A Hybrid Intelligent System to Detect Anomalies in Robot Performance

  1. Nuño Basurto 1
  2. Ángel Arroyo 1
  3. Carlos Cambra 1
  4. Álvaro Herrero 1
  1. 1 Universidad de Burgos
    info

    Universidad de Burgos

    Burgos, España

    ROR https://ror.org/049da5t36

Libro:
Hybrid Artificial Intelligent Systems: 16th International Conference, HAIS 2021. Bilbao, Spain. September 22–24, 2021. Proceedings
  1. Hugo Sanjurjo González (coord.)
  2. Iker Pastor López (coord.)
  3. Pablo García Bringas (coord.)
  4. Héctor Quintián (coord.)
  5. Emilio Corchado (coord.)

Editorial: Springer International Publishing AG

ISBN: 978-3-030-86271-8 978-3-030-86270-1

Año de publicación: 2021

Páginas: 415-426

Congreso: Hybrid Artificial Intelligent Systems (HAIS) (16. 2021. Bilbao)

Tipo: Aportación congreso

Resumen

Although self-diagnosis is required for autonomous robots, little effort has been devoted to detect software anomalies in such systems. The present work contributes to this field by applying a Hybrid Artificial Intelligence System (HAIS) to successfully detect these anomalies. The proposed HAIS mainly consists of imputation techniques (to deal with the MV), data balancing methods (in order to overcome the unbalancing of available data), and a classifier (to detect the anomalies). Imputation and balancing techniques are subsequently applied in for improving the classification performance of a well-know classifier: the Support Vector Machine. The proposed framework is validated with an open and recent dataset containing data collected from a robot interacting in a real environment.