Hierarchical Intention-Aware Expressive Motion Generation for Humanoid Robots

TL;DR

This paper presents a hierarchical framework combining intention-aware reasoning with diffusion models to generate expressive, socially appropriate humanoid robot motions in real-time, enhancing human-robot interaction.

Contribution

It introduces a novel hierarchical system integrating intention reasoning via in-context learning with diffusion-based motion synthesis for humanoid robots.

Findings

Robust real-time motion generation in dynamic scenarios

High social appropriateness of generated gestures

Effective intention refinement and adaptive responses

Abstract

Effective human-robot interaction requires robots to identify human intentions and generate expressive, socially appropriate motions in real-time. Existing approaches often rely on fixed motion libraries or computationally expensive generative models. We propose a hierarchical framework that combines intention-aware reasoning via in-context learning (ICL) with real-time motion generation using diffusion models. Our system introduces structured prompting with confidence scoring, fallback behaviors, and social context awareness to enable intention refinement and adaptive response. Leveraging large-scale motion datasets and efficient latent-space denoising, the framework generates diverse, physically plausible gestures suitable for dynamic humanoid interactions. Experimental validation on a physical platform demonstrates the robustness and social alignment of our method in realistic scenarios.