Current as Touch: Proprioceptive Contact Feedback for Compliant Dexterous Manipulation

2026-07-03

AI Summary

This work addresses the challenge of achieving compliant manipulation with low-cost dexterous hands, which often lack affordable and reliable contact-sensing capabilities. The authors propose a novel approach that leverages motor currents and joint states as learnable proprioceptive signals to directly predict compliant reference positions, enabling a standard PD controller to generate appropriate grasping forces without requiring additional tactile or force sensors. This method is compatible with mainstream teleoperation and policy learning frameworks and demonstrates robust compliant grasping across diverse dexterous hands in tasks involving high contact complexity. Experimental results show significant improvements in teleoperation safety and enhanced performance in downstream policy learning.

Abstract

Compliance is essential for dexterous manipulation, yet existing solutions often rely on external tactile or force sensors that are costly, fragile, and difficult to deploy on low-cost robot hands. We propose a proprioception-driven framework that learns contact-aware compliance cues from motor current and joint states. Since motor current is closely related to actuator torque, it provides an intrinsic signal for perceiving contact force, object resistance, and grasp stability without additional sensing hardware. Rather than estimating external wrenches or commanding torque, our method predicts a compliance reference position: an ideal joint-position target for a standard PD controller whose induced position error generates appropriate grasping force. This position-based formulation is compatible with mainstream teleoperation and policy-learning pipelines, while enabling the robot to adapt interaction forces from real-time proprioceptive feedback. Thus, motor current serves not only as a force proxy but also as a learnable proprioceptive contact signal for compliance reference prediction. Experiments on multiple dexterous hands and contact-rich tasks, including fragile object handling, sustained surface contact, thin-object retrieval, and dynamic load adaptation, show stable compliant grasping, safer and more efficient teleoperation, and improved downstream policy learning without external tactile or force sensors.

Problem

• compliance
• dexterous manipulation
• proprioception
• contact feedback
• motor current

Innovation

• proprioceptive feedback
• compliant manipulation
• motor current sensing
• reference position prediction
• dexterous grasping