Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control

TL;DR

This paper introduces TER-DAgger, a force-aware imitation learning framework that improves contact-rich insertion tasks by reducing covariate shift and minimizing expert intervention through trajectory editing and force-based failure detection.

Contribution

It presents a novel, scalable imitation learning method that combines trajectory editing, force-aware failure anticipation, and impedance control for safer, more efficient contact-rich manipulation.

Findings

TER-DAgger increases success rate by over 37% in real-world tasks.

The approach effectively reduces the need for continuous expert monitoring.

Experimental results validate improved robustness and scalability.

Abstract

Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered by covariate shift and the need for continuous expert monitoring to recover from failures during execution. In this paper, we propose Trajectory Editing Residual Dataset Aggregation (TER-DAgger), a scalable and force-aware human-in-the-loop imitation learning framework that mitigates covariate shift by learning residual policies through optimization-based trajectory editing. This approach smoothly fuses policy rollouts with human corrective trajectories, providing consistent and stable supervision. Second, we introduce a force-aware failure anticipation mechanism that triggers human intervention only when discrepancies arise between predicted and measured end-effector forces, significantly reducing the requirement for continuous expert monitoring. Third, all learned policies are executed within a Cartesian impedance control framework, ensuring compliant and safe behavior during contact-rich interactions. Extensive experiments in both simulation and real-world precision insertion tasks show that TER-DAgger improves the average success rate by over 37\% compared to behavior cloning, human-guided correction, retraining, and fine-tuning baselines, demonstrating its effectiveness in mitigating covariate shift and enabling scalable deployment in contact-rich manipulation.