Generative Adversarial Networks for Localized Vibrotactile Feedback in Haptic Surfaces

Abstract

Touch-screens are the most relevant interface in the context of human-computer interaction. Moreover, they are widely used as interaction means for digital musical instruments, where a complex action-perception loop is involved in the user experience. This is why reestablishing a rich vibrotactile feedback is of key importance for improving the quality of the user's interaction. To the knowledge of the authors, this paper presents the first experiments with Generative Adversarial Networks (GANs) to generate time-reversed signals that can be used to create localized vibrotactile feedback over a rigid surface. The generated signals are sent into an experimental setup and a vibration scan is carried out. A localized peak generated with a signal synthesized by the trained GAN model is observed and studied. Later, different metrics are proposed to evaluate the quality of the generated samples and the obtained localized peak. Finally, a preliminary evaluation of the feasibility of this approach to generate localized vibrations in the range of 200 -300 Hz for touch-screen applications is discussed.

Conditional Generative Adversarial Network-Based Tactile Stimulus Generation for Ultrasonic Tactile Display

“…This study considers the conversion from tactile sensation to display input, and focuses on conditional generative adversarial networks (CGANs) [16], [17], which are a type of generative adversarial network (GAN) [18], [19], as the conversion method. In fact, several studies applying GAN to tactile technology have been conducted in recent years [20], [21], [22], [23]. These studies indicate the effectiveness of using GANs to generate input signals for tactile displays.…”

Modeling and Experimental Evaluation of Haptic Localization Using Electrostatic Vibration Actuators

“…The inverse filter method produces localized vibrotactile feedback using a finite number of piezo actuators in the human vibrotactile range [23]. Localized vibrations in the 200-300 Hz range are reported to be achieved using a generalized adversarial network (GAN) to generate time-reversed signals [24]. Superimposition of vibration modes can also lead to localized vibrotactile feedback on large touch surfaces [25], [26].…”