# ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation

arXiv: https://arxiv.org/abs/2509.20841 · HTML: https://mlsanity.com/paper/2509.20841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [Deep Spatial Autoencoders for Visuomotor Learning](https://mlsanity.com/paper/1509.06113/) (2015)
- [SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion](https://mlsanity.com/paper/2209.03855/) (2022)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching](https://mlsanity.com/paper/1710.01330/) (2017)
- [Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach](https://mlsanity.com/paper/1804.05172/) (2018)
- [Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models](https://mlsanity.com/paper/2404.13013/) (2024)
- [Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge](https://mlsanity.com/paper/1609.09475/) (2016)
- [KETO: Learning Keypoint Representations for Tool Manipulation](https://mlsanity.com/paper/1910.11977/) (2019)
- [OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints](https://mlsanity.com/paper/2501.03841/) (2025)
- [Motion Policy Networks](https://mlsanity.com/paper/2210.12209/) (2022)

## Abstract (arXiv)

End-to-end robot manipulation policies offer significant potential for enabling embodied agents to understand and interact with the world. Unlike traditional modular pipelines, end-to-end learning mitigates key limitations such as information loss between modules and feature misalignment caused by isolated optimization targets. Despite these advantages, existing end-to-end neural networks for robotic manipulation--including those based on large VLM/VLA models--remain insufficiently performant for large-scale practical deployment. In this paper, we take a step towards an end-to-end manipulation policy that is generalizable, accurate and reliable. To achieve this goal, we propose a novel Chain of Moving Oriented Keypoints (CoMOK) formulation for robotic manipulation. Our formulation is used as the action representation of a neural policy, which can be trained in an end-to-end fashion. Such an action representation is general, as it extends the standard end-effector pose action representation and supports a diverse set of manipulation tasks in a unified manner. The oriented keypoint in our method enables natural generalization to objects with different shapes and sizes, while achieving sub-centimeter accuracy. Moreover, our formulation can easily handle multi-stage tasks, multi-modal robot behaviors, and deformable objects. Extensive simulated and hardware experiments demonstrate the effectiveness of our method.