ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914357573582848 |
|---|---|
| author | Yang, Fan Jing, Peiguang Qu, Kaihua Zhao, Ningyuan Su, Yuting |
| author_facet | Yang, Fan Jing, Peiguang Qu, Kaihua Zhao, Ningyuan Su, Yuting |
| contents | Robotic manipulation requires policies that are smooth and responsive to evolving observations. However, synchronous inference in the raw action space introduces several challenges, including intra-chunk jitter, inter-chunk discontinuities, and stop-and-go execution. These issues undermine a policy's smoothness and its responsiveness to environmental changes. We propose ABPolicy, an asynchronous flow-matching policy that operates in a B-spline control-point action space. First, the B-spline representation ensures intra-chunk smoothness. Second, we introduce bidirectional action prediction coupled with refitting optimization to enforce inter-chunk continuity. Finally, by leveraging asynchronous inference, ABPolicy delivers real-time, continuous updates. We evaluate ABPolicy across seven tasks encompassing both static settings and dynamic settings with moving objects. Empirical results indicate that ABPolicy reduces trajectory jerk, leading to smoother motion and improved performance. Project website: https://teee000.github.io/ABPolicy/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23901 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation Yang, Fan Jing, Peiguang Qu, Kaihua Zhao, Ningyuan Su, Yuting Robotics Computer Vision and Pattern Recognition Robotic manipulation requires policies that are smooth and responsive to evolving observations. However, synchronous inference in the raw action space introduces several challenges, including intra-chunk jitter, inter-chunk discontinuities, and stop-and-go execution. These issues undermine a policy's smoothness and its responsiveness to environmental changes. We propose ABPolicy, an asynchronous flow-matching policy that operates in a B-spline control-point action space. First, the B-spline representation ensures intra-chunk smoothness. Second, we introduce bidirectional action prediction coupled with refitting optimization to enforce inter-chunk continuity. Finally, by leveraging asynchronous inference, ABPolicy delivers real-time, continuous updates. We evaluate ABPolicy across seven tasks encompassing both static settings and dynamic settings with moving objects. Empirical results indicate that ABPolicy reduces trajectory jerk, leading to smoother motion and improved performance. Project website: https://teee000.github.io/ABPolicy/. |
| title | ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23901 |