Imp-ACT: Adaptive Impedance Control and Action Chunking with Transformers to Learn Contact-Rich Manipulation from Demonstrations

2026-09-25

AI Summary

This study addresses the challenge of balancing precise tracking with compliant interaction in vision-action policies for contact-rich manipulation, proposing the Imp-ACT method. Imp-ACT integrates direction-dependent stiffness modulation into demonstration collection by dynamically adjusting stiffness along motion directions via a self-tuning impedance controller during teleoperation. Building upon the ACT architecture, it fuses visual, proprioceptive, and torque observations for end-to-end learning, enabling a Transformer to jointly predict poses, actions, and adaptive stiffness. Experimental results demonstrate that Imp-ACT eliminates the need for manual stiffness selection or offline trajectory reconstruction. In wiping tasks, contact force oscillations are reduced by approximately 29-fold, while orthogonal forces during peg insertion decrease by 43%. The method effectively constrains interaction forces while maintaining high task success rates.

Abstract

Contact-rich manipulation requires robots to balance accurate motion tracking with compliant interaction, yet most visual-action policies leave compliance fixed at the controller level. We present Imp-ACT, a methodologically grounded and practical approach to incorporating direction-dependent Cartesian stiffness modulation directly into demonstration collection, without manual stiffness selection or offline target reconstruction. During teleoperation, a self-tuning impedance controller adapts stiffness along the instantaneous direction of motion while maintaining compliance in orthogonal directions. The adapted stiffness is applied and recorded alongside visual observations and motion commands, capturing motion and compliance under the same dynamics. We implement this pipeline using Action Chunking with Transformer (ACT) to predict end-effector pose, gripper action, and motion-direction stiffness from visual, proprioceptive, and wrench observations. The performance of Imp-ACT is evaluated on wiping and plug insertion using both success rate and quantitative measures of contact behavior. Compared with fixed low- and high-stiffness baselines, Imp-ACT achieves comparable or higher success while maintaining low interaction forces. In wiping, it reduces contact-force vibration by approximately $29\times$ relative to the compliant baseline and $180\times$ relative to the stiff baseline. In plug insertion, it reduces forces orthogonal to the insertion direction by $43\%$ relative to the better fixed-stiffness baseline. These results highlight the benefit of maintaining sufficient stiffness along the direction needed for task execution while preserving compliance in other directions to limit contact forces and accommodate environmental constraints.

Problem

• contact-rich manipulation
• impedance control
• stiffness modulation
• compliant interaction
• learning from demonstrations

Innovation

• Adaptive Impedance Control
• Action Chunking with Transformers
• Contact-Rich Manipulation
• Cartesian Stiffness Modulation
• Learning from Demonstrations