# OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation

arXiv: https://arxiv.org/abs/2503.21257 · HTML: https://mlsanity.com/paper/2503.21257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Real-world robot offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 21 of its 22 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Placed in

- Offline RL and imitation learning from data / [Real-world robot offline RL](https://mlsanity.com/offlinerl/real-world-robot-offline-rl/)

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

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [HumanPlus: Humanoid Shadowing and Imitation from Humans](https://mlsanity.com/paper/2406.10454/) (2024)
- [ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation](https://mlsanity.com/paper/2403.08321/) (2024)
- [RMT: Retentive Networks Meet Vision Transformers](https://mlsanity.com/paper/2309.11523/) (2023)
- [SA-Net: Shuffle Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2102.00240/) (2021)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [Channel prior convolutional attention for medical image segmentation](https://mlsanity.com/paper/2306.05196/) (2023)
- [ELA: Efficient Local Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2403.01123/) (2024)

## Abstract (arXiv)

With the rapid development of embodied intelligence, leveraging large-scale human data for high-level imitation learning on humanoid robots has become a focal point of interest in both academia and industry. However, applying humanoid robots to precision operation domains remains challenging due to the complexities they face in perception and control processes, the long-standing physical differences in morphology and actuation mechanisms between humanoid robots and humans, and the lack of task-relevant features obtained from egocentric vision. To address the issue of covariate shift in imitation learning, this paper proposes an imitation learning algorithm tailored for humanoid robots. By focusing on the primary task objectives, filtering out background information, and incorporating channel feature fusion with spatial attention mechanisms, the proposed algorithm suppresses environmental disturbances and utilizes a dynamic weight update strategy to significantly improve the success rate of humanoid robots in accomplishing target tasks. Experimental results demonstrate that the proposed method exhibits robustness and scalability across various typical task scenarios, providing new ideas and approaches for autonomous learning and control in humanoid robots. The project will be open-sourced on GitHub.