Kinematics-informed neural network control on SO(3)☆

作     者：Reis, Joel Silvestre, Carlos 

作者机构：Univ Macau Fac Sci & Technol Taipa Macao Peoples R China Univ Lisbon Inst Syst & Robot Inst Super Tecn P-1049001 Lisbon Portugal 

出 版 物：《AUTOMATICA》 (Automatica)

年 卷 期：2025年第174卷

核心收录：

学科分类：0711[理学-系统科学] 0808[工学-电气工程] 07[理学] 08[工学] 070105[理学-运筹学与控制论] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 0701[理学-数学] 071101[理学-系统理论] 

基　　金：Macao Science and Technology Development Fund [FDCT/0192/2023/RIA3, FDCT/0059/2024/RIA1] University of Macau, Macau, China [MYRG2022-00205-FST, MYRG-GRG2023-00107-FST-UMDF, SRG2024-00012-FST] LARSyS FCT, Portugal 

主　　题：Attitude control systems Neural networks Machine learning control Special orthogonal group 

摘      要：This paper presents an adaptive geometric control method for dynamic-model-free attitude tracking on the manifold of 3D rotations (SO(3)). Utilizing well-established definitions of attitude errors on SO(3), we develop a general control-affine linear error system. The input to this system is implicitly approximated by a kinematics-informed neural network (NN), which serves as the controller. The weights of this NN, designed to be inherently bounded, are adjusted online using a modified gradient- descent strategy that relies solely on system kinematics. We demonstrate the effectiveness and online learning capability of our proposed method through comprehensive simulation results, using a satellite attitude control system as an example. A comparative analysis is also provided to validate our approach. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.