An Overview of Data-Driven Paradigms for Identification and Control of Robotic Systems

被引:0
|
作者
Sah, Chandan Kumar [1 ]
Singh, Rajpal [1 ]
Keshavan, Jishnu [1 ]
机构
[1] Indian Inst Sci, Dept Mat Engn, CV Raman Rd, Bengaluru 560012, Karnataka, India
关键词
Data-driven; Machine learning; Robotic systems; Manipulators; Soft robots; Mobile robots; DYNAMIC-MODE DECOMPOSITION; SMALL MOBILE ROBOTS; GAUSSIAN PROCESS; KOOPMAN OPERATOR; SPARSE IDENTIFICATION; SPECTRAL-ANALYSIS; REGRESSION; APPROXIMATION; COMPUTATION; NAVIGATION;
D O I
10.1007/s41745-025-00464-w
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Fueled by the ever-growing availability of large-scale datasets and cutting-edge machine learning advances, data-driven approaches are revolutionizing the design, identification, and control of nonlinear robotic systems. This review paper examines this transformative paradigm, focusing on studies that utilize data-driven techniques involving the Koopman operator-theoretic framework, recurrent neural networks, and the Gaussian process regression for modeling and control of robotic systems. In particular, this study undertakes a review of these state-of-the-art data-driven methods, which have delivered significant performance improvement over a large class of robotic systems, including rigid manipulators, soft robots, and quadrotor aerial systems. The challenges, opportunities, and future directions across this dynamic landscape of data-driven robotics are also explored in this study with an emphasis on the interdisciplinary nature of this rapidly evolving field.
引用
收藏
页数:34
相关论文
共 50 条
  • [1] Data-driven identification and control based on optic tracking feedback for robotic systems
    Josué Gómez
    Chidentree Treesatayapun
    América Morales
    The International Journal of Advanced Manufacturing Technology, 2021, 113 : 1485 - 1503
  • [2] Data-driven identification and control based on optic tracking feedback for robotic systems
    Gomez, Josue
    Treesatayapun, Chidentree
    Morales, America
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2021, 113 (5-6): : 1485 - 1503
  • [3] Local Koopman Operators for Data-Driven Control of Robotic Systems
    Mamakoukas, Giorgos
    Castano, Maria
    Tan, Xiaobo
    Murphey, Todd
    ROBOTICS: SCIENCE AND SYSTEMS XV, 2019,
  • [4] Data-Driven Control: Overview and Perspectives
    Tang, Wentao
    Daoutidis, Prodromos
    2022 AMERICAN CONTROL CONFERENCE, ACC, 2022, : 1048 - 1064
  • [5] Causality in Control Systems Based on Data-Driven Oscillation Identification
    Falkowski, Michal J.
    Domanski, Pawel D.
    Pawluszewicz, Ewa
    APPLIED SCIENCES-BASEL, 2022, 12 (08):
  • [6] On Equivalence of Data Informativity for Identification and Data-Driven Control of Partially Observable Systems
    Sadamoto, Tomonori
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (07) : 4289 - 4296
  • [7] Online Data-Driven Fault Detection for Robotic Systems
    Golombek, Raphael
    Wrede, Sebastian
    Hanheide, Marc
    Heckmann, Martin
    2011 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, 2011, : 3011 - 3016
  • [8] Data-Driven Control Design by Prediction Error Identification for Multivariable Systems
    Huff, Daniel D.
    Campestrini, Luciola
    Goncalves da Silva, Gustavo R.
    Bazanella, Alexandre S.
    JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS, 2019, 30 (04) : 465 - 478
  • [9] Data-Driven Control Design by Prediction Error Identification for Multivariable Systems
    Daniel D. Huff
    Luciola Campestrini
    Gustavo R. Gonçalves da Silva
    Alexandre S. Bazanella
    Journal of Control, Automation and Electrical Systems, 2019, 30 : 465 - 478
  • [10] A Data-driven Motion Control Approach for a Robotic Fish
    Ren, Qinyuan
    Xu, Jianxin
    Li, Xuefang
    JOURNAL OF BIONIC ENGINEERING, 2015, 12 (03) : 382 - 394