Modality Selection and Skill Segmentation via Cross-Modality Attention
This work addresses the curse of dimensionality in robotics for multi-modal sensory integration, though it appears incremental as it builds on existing attention-based methods.
The paper tackles the challenge of incorporating multiple sensory modalities into robotic models by proposing a cross-modality attention mechanism for modality selection and skill segmentation, enabling a hierarchical policy to solve long-horizon, contact-rich manipulation tasks.
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.