Search papers, labs, and topics across Lattice.
This paper introduces SPARK, a two-stage pipeline for retargeting human motion data onto humanoid robots to generate dynamically feasible motion references. The method first converts human motion into a URDF-based skeleton representation and calibrates it to the target robot's dimensions, reducing inverse kinematics error. Then, it refines the retargeted trajectories using a three-stage progressive kinodynamic trajectory optimization (TO) approach.
Achieve natural and dynamically feasible humanoid robot motion by retargeting human motion data with a skeleton-aligned approach, significantly reducing inverse kinematics error compared to task-space methods.
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.