F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911586494447616 |
|---|---|
| author | Wei, Haoyu Xu, Xiuwei Cheng, Ziyang Yin, Hang Ma, Angyuan Yu, Bingyao Zhou, Jie Lu, Jiwen |
| author_facet | Wei, Haoyu Xu, Xiuwei Cheng, Ziyang Yin, Hang Ma, Angyuan Yu, Bingyao Zhou, Jie Lu, Jiwen |
| contents | Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency causes generated actions to inevitably lag behind the real-time environment. This issue is particularly exacerbated in dynamic scenarios, where such temporal misalignment severely compromises the policy's ability to interpret and react to rapidly evolving surroundings. In this paper, we propose a novel framework that leverages predicted object flow to synthesize future observations, incorporating a flow-based contrastive learning objective to align the visual feature representations of predicted observations with ground-truth future states. Empowered by this anticipated visual context, our asynchronous policy gains the capacity for proactive planning and motion, enabling it to explicitly compensate for latency and robustly execute manipulation tasks involving actively moving objects. Experimental results demonstrate that our approach significantly enhances responsiveness and success rates in complex dynamic manipulation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02408 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation Wei, Haoyu Xu, Xiuwei Cheng, Ziyang Yin, Hang Ma, Angyuan Yu, Bingyao Zhou, Jie Lu, Jiwen Robotics Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency causes generated actions to inevitably lag behind the real-time environment. This issue is particularly exacerbated in dynamic scenarios, where such temporal misalignment severely compromises the policy's ability to interpret and react to rapidly evolving surroundings. In this paper, we propose a novel framework that leverages predicted object flow to synthesize future observations, incorporating a flow-based contrastive learning objective to align the visual feature representations of predicted observations with ground-truth future states. Empowered by this anticipated visual context, our asynchronous policy gains the capacity for proactive planning and motion, enabling it to explicitly compensate for latency and robustly execute manipulation tasks involving actively moving objects. Experimental results demonstrate that our approach significantly enhances responsiveness and success rates in complex dynamic manipulation tasks. |
| title | F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.02408 |