Modality Selection and Skill Segmentation via Cross-Modality Attention
Year: 2025
Type: preprint
Abstract: Incorporating additional sensory modalities such as tactile and audio into foundational robotic models poses significant challenges due to the curse of dimensionality. This work addresses this issue through modality selection. We propose a cross-modality attention (CMA) mechanism to identify and selectively utilize the modalities that are most informative for action generation at each timestep. Furthermore, we extend the application of CMA to segment primitive skills from expert demonstrations and leverage this segmentation to train a hierarchical policy capable of solving long-horizon, contact-rich manipulation tasks.
Source: arXiv (Cornell University)
Authors: Jiang, Jiawei, Ota, Kei, Jha, Devesh K., Kanezaki, Asako
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6947979703
Cites:
Cited by:
Related to: