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

2026-03-11

AI Summary

This work addresses the challenge of directly applying human motion data to humanoid robot control due to mismatches in kinematics and dynamics. To overcome this, the authors propose a two-stage framework: first, human motions are mapped onto a URDF skeleton aligned with the target robot’s morphology; second, a three-phase progressive dynamic trajectory optimization—comprising kinematic refinement, inverse dynamics, and full dynamics optimization—is employed to generate natural and physically feasible reference trajectories. By replacing heuristic task-space adjustments with explicit structural alignment and incorporating a staged warm-start strategy, the method substantially reduces inverse kinematics errors and enhances dynamic consistency. Experiments demonstrate that the framework efficiently produces high-quality state and torque references across diverse humanoid platforms, effectively supporting the training of learning-based controllers.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

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.

Problem

• humanoid robots
• motion retargeting
• kinodynamic optimization
• trajectory generation
• human motion transfer

Innovation

• skeleton-parameter alignment
• kinodynamic trajectory optimization
• humanoid motion retargeting
• URDF-based representation
• progressive optimization