🤖 AI Summary
Virtual interactions lack tactile feedback for material textures, limiting realism in VR and gaming.
Method: This paper proposes a user-guided vibrotactile synthesis method enabling intuitive, real-time control of high-dimensional vibration parameters. We integrate differential subspace search (DSS) with generative adversarial networks (GANs) to construct a user-centric vibration generation framework, allowing single-slider manipulation of high-dimensional latent spaces. Additionally, we establish the first quantitative correlation model linking human perceptual discriminability between real and synthesized vibrations.
Contributions/Results: Trained on an open haptic dataset and validated via human-in-the-loop experiments, our system generates five distinguishable texture-specific vibration signals. User studies confirm that synthesized vibrations preserve target texture features with high fidelity; discrimination accuracy for generated samples strongly correlates with that for real stimuli (p < 0.01), demonstrating the method’s effectiveness and practicality in enhancing tactile realism for VR and interactive applications.
📝 Abstract
Vibration rendering is essential for creating realistic tactile experiences in human-virtual object interactions, such as in video game controllers and VR devices. By dynamically adjusting vibration parameters based on user actions, these systems can convey spatial features and contribute to texture representation. However, generating arbitrary vibrations to replicate real-world material textures is challenging due to the large parameter space. This study proposes a human-in-the-loop vibration generation model based on user preferences. To enable users to easily control the generation of vibration samples with large parameter spaces, we introduced an optimization model based on Differential Subspace Search (DSS) and Generative Adversarial Network (GAN). With DSS, users can employ a one-dimensional slider to easily modify the high-dimensional latent space to ensure that the GAN can generate desired vibrations. We trained the generative model using an open dataset of tactile vibration data and selected five types of vibrations as target samples for the generation experiment. Extensive user experiments were conducted using the generated and real samples. The results indicated that our system could generate distinguishable samples that matched the target characteristics. Moreover, we established a correlation between subjects' ability to distinguish real samples and their ability to distinguish generated samples.