GAN-Based Fine-Tuning of Vibrotactile Signals to Render Material Surfaces

Abstract

The design productivity of fine-tuning for vibrotactile stimuli becomes important as consumer devices equipped with vibrotactile actuators will become widespread. The fine-tuned vibrotactile stimuli output by vibrotactile actuators allows the end-users to feel the surface of the virtual material. However, there is no suitable tool for fine-tuning while there are existing tools suitable for initial designing. In this paper, we test whether we can use GAN (Generative Adversarial Network)-based vibrotactile signal generator at the tuning phase. The generator provides a material-level interface to designers. Designers can define any intermediate materials among pre-defined 108 materials and obtain corresponding intermediate signals that the generator generates. We showed the applicability of the generator to the fine-tuning of vibrotactile signals from the viewpoints of principal component analysis and a user test. INDEX TERMS Human computer interaction, design tools, haptic interfaces.

A multimodal multitask deep learning framework for vibrotactile feedback and sound rendering

“…Hassan et al 30 presented the concept of Haptic Authoring, which involves the creation of novel virtual textures through the interpolation of pre-existing texture models, guided by their correlation with descriptive affective attributes. Vibrotactile signals are produced using Generative Adversarial Network (GAN) in 11 . Nai et al 3 proposed a rendering approach that involves identifying a representative waveform segment from the recorded acceleration signal.…”

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.…”