在空间机器人抓捕目标的过程中，整个系统的惯性张量会随时间变化且在目标被捕获瞬间发生突变，这会严重影响整体姿态控制的精度。针对以上问题，提出了一种基于长短期记忆（LSTM）的系统惯性张量在轨实时辨识方法。首先，对于目标捕获前后的2个阶段，利用拉格朗日方程建立了空间机器人的动力学模型；然后，基于所建空间机器人模型采用域随机化方法生成足量训练数据，并用其对由LSTM网络与多层全连接网络构建的参数辨识网络进行训练；最后，使用训练好的参数辨识网络对系统惯性张量进行辨识。数值仿真结果表明：所提方法能够精确辨识空间机器人抓捕过程中的系统惯性张量，所研究系统的主惯量平均相对辨识误差小于0.001，惯性积的平均相对辨识误差小于0.01。
The system inertia tensor of the space robot is time-varying in the process of an out-of-control target capture and even undergoes abrupt changes at the moment of capture, seriously affecting the accuracy of its overall attitude control. To address the above problem, we propose an on-orbit real-time identification method for the system inertia tensor based on Long-Short Term Memory (LSTM). According to the two stages of pre-capture and post-capture, the dynamic model of the space robot is firstly developed using the Lagrangian equation. Based on the proposed model, the domain randomization method is then adopted to generate sufficient training data to train the parameter identification network constructed by an LSTM network and a multilayer fully connected network. Finally, the trained parameter identification network is used to identify the system inertia tensor. The test results demonstrate that the proposed method can accurately identify the system inertia tensor during the capture process of the space robot. The average relative identification error of the main moment of inertia is less than 0.001, and that of the product of inertia less than 0.01.
[1] FLORES-ABAD A, MA O, PHAM K, et al. A review of space robotics technologies for on-orbit servicing[J]. Progress in Aerospace Sciences, 2014, 68:1-26.
[2] MENG Q L, LIANG J X, MA O. Identification of all the inertial parameters of a non-cooperative object in orbit[J]. Aerospace Science and Technology, 2019, 91:571-582.
[3] BIONDI G, MAURO S, MOHTAR T, et al. Attitude recovery from feature tracking for estimating angular rate of non-cooperative spacecraft[J]. Mechanical Systems and Signal Processing, 2017, 83:321-336.
[4] MUROTSU Y, SENDA K, OZAKI M, et al. Parameter identification of unknown object handled by free-flying space robot[J]. Journal of Guidance, Control, and Dynamics, 1994, 17(3):488-494.
[5] 王明, 黄攀峰, 常海涛, 等. 基于机械臂运动的组合航天器惯性参数在轨辨识[J]. 西北工业大学学报, 2014, 32(5):811-816. WANG M, HUANG P F, CHANG H T, et al. On-orbit identification of inertia parameters of compound spacecraft using space manipulator[J]. Journal of Northwestern Polytechnical University, 2014, 32(5):811-816(in Chinese).
[6] 侯振东, 王兆魁, 张育林. 基于推力器的组合航天器质量特性辨识方法研究[J]. 航天控制, 2015, 33(1):54-60. HOU Z D, WANG Z K, ZHANG Y L. Research on identification of mass characteristics for spacecraft combination based on thrusters[J]. Aerospace Control, 2015, 33(1):54-60(in Chinese).
[7] 张博, 梁斌, 王学谦, 等. 基于自适应反作用零空间控制的大型非合作目标动力学参数实时辨识仿真[J]. 机器人, 2016, 38(1):98-106. ZHANG B, LIANG B, WANG X Q, et al. Simulation of real-time dynamic parameter identification for large non-cooperative targets using adaptive reaction null space control[J]. Robot, 2016, 38(1):98-106(in Chinese).
[8] CHU Z Y, MA Y, HOU Y Y, et al. Inertial parameter identification using contact force information for an unknown object captured by a space manipulator[J]. Acta Astronautica, 2017, 131:69-82.
[9] XU W F, HU Z H, ZHANG Y, et al. On-orbit identifying the inertia parameters of space robotic systems using simple equivalent dynamics[J]. Acta Astronautica, 2017, 132:131-142.
[10] PUNJANI A, ABBEEL P. Deep learning helicopter dynamics models[C]//2015 IEEE International Conference on Robotics and Automation (ICRA). Piscataway:IEEE Press, 2015:3223-3230.
[11] AULI M, GALLEY M, QUIRK C, et al. Joint language and translation modeling with recurrent neural networks[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:Association for Computational Linguistics, 2013, 3:1044-1054.
[12] LIU Y H, WANG H L, SU Z K, et al. Deep learning based trajectory optimization for UAV aerial refueling docking under bow wave[J]. Aerospace Science and Technology, 2018, 80:392-402.
[13] ZHAO R, YAN R Q, WANG J J, et al. Learning to monitor machine health with convolutional bi-directional LSTM networks[J]. Sensors, 2017, 17(2):273.
[14] DONG Y Q. An application of Deep Neural Networks to the in-flight parameter identification for detection and characterization of aircraft icing[J]. Aerospace Science and Technology, 2018, 77:34-49.
[15] 魏晓良, 潮群, 陶建峰, 等. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021, 42(3):423876. WEI X L, CHAO Q, TAO J F, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(3):423876(in Chinese).
[16] YU W H, TAN J, LIU C K, et al. Preparing for the unknown:Learning a universal policy with online system identification[DB/OL]. arXiv preprint:1702.02453, 2017.
[17] TOBIN J, FONG R, RAY A, et al. Domain randomization for transferring deep neural networks from simulation to the real world[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway:IEEE Press, 2017:23-30.
[18] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[J]. Journal of Machine Learning Research, 2011, 15:315-323.
[19] HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//2015 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2015:1026-1034.
[20] KINGMA D, BA J. Adam:a method for stochastic optimization[DB/OL]. arXiv preprint:1412.6980, 2014.
[21] CHAI R Q, TSOURDOS A, SAVVARIS A, et al. Real-time reentry trajectory planning of hypersonic vehicles:A two-step strategy incorporating fuzzy multiobjective transcription and deep neural network[J]. IEEE Transactions on Industrial Electronics, 2020, 67(8):6904-6915.
CJA