Fault-tolerant Learning

Fault-Tolerant Learning is a learning framework in safe robot learning that, unlike standard learning approaches, ensures continued performance and convergence in the presence of hardware failures, software errors, or unmodeled environmental disruptions by explicitly integrating fault detection, adaptation, and robustness mechanisms into the learning process.

192

Publications

8.3K

Citations

518

Authors

235

Institutions

Publications per year

2017–2026

102

Authors

518

  1. CL
    Chi-Sing Leung

    City University of Hong Kong, Hong Kong SAR China

    6 publications · 223 citations

    6

    h-index

  2. FG
    Furong Gao

    Hong Kong University of Science and Technology, Hong Kong SAR China

    5 publications · 351 citations

    5

    h-index

  3. LW
    Limin Wang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    5 publications · 223 citations

    5

    h-index

  4. JX
    Jianping Xuan

    Huazhong University of Science and Technology, China

    4 publications · 158 citations

    4

    h-index

  5. ZG
    Zhiwei Gao

    Northumbria University, United Kingdom

    4 publications · 131 citations

    4

    h-index

1–5 of 518

Venues

  1. 9

    h-index

  2. IEEE Transactions on Neural Networks

    7 publications · 288 citations

    7

    h-index

  3. Neural Networks

    6 publications · 223 citations

    6

    h-index

  4. Journal of Process Control

    5 publications · 285 citations

    5

    h-index

  5. Neurocomputing

    7 publications · 141 citations

    5

    h-index

1–5