Attitude-Orbit Coupling Intelligent Control of Flexible Asteroid Lander

Abstract

A method for attitude-orbit coupling intelligent control of flexible lander based on maximum entropy reinforcement learning is proposed in this paper，aiming at solve the adverse effects of the complex perturbation environment and the inaccurate flexible deformation force. Firstly，the orbital dynamics model of the equivalent agent is established by introducing the internal flexible force of the lander. The datum plane method is used to characterize the attitude of the flexible lander with complex deformation. The attitude-orbit coupling dynamic environment of the lander is constructed to train the intelligent controller. Then，an intelligent controller with deep neural network architecture is designed according to the soft actor-critic（SAC）algorithm of maximum entropy reinforcement learning theory. Each thruster can keep the lander attitude stable and track the navigation trajectory with high precision by self-adapting the output thrust. Finally，the landing process with the controller deployed is simulated. The simulation results show that compared with the classic PD control method，the intelligent control method proposed in this paper has stronger robustness.

Keywords

small celestial landing / flexible lander / deep reinforcement learning / attitude-orbit coupling control

References

[1] 崔平远，张成宇，朱圣英，等. 小天体柔性附着技术[J]. 宇航学报，2023，44（6）：805-816.
CUI P Y，ZHANG C Y，ZHU S Y，et al. Technologies for flexible landing on small celestial bodies[J]. Journal of Astronautics，2023，44（6）：805-816.
[2] 崔平远，陆晓萱，朱圣英，等. 小天体柔性附着状态协同估计方法[J]. 宇航学报，2022，43（9）：1219-1226.
CUI P Y，LU X X，ZHU S Y，et al. Cooperative state estimation method for small celestial body flexible landing[J]. Journal of Astronautics，2022，43（9）：1219-1226.
[3] SANDY C. Development of the Mars Pathfinder inflatable airbag subsystem[C]//Proceedings of 14th Aerodynamic Decelerator Systems Technology Conference. Frederica：AIAA，1997.
[4] FURFARO R，CERSOSIMO D，WIBBEN D R. Asteroid precision landing via multiple sliding surfaces guidance techniques[J]. Journal of Guidance，Control，and Dynamics，2013，36（4）：1075-1092.
[5] LAN Q，LI S，YANG J，et al. Finite-time soft landing on asteroids using nonsingular terminal sliding mode control[J]. Transactions of the Institute of Measurement and Control，2013，36（2）：216-223.
[6] LIU X，SHAN Z，LI Y. Dynamic boundary layer based neural network quasi-sliding mode control for soft touching down on asteroid[J]. Advances in Space Research，2017，59（8）：2173-2185.
[7] ZHAI G，LI J，SUN Y Y，et al. Research on asteroid landing with a new flexible spacecraft[J]. Journal of Aerospace Engineering，2022，35（5）.
[8] PHILIP S T，BRUNSKILL E. Policy gradient methods for reinforcement learning with function approximation and action-dependent baselines[EB/OL]. （2017-6-20）[2024-03-31]. https：//arxiv.org/abs/1706.066432000.
[9] MNIH V，KAVUKCUOGLU K，SILVER D，et al. Playing atari with deep reinforcement learning[EB/OL]. （2013-12-19）[2024-03-31]. https：//arxiv.org/abs/1312.5602.
[10] MNIH V， KAVUKCUOGLU V，SILVER D，et al. Human-level control through deep reinforcement learning[J]. Nature，2015，518（7540）：529-533.
[11] HAARNOJA T，ZHOU A，ABBEEL P，et al. Soft actor-critic：off-policy maximum entropy deep reinforcement learning with a stochastic actor[EB/OL]. （2018-1-4）[2024-03-31]. https：//arxiv.org/abs/1801.01290.
[12] 杨来义，毕敬，苑海涛. 基于SAC算法的移动机器人智能路径规划[J]. 系统仿真学报，2023，35（8）：1726-1736.
YANG L Y，BI J，YUAN H T. Intelligent path planning for mobile robots based on SAC algorithm[J]. Journal of System Simulation，2023，35（8）：1726-1736.
[13] 唐腾，任双印，王春江. 基于SAC算法的四旋翼无人机姿态控制[C]//第三十四届中国仿真大会暨第二十一届亚洲仿真会议. 长沙：中国仿真大会，2022.
TANG T，REN S Y，WANG C J. Attitude control of quadrotor UAV based on soft actor critic[C]//Proceedings of China Simulation Federation. The 34th China Simulation Conference and the 21st Asian Simulation Conference. Changsha：China Simulation Federation，2022.
[14] 李波，白双霞，孟波波，等. 基于SAC算法的无人机自主空战决策算[J]. 指挥控制与仿真，2022，44（5）：24-30.
LI B，BAI S X，MENG B B，et al. Autonomous air combat decision-making algorithm of UAVs based on SAC algorithm[J]. Command Control & Simulation，2022，44（5）：24-30.
[15] 郑鹤鸣，翟光，孙一勇. 面向在轨加注的组合体姿态SAC智能控制[J]. 宇航学报，2023，44（7）：1020-1033.
ZHENG H M，ZHAI G，SUN Y Y. SAC intelligent attitude control method for on-orbit refueling combination[J]. Journal of Astronautics，2023，44（7）：1020-1033.
[16] YAN W F，BAOYIN H. Position-attitude coupling guidance and control for asteroid landing with a flexible lander[J]. Aerospace Science and Technology，2023，141：108567.