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

2026-09-25

AI Summary

This study addresses the failure of force control in contact-rich manipulation caused by geometric deviations during trajectory imitation learning. Rather than cloning kinematic trajectories, this work proposes encoding task intent as impedance parameters. Through bilateral teleoperation and particle filtering, biomechanical priors such as stiffness and equilibrium points are extracted without force sensors, while parameter learning is implemented using ILBiT integrated with a Mamba architecture. By leveraging passive compliance to absorb contact uncertainties, the method achieves cross-geometric generalization on a CRANE-X7 manipulator from a single demonstration. Experimental results demonstrate stable contact forces during wiping tasks and an 84% grasping success rate, significantly outperforming fixed-impedance baselines.

Abstract

Contact-rich manipulation requires robots to regulate force against surfaces whose geometry deviates unpredictably from training conditions. Trajectory-based imitation learning, which reproduces observable outputs, breaks down under such shifts. We propose Impedance Cloning, which instead imitates the biomechanical priors that generate motion -- the stiffness and equilibrium point -- and thereby passively absorbs contact uncertainty. Because these parameters encode intent rather than outcome, they generalize across surface geometries where trajectory reproduction does not. We extract them from bilateral teleoperation demonstrations via a particle filter without force/torque sensors and evaluate the framework on two CRANE-X7 manipulators. In a wiping task with joint-space actions, the trajectory-based baseline loses contact below -6 cm, whereas the proposed method maintains a consistent 4-5 N contact force above -6 cm, with a gradual decrease below; with Cartesian-space actions, its force-height slope over 0 to +8 cm is 0.13 +/- 0.03 N/cm, versus 0.34-0.83 N/cm for fixed-impedance baselines. In a pick-and-place task with 10 diverse cups (100 trials), the proposed method succeeds in 84 trials, outperforming the fixed-impedance baseline (74/100) and performing comparably to a variable impedance control baseline (82/100) with one demonstration instead of ten. In a grasping task, the representation reduces torque tracking error with both ILBiT and Mamba backbones, confirming its generality across architectures.

Problem

• contact-rich manipulation
• imitation learning
• force regulation
• generalization

Innovation

• Impedance Cloning
• Equilibrium Point
• Imitation Learning
• Contact-Rich Manipulation
• Particle Filter