cs.RONov 14, 2026

ImpedanceMimic: Learned Impedance as Action Space for Force-Accurate Motion Imitation

Authors: Matthias Jammot, Pembe Gizem Özdil

Organizations: Harvard University · Kempner Institute for the Study of Natural and Artificial Intelligence

Abstract

Recovering the forces behind a motion is ill-posed: different controllers can reproduce the same movement while generating different contact forces. Physics-based motion imitation resolves this ambiguity through simulation, but relies on fixed-gain proportional-derivative (PD) control. We show that fixed gains impose a trade-off between motion and force tracking, as contact and swing place conflicting demands on joint stiffness and damping. We introduce ImpedanceMimic, a reinforcement-learning policy that modulates per-joint stiffness, damping, and position setpoints from motion and force measurements, but requires only motion at inference. Across 129 participants and six activities, ImpedanceMimic outperforms matched fixed-gain PD under every integration scheme, direct-torque, muscle-actuated and existing imitation controllers in kinematic and force fidelity, approaching a dedicated motion-to-force regressor. By expressing gains as multiples of inertia-scaled priors, a single policy controls subject-specific biomechanical models without explicit anthropometric input and transfers zero-shot to unseen humans and a humanoid robot. The learned impedance forms a low-dimensional representation of motor state, shared across bodies, that generalizes to withheld activities: stiffness scales with load, and damping anticipates unloading.

Figures & tables

Explore similar work

CardsList
  1. Impedance Cloning: Learning Equilibrium Point Parameters for Contact-Rich Manipulation

    Sep 25, 2026Hayato Takahashi, Ryoga Oishi, Yuki Kasuga +1Contact-Rich Robotic ManipulationForce-Controlled Robotic Manipulation

  2. Continuous Manifold-Decomposed Impedance Retargeting for Contact-Rich Imitation Learning

    Sep 14, 2026Jiahao Liu, Kento Kawaharazuka, Tasuku Makabe +1Impedance ControlForce-Controlled Robotic Manipulation

  3. Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale

    Mar 26, 2026Chengkun Li, Cheryl Wang, Bianca Ziliotto +4Musculoskeletal ModelingHuman-to-Robot Motion Imitation