A Method for Quantifying a Robot’s Confidence in its Human Co-worker in Human-Robot Cooperative Grit-Blasting

Konferenz: ISR 2018 - 50th International Symposium on Robotics
20.06.2018 - 21.06.2016 in München, Germany

Tagungsband: ISR 2018

Seiten: 8Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Tran, Antony; Liu, Dikai; Ranasinghe, Ravindra; Carmichael, Marc (Center for Autonomous Systems, University of Technology Sydney, Ultimo, 2007, NSW, Australia)

Inhalt:
In cooperative Human-Robot operations with physical contact, the human is generally in control while the robot assists the human. However, if the performance of the human were to decrease due to factors such as fatigue or distractions, there should be a mechanism that allows the robot to measure the performance of human operator and intervene in the interaction if needed. This becomes more important in physical Human-Robot Interactions such as cooperative grit-blasting, as the safety of the human may be affected if their performance decreases. In this work, a method for measuring the confidence of a robot in its human operator is presented. This method is then verified in a Human-Robot cooperative grit-blasting operation.