Article

Context-Aware Generation and Modulation of Expressive Motion Behavior Using Multimodal Foundation Models

This research proposes a method to automatically generate and modulate complex full-body expressive gesture sequences from multimodal context descriptions spanning text, audio, and video. It implements the principles of animation in a unified way based on Dynamic Movement Primitives (DMP) and uses multimodal foundation models to generate highly context-aware parametric motion variants.

Part of the event: Multimodal foundation models generate expressive robot motions

This page provides a summary and source link only.