Addressing catastrophic forgetting in payload parameter identification using incremental ensemble learning

被引:0
|
作者
Taie, Wael [1 ]
El Geneidy, Khaled [2 ]
Al-Yacoub, Ali [3 ]
Sun, Ronglei [1 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Mech Sci & Engn, State Key Lab Intelligent Mfg Equipment & Technol, Wuhan, Peoples R China
[2] Coventry Univ, Sch Engn, Cairo, Egypt
[3] Loughborough Univ, Intelligent Automat Ctr, Loughborough, England
来源
FRONTIERS IN ROBOTICS AND AI | 2024年 / 11卷
基金
中国国家自然科学基金;
关键词
collaborative robots; payload dynamics identification; incremental learning; ensemble learning; catastrophic forgetting;
D O I
10.3389/frobt.2024.1470163
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Collaborative robots (cobots) are increasingly integrated into Industry 4.0 dynamic manufacturing environments that require frequent system reconfiguration due to changes in cobot paths and payloads. This necessitates fast methods for identifying payload inertial parameters to compensate the cobot controller and ensure precise and safe operation. Our prior work used Incremental Ensemble Model (IEM) to identify payload parameters, eliminating the need for an excitation path and thus removing the separate identification step. However, this approach suffers from catastrophic forgetting. This paper introduces a novel incremental ensemble learning method that addresses the problem of catastrophic forgetting by adding a new weak learner to the ensemble model for each new training bag. Moreover, it proposes a new classification model that assists the ensemble model in identifying which weak learner provides the most accurate estimation for new input data. The proposed method incrementally updates the identification model while the cobot navigates any task path, maintaining accuracy on old weak learner even after updating with new data. Validation performed on the Franka Emika cobot showcases the model's superior accuracy and adaptability, effectively eliminating the problem of catastrophic forgetting.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Identification of Walker Identity Using Smartphone Sensors: An Experiment Using Ensemble Learning
    Angrisano, Antonio
    Bernardi, Mario Luca
    Cimitile, Marta
    Gaglione, Salvatore
    Vultaggio, Mario
    IEEE ACCESS, 2020, 8 : 27435 - 27447
  • [42] A Data-Driven Approach for Lithology Identification Based on Parameter-Optimized Ensemble Learning
    Sun, Zhixue
    Jiang, Baosheng
    Li, Xiangling
    Li, Jikang
    Xiao, Kang
    ENERGIES, 2020, 13 (15)
  • [43] An Online Parameter Identification for Ultracapacitor Model by Using Recursive Least Square with Multi-forgetting Factor
    Bao, Jiayi
    Liu, Jianfeng
    Huang, Zhiwu
    Liu, Weirong
    Li, Heng
    2018 13TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2018, : 962 - 966
  • [44] Nonlinear Multi-model Ensemble Prediction Using Dynamic Neural Network with Incremental Learning
    Siek, Michael
    Solomatine, Dimitri
    2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 2873 - 2880
  • [45] Using Incremental Ensemble Learning Techniques to Design Portable Intrusion Detection for Computationally Constraint Systems
    Agbedanu, Promise R.
    Musabe, Richard
    Rwigema, James
    Gatare, Ignace
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (11) : 33 - 45
  • [46] Identification of radioactive isotopes in decommissioning of nuclear facilities using ensemble learning
    Park, Jaehyun
    Song, Gyohyeok
    Kim, Wonku
    Kim, Junhyeok
    Hwang, Jisung
    Kim, Hyunduk
    Cho, Gyuseong
    RADIATION PHYSICS AND CHEMISTRY, 2024, 220
  • [47] A method for automatic identification and separation of wildlife images using ensemble learning
    Meng, De-Yao
    Li, Tao
    Li, Hao-Xuan
    Zhang, Mei
    Tan, Kun
    Huang, Zhi-Pang
    Li, Na
    Wu, Rong-Hai
    Li, Xiao-Wei
    Chen, Ben-Hui
    Ren, Guo-Peng
    Xiao, Wen
    Yang, Deng-Qi
    ECOLOGICAL INFORMATICS, 2023, 77
  • [48] Identification of Civil Infrastructure Damage Using Ensemble Transfer Learning Model
    Ebenezer, A. Shamila
    Kanmani, S. Deepa
    Sheela, V
    Ramalakshmi, K.
    Chandran, V
    Sumithra, M. G.
    Elakkiya, B.
    Murugesan, Bharani
    ADVANCES IN CIVIL ENGINEERING, 2021, 2021
  • [49] Subsurface Natural Fracture Identification Using an Integrated Ensemble Learning Method
    Lu, Guoqing
    Zeng, Lianbo
    Liu, Guoping
    Chen, Xiaoxuan
    Ostadhassan, Mehdi
    Du, Xiaoyu
    Chen, Yangkang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [50] Task-based parameter isolation for foreground segmentation without catastrophic forgetting using multi-scale region and edges fusion network
    Osman, Islam
    Eltantawy, Agwad
    Shehata, Mohamed S.
    IMAGE AND VISION COMPUTING, 2021, 113