Exploring the Relation Between Stiffness Perception and Action Using Models and Artificial Neural Networks

Abstract

AbstractApplying artificial skin stretch with force feedback increases perceived stiffness and affects grip force. We explored if participants’ perceptual responses in a stiffness discrimination task could be predicted solely from their action signals using models and artificial neural networks. Successful prediction could indicate a relation between participants’ perception and action. We found that the skin stretch perceptual augmentation could be predicted to an extent from action signals alone. We predicted the general trend of increased predicted augmentation for increased real augmentation, and average augmentation effect across participants, but not the precise effect sizes of individual participants. This indicates some relation between participants’ perceptual reports and action signals, enabling the partial prediction. Furthermore, of the action signals examined, grip force was necessary for predicting the augmentation effect, and a motion signal (e.g., position) was needed for predicting human-like perception, shedding light on what information may be present in the different signals.