# Refinement of Accelerated Demonstrations via Incremental Iterative Reference Learning Control for Fast Contact-Rich Imitation Learning

arXiv: https://arxiv.org/abs/2604.16850 · HTML: https://mlsanity.com/paper/2604.16850/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 21 of 21)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [Dynamic Movement Primitives in Robotics: A Tutorial Survey](https://mlsanity.com/paper/2102.03861/) (2021)
- [Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control](https://mlsanity.com/paper/2410.09309/) (2024)
- [FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning](https://mlsanity.com/paper/2502.17432/) (2025)
- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies](https://mlsanity.com/paper/2506.11948/) (2025)
- [Imitation Learning for Variable Speed Contact Motion for Operation up to Control Bandwidth](https://mlsanity.com/paper/2102.10283/) (2021)
- [Soft and Rigid Object Grasping With Cross-Structure Hand Using Bilateral Control-Based Imitation Learning](https://mlsanity.com/paper/2311.09555/) (2023)
- [Learning Variable Compliance Control From a Few Demonstrations for Bimanual Robot with Haptic Feedback Teleoperation System](https://mlsanity.com/paper/2406.14990/) (2024)
- [DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration](https://mlsanity.com/paper/2506.05064/) (2025)
- [Robotic Compliant Object Prying Using Diffusion Policy Guided by Vision and Force Observations](https://mlsanity.com/paper/2503.03998/) (2025)
- [Real-time Motion Generation and Data Augmentation for Grasping Moving Objects with Dynamic Speed and Position Changes](https://mlsanity.com/paper/2309.12547/) (2023)
- [SliceIt! -- A Dual Simulator Framework for Learning Robot Food Slicing](https://mlsanity.com/paper/2404.02569/) (2024)
- [Soft Robotic Dynamic In-Hand Pen Spinning](https://mlsanity.com/paper/2411.12734/) (2024)
- [Motion ReTouch: Motion Modification Using Four-Channel Bilateral Control](https://mlsanity.com/paper/2502.20982/) (2025)
- [High-speed electrical connector assembly by structured compliance in a finray-effect gripper](https://mlsanity.com/paper/2307.15589/) (2023)
- [Improving Low-Cost Teleoperation: Augmenting GELLO with Force](https://mlsanity.com/paper/2507.13602/) (2025)
- [Input-gated Bilateral Teleoperation: An Easy-to-implement Force Feedback Teleoperation Method for Low-cost Hardware](https://mlsanity.com/paper/2509.08226/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bi-MoDe: Bilateral Control-based Imitation Learning via Modifier-Conditioned Decoding for Modulation of Execution Speed and Contact Intensity](https://mlsanity.com/paper/2609.16040/) (2026)

## Abstract (arXiv)

Fast execution of contact-rich manipulation is critical for practical deployment, yet providing fast demonstrations for imitation learning (IL) remains challenging: humans cannot demonstrate at high speed, and naively accelerating demonstrations alters contact dynamics and induces large tracking errors. We present a method to autonomously refine time-accelerated demonstrations by repurposing Iterative Reference Learning Control (IRLC) to iteratively update the reference trajectory from observed tracking errors. However, applying IRLC directly at high speed tends to produce larger early-iteration errors and less stable transients. To address this issue, we propose Incremental Iterative Reference Learning Control (I2RLC), which gradually increases the speed while updating the reference, yielding high-fidelity trajectories. We validate on real-robot whiteboard erasing and peg-in-hole tasks using a teleoperation setup with a compliance-controlled follower and a 3D-printed haptic leader. Both IRLC and I2RLC achieve up to 10x faster demonstrations with reduced tracking error; moreover, I2RLC improves spatial similarity to the original trajectories by 22.5% on average over IRLC across three tasks and multiple speeds (3x-10x). We then use the refined trajectories to train IL policies; the resulting policies execute faster than the demonstrations and achieve 100% success rates in the peg-in-hole task at both seen and unseen positions, with I2RLC-trained policies exhibiting lower contact forces than those trained on IRLC-refined demonstrations. These results indicate that gradual speed scheduling coupled with reference adaptation provides a practical path to fast, contact-rich IL.