SPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization

TL;DR

This paper introduces a two-stage pipeline that converts human motion into natural, dynamically feasible trajectories for humanoid robots by skeleton calibration and kinodynamic trajectory optimization, improving motion reference quality.

Contribution

The novel approach aligns skeleton structures and applies progressive kinodynamic optimization to generate high-quality motion references for diverse humanoid robots.

Findings

Reduces inverse kinematics error significantly

Produces physically consistent motion trajectories

Enhances motion reference quality for learning controllers

Abstract

Human motion provides rich priors for training general-purpose humanoid control policies, but raw demonstrations are often incompatible with a robot's kinematics and dynamics, limiting their direct use. We present a two-stage pipeline for generating natural and dynamically feasible motion references from task-space human data. First, we convert human motion into a unified robot description format (URDF)-based skeleton representation and calibrate it to the target humanoid's dimensions. By aligning the underlying skeleton structure rather than heuristically modifying task-space targets, this step significantly reduces inverse kinematics error and tuning effort. Second, we refine the retargeted trajectories through progressive kinodynamic trajectory optimization (TO), solved in three stages: kinematic TO, inverse dynamics, and full kinodynamic TO, each warm-started from the previous solution. The final result yields dynamically consistent state trajectories and joint torque profiles, providing high-quality references for learning-based controllers. Together, skeleton calibration and kinodynamic TO enable the generation of natural, physically consistent motion references across diverse humanoid platforms.