Article

MiTaS multi-resolution tactile imitation learning framework for contact-rich manipulation tasks

MiTaS is a multi-resolution tactile representation framework that uses modality-specific convolutional stems and a Transformer-based fusion structure to integrate information from an RGB camera, a GelSight Mini vision-based tactile sensor, and a high-frequency event-based Evetac sensor, then conditions a flow-matching policy to perform downstream tasks.

Part of the event: MiTaS multi-resolution tactile framework achieves 80% success rate on five manipulation tasks

This page provides a summary and source link only.