FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks

2025-09-21

AI Summary

To address insufficient force control accuracy and the high cost of external force sensors in contact-rich manipulation tasks (e.g., insertion, assembly), this paper proposes a dual-loop force-guided imitation learning framework. The inner loop enables sensorless end-effector contact force estimation via joint torque observation and a digital twin model; the outer loop employs a Transformer-based policy that fuses visual and proprioceptive inputs, coupled with analytic Jacobian-inverse-based torque impedance control for compliant execution. Our key innovation lies in the first integration of digital twin compensation into sensorless force estimation, and the principled coupling of imitation learning with physics-driven impedance control. Experiments demonstrate significant improvements in safety, compliance, and task adaptability over vision-only or joint-torque-only baselines, successfully achieving high-precision peg-in-hole and assembly tasks.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: Manipulation
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Contact-rich manipulation is crucial for robots to perform tasks requiring precise force control, such as insertion, assembly, and in-hand manipulation. However, most imitation learning (IL) policies remain position-centric and lack explicit force awareness, and adding force/torque sensors to collaborative robot arms is often costly and requires additional hardware design. To overcome these issues, we propose FILIC, a Force-guided Imitation Learning framework with impedance torque control. FILIC integrates a Transformer-based IL policy with an impedance controller in a dual-loop structure, enabling compliant force-informed, force-executed manipulation. For robots without force/torque sensors, we introduce a cost-effective end-effector force estimator using joint torque measurements through analytical Jacobian-based inversion while compensating with model-predicted torques from a digital twin. We also design complementary force feedback frameworks via handheld haptics and VR visualization to improve demonstration quality. Experiments show that FILIC significantly outperforms vision-only and joint-torque-based methods, achieving safer, more compliant, and adaptable contact-rich manipulation. Our code can be found in https://github.com/TATP-233/FILIC.

Problem

• Addresses position-centric imitation learning lacking force awareness
• Solves costly force sensor requirement for collaborative robot arms
• Enables compliant force-informed manipulation without force/torque sensors

Innovation

• Dual-loop structure integrating Transformer policy with impedance control
• Jacobian-based force estimation using joint torque measurements
• Complementary force feedback via haptic and VR interfaces