the encounter sequence planning) based on Monte Carlo Tree Search (MCTS). We discuss a number of modifications to traditional MCTS unique to the domain of interplanetary trajectory planning and provide results on the Rosetta and Cassini-Huygens interplanetary mission design problems. The resulting heuristic-free method is found to be orders of magnitude more efficient with respect to a standard tree search with heuristic-based pruning which is the current state-of-the art in this domain.

[1]  Nathan J. Strange,et al.  Automated Design of the Europa Orbiter Tour , 2002 .

[2]  James M. Longuski,et al.  V8 Leveraging for Interplanetary Missions: Multiple-Revolution Orbit Techniques , 1997 .

[3]  D. Izzo.  Revisiting Lambert’s problem , 2014, 1403.2705.

[4]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

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

[6]  Pieter Spronck,et al.  Monte-Carlo Tree Search: A New Framework for Game AI , 2008, AIIDE.

[7]  Ashish Sabharwal,et al.  Guiding Combinatorial Optimization with UCT , 2012, CPAIOR.

[8]  H. Jaap van den Herik,et al.  Improving multivariate Horner schemes with Monte Carlo tree search , 2012, Comput. Phys. Commun..

[9]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[10]  James M. Longuski,et al.  Automated design of gravity-assist trajectories to Mars and the outer planets , 1991 .

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

[12]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[13]  Kalyanmoy Deb,et al.  Interplanetary Trajectory Optimization with Swing-Bys Using Evolutionary Multi-objective Optimization , 2007, ISICA.

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

[15]  Anastassios E. Petropoulos,et al.  Trajectories to Jupiter via Gravity Assists from Venus, Earth, and Mars , 1998 .

[16]  H. Jaap van den Herik,et al.  Single-Player Monte-Carlo Tree Search , 2008, Computers and Games.

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

[18]  H. Jaap van den Herik,et al.  Investigations with Monte Carlo Tree Search for Finding Better Multivariate Horner Schemes , 2013, ICAART.

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

[20]  Anne Auger,et al.  Performance evaluation of an advanced local search evolutionary algorithm , 2005, 2005 IEEE Congress on Evolutionary Computation.