HACo: Learning Haptic Active Compliance for Force-Aware Dexterous Manipulation

2026-09-28

AI Summary

This study addresses the challenges of force perception and multi-contact load regulation in dexterous manipulation. To this end, it proposes the HACo strategy, which integrates fingertip tactile sensing with joint torque measurements to achieve closed-loop active compliance control. Specifically, a compliant grounding module is designed to facilitate supervised learning of force-regulation actions without requiring explicit online contact modeling. Furthermore, a gated tactile cross-attention mechanism is introduced to efficiently align cross-modal features, complemented by a compliant teleoperation pipeline for data generation. Real-world benchmark evaluations demonstrate that the proposed approach achieves an average success rate of 83%, significantly outperforming existing baseline methods.

Abstract

Contact-rich dexterous manipulation requires policies that translate physical feedback into motion commands while regulating interaction loads across evolving multi-contact interactions. This requires haptic observations of contact state and action supervision showing how commands should adapt. Existing policies often overlook complementary fingertip tactile and joint-torque feedback, while common action targets either encode excessive loading or omit motion constrained by the object. We introduce HACo, a Haptic Active Compliance policy that learns force-regulating actions directly from haptic feedback. Compliance-regulated teleoperation converts operator inputs into controller-executable compliant actions that preserve motion intent while regulating loads. HACo learns these actions directly, using command-state discrepancy as auxiliary compliant-intent supervision. It combines local fingertip tactile responses with joint-torque feedback capturing load transmission through the articulated hand, including contacts beyond tactile coverage. A Compliance Grounding Module uses gated haptic cross-attention to ground action generation in the evolving haptic state, enabling closed-loop force regulation without explicit online contact modeling. We evaluate HACo on a real-world benchmark covering multi-contact friction, tangential interaction, fragile curved-surface contact, rotational torque, and deformable-object manipulation. Across 20 trials per task, HACo achieves an 83% mean success rate, compared with 35% for the strongest evaluated baseline. These results demonstrate active compliance across diverse force-sensitive dexterous manipulation tasks.

Problem

• dexterous manipulation
• haptic feedback
• force regulation
• active compliance
• multi-contact interaction

Innovation

• Haptic Active Compliance
• Dexterous Manipulation
• Gated Haptic Cross-Attention
• Compliance-regulated Teleoperation
• Force Regulation