analiza aiqbench
This research presents TER-DAgger, a novel imitation learning framework that enhances robotic precision insertion by integrating force-aware failure anticipation and residual policy optimization. By leveraging Cartesian impedance control to ensure safe contact-rich interactions while reducing the need for continuous human monitoring, the method achieves over 37% higher success rates than standard baselines in both simulation and real-world scenarios. The work addresses critical deployment hurdles like covariate shift through trajectory editing techniques that fuse AI rollouts with expert corrections only when necessary.
Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control
arXiv:2603.04038v3 Announce Type: replace 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.
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.
8 pages, 3 figures. Accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
Robotics (cs.RO)
arXiv:2603.04038 [cs.RO]
(or arXiv:2603.04038v3 [cs.RO] for this version)
Text integral sub licența deschisă a publicației · 203 cuvinte
Subiecte conexe
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · 3 aug. 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
K-VARK: Kernelized Variance-Aware Residual Kalman Filter for Sensorless Force Estimation in Collaborative Robots
arXiv · 17 iun. 2026