# Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning

arXiv: https://arxiv.org/abs/2411.03294 · HTML: https://mlsanity.com/paper/2411.03294/

## Key facts

- Cited by 7 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 32 of its 44 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## 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, 30 of 32)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors](https://mlsanity.com/paper/2210.11339/) (2022)
- [Flow as the Cross-Domain Manipulation Interface](https://mlsanity.com/paper/2407.15208/) (2024)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [Learning Dexterous Grasping with Object-Centric Visual Affordances](https://mlsanity.com/paper/2009.01439/) (2020)
- [Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations](https://mlsanity.com/paper/2303.01497/) (2023)
- [On the Generalization Properties of Diffusion Models](https://mlsanity.com/paper/2311.01797/) (2023)
- [Waypoint-Based Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2307.14326/) (2023)
- [Deep Object-Centric Representations for Generalizable Robot Learning](https://mlsanity.com/paper/1708.04225/) (2017)
- [RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning](https://mlsanity.com/paper/2409.14674/) (2024)
- [ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers](https://mlsanity.com/paper/2309.11986/) (2023)
- [K-VIL: Keypoints-based Visual Imitation Learning](https://mlsanity.com/paper/2209.03277/) (2022)
- [An Information-theoretic Approach to Distribution Shifts](https://mlsanity.com/paper/2106.03783/) (2021)
- [Back to the Manifold: Recovering from Out-of-Distribution States](https://mlsanity.com/paper/2207.08673/) (2022)

## Built on by (most cited first, 7 of 7)

- [VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon](https://mlsanity.com/paper/2607.01804/) (2026)
- [Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning](https://mlsanity.com/paper/2510.19495/) (2025)
- [Prepare Before You Act: Learning From Humans to Rearrange Initial States](https://mlsanity.com/paper/2509.18043/) (2025)
- [Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness](https://mlsanity.com/paper/2603.21017/) (2026)
- [Exploration-assisted Bottleneck Transition Toward Robust and Data-efficient Deformable Object Manipulation](https://mlsanity.com/paper/2603.13756/) (2026)
- [Wavelet Policy: Imitation Learning in the Scale Domain with World Prior Memory](https://mlsanity.com/paper/2504.04991/) (2025)
- [Recovering Hidden Reward in Diffusion-Based Policies](https://mlsanity.com/paper/2605.00623/) (2026)

## Abstract (arXiv)

We propose an object-centric recovery (OCR) framework to address the challenges of out-of-distribution (OOD) scenarios in visuomotor policy learning. Previous behavior cloning (BC) methods rely heavily on a large amount of labeled data coverage, failing in unfamiliar spatial states. Without relying on extra data collection, our approach learns a recovery policy constructed by an inverse policy inferred from the object keypoint manifold gradient in the original training data. The recovery policy serves as a simple add-on to any base visuomotor BC policy, agnostic to a specific method, guiding the system back towards the training distribution to ensure task success even in OOD situations. We demonstrate the effectiveness of our object-centric framework in both simulation and real robot experiments, achieving an improvement of 77.7% over the base policy in OOD. Furthermore, we show OCR's capacity to autonomously collect demonstrations for continual learning. Overall, we believe this framework represents a step toward improving the robustness of visuomotor policies in real-world settings.