The feasibility criterion of fuel-optimal planetary landing using neural networks

Abstract This paper focuses on the feasibility criterion of fuel-optimal powered landing problems. Due to the uncertainties during landing on the surface of the planet, the initial states of the powered descent and landing phase may be placed in an infeasible region. Clarifying the feasibility criterion of the fuel-optimal problem is critical to ensure the convergence of the powered landing guidance algorithm. According to Pontryagin's maximum principle, the fuel-optimal conditions for the powered landing problem and its inverse problem are derived. By analyzing the inverse problem, a data generation strategy is proposed to generate sample trajectories. Deep neural networks are used to fit the parameter correlation and construct the feasibility criterion. Numerical simulations are presented to evaluate the effectiveness of the proposed deep-neural-network-based feasibility criterion and further illustrate the feasible regions of specific scenarios.

[1]  Francesco Topputo,et al.  Neural Networks in Time-Optimal Low-Thrust Interplanetary Transfers , 2019, IEEE Access.

[2]  Naigang Cui,et al.  A Pseudospectral-Convex Optimization Algorithm for Rocket Landing Guidance , 2018 .

[3]  Ping Lu,et al.  The State of the Journal Is Strong , 2017 .

[4]  Hongyu Zhou,et al.  Glide guidance for reusable launch vehicles using analytical dynamics , 2020 .

[5]  Youmin Gong,et al.  Mars entry guidance for mid-lift-to-drag ratio vehicle with control constraints , 2020 .

[6]  Christophe Talbot,et al.  Overview of some optimal control methods adapted to expendable and reusable launch vehicle trajectories , 2006 .

[7]  Xinfu Liu.  Fuel-Optimal Rocket Landing with Aerodynamic Controls , 2017, Journal of Guidance, Control, and Dynamics.

[8]  Andrew E. Johnson,et al.  ADAPT demonstrations of onboard large-divert Guidance with a VTVL rocket , 2014, 2014 IEEE Aerospace Conference.

[9]  Yu Song,et al.  Solar-Sail Trajectory Design of Multiple Near Earth Asteroids Exploration Based on Deep Neural Network , 2019, Aerospace Science and Technology.

[10]  Joel Benito,et al.  Reachable and Controllable Sets for Planetary Entry and Landing , 2010 .

[11]  Dario Izzo,et al.  Learning the optimal state-feedback via supervised imitation learning , 2019, Astrodynamics.

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

[13]  Nazim Kemal Ure,et al.  Autolanding control system design with deep learning based fault estimation , 2020 .

[14]  Lin Cheng,et al.  Real-time control for fuel-optimal Moon landing based on an interactive deep reinforcement learning algorithm , 2019, Astrodynamics.

[15]  Xiuqiang Jiang,et al.  RBF neural network based second-order sliding mode guidance for Mars entry under uncertainties , 2015 .

[16]  Ping Lu,et al.  Propellant-Optimal Powered Descent Guidance , 2017 .

[17]  Chen Hu,et al.  Neural network based online predictive guidance for high lifting vehicles , 2018, Aerospace Science and Technology.

[18]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[19]  Dario Izzo,et al.  Machine learning and evolutionary techniques in interplanetary trajectory design , 2018, Springer Optimization and Its Applications.

[20]  J. Betts.  Survey of Numerical Methods for Trajectory Optimization , 1998 .

[21]  Yu Song,et al.  Real-time optimal control for irregular asteroid landings using deep neural networks , 2019, Acta Astronautica.

[22]  W. Chen,et al.  Conjugate gradient method with pseudospectral collocation scheme for optimal rocket landing guidance , 2020 .

[23]  Wei Kang,et al.  Pseudospectral Feedback Control: Foundations, Examples and Experimental Results , 2006 .

[24]  Behçet Açikmese,et al.  Constrained Reachability and Controllability Sets for Planetary Precision Landing via Convex Optimization , 2015 .

[25]  Pedro Simplício,et al.  A Reusable Launcher Benchmark with Advanced Recovery Guidance , 2019 .

[26]  Lin Ma,et al.  Multi-point powered descent guidance based on optimal sensitivity , 2019, Aerospace Science and Technology.

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

[28]  Dario Izzo,et al.  A survey on artificial intelligence trends in spacecraft guidance dynamics and control , 2018, Astrodynamics.

[29]  Marco Sagliano,et al.  Survey of autonomous guidance methods for powered planetary landing , 2020, Frontiers of Information Technology & Electronic Engineering.

[30]  Shengping Gong,et al.  Adaptive powered descent guidance based on multi-phase pseudospectral convex optimization , 2021 .

[31]  Behcet Acikmese,et al.  Convex programming approach to powered descent guidance for mars landing , 2007 .

[32]  Carlo Novara,et al.  GNC robustness stability verification for an autonomous lander , 2020 .

[33]  Jun Hu,et al.  An approach and landing guidance design for reusable launch vehicle based on adaptive predictor–corrector technique , 2018 .

[34]  Behcet Acikmese,et al.  Lossless convexification of Powered-Descent Guidance with non-convex thrust bound and pointing constraints , 2011, Proceedings of the 2011 American Control Conference.

[35]  John L. Crassidis,et al.  Design and optimization of navigation and guidance techniques for Mars pinpoint landing: Review and prospect , 2017 .

[36]  Anil V. Rao,et al.  Algorithm 902: GPOPS, A MATLAB software for solving multiple-phase optimal control problems using the gauss pseudospectral method , 2010, TOMS.

[37]  Ting Tao,et al.  Computational guidance for planetary powered descent using collaborative optimization , 2018 .