Dynamic Whole-Body Dancing with Humanoid Robots -- A Model-Based Control Approach

TL;DR

This paper introduces a model-based control framework enabling humanoid robots to perform dynamic whole-body dance motions through offline planning and online real-time control, validated on Kuavo 4Pro robots.

Contribution

The paper presents a novel integrated framework combining motion capture, retargeting, trajectory optimization, and model predictive control for dynamic dance motions in humanoid robots.

Findings

Longer prediction horizons enhance motion expressiveness.

The framework achieves stable real-time execution in live performances.

Demonstrated successful dance motions on Kuavo 4Pro robots in simulation and live show.

Abstract

This paper presents an integrated model-based framework for generating and executing dynamic whole-body dance motions on humanoid robots. The framework operates in two stages: offline motion generation and online motion execution, both leveraging future state prediction to enable robust and dynamic dance motions in real-world environments. In the offline motion generation stage, human dance demonstrations are captured via a motion capture (MoCap) system, retargeted to the robot by solving a Quadratic Programming (QP) problem, and further refined using Trajectory Optimization (TO) to ensure dynamic feasibility. In the online motion execution stage, a centroidal dynamics-based Model Predictive Control (MPC) framework tracks the planned motions in real time and proactively adjusts swing foot placement to adapt to real world disturbances. We validate our framework on the full-size humanoid robot Kuavo 4Pro, demonstrating the dynamic dance motions both in simulation and in a four-minute live public performance with a team of four robots. Experimental results show that longer prediction horizons improve both motion expressiveness in planning and stability in execution.