# "Touching to See" and "Seeing to Feel": Robotic Cross-modal SensoryData Generation for Visual-Tactile Perception

## TL;DR

This paper introduces a novel cross-modal sensory data generation framework using GANs to enhance visual-tactile perception in robotics, enabling realistic data synthesis and improved perception performance.

## Contribution

It presents a new GAN-based method for generating visual or tactile data from the other modality, improving data augmentation and perception in robotic tasks.

## Key findings

- Generated realistic visual and tactile data confirmed by SSIM scores.
- Inclusion of generated data improves classification accuracy.
- Method effectively expands datasets for perception tasks.

## Abstract

The integration of visual-tactile stimulus is common while humans performing daily tasks. In contrast, using unimodal visual or tactile perception limits the perceivable dimensionality of a subject. However, it remains a challenge to integrate the visual and tactile perception to facilitate robotic tasks. In this paper, we propose a novel framework for the cross-modal sensory data generation for visual and tactile perception. Taking texture perception as an example, we apply conditional generative adversarial networks to generate pseudo visual images or tactile outputs from data of the other modality. Extensive experiments on the ViTac dataset of cloth textures show that the proposed method can produce realistic outputs from other sensory inputs. We adopt the structural similarity index to evaluate similarity of the generated output and real data and results show that realistic data have been generated. Classification evaluation has also been performed to show that the inclusion of generated data can improve the perception performance. The proposed framework has potential to expand datasets for classification tasks, generate sensory outputs that are not easy to access, and also advance integrated visual-tactile perception.