FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908576500416512 |
|---|---|
| author | Zhong, Yiming Liu, Yumeng Xiao, Chuyang Yang, Zemin Wang, Youzhuo Zhu, Yufei Shi, Ye Sun, Yujing Zhu, Xinge Ma, Yuexin |
| author_facet | Zhong, Yiming Liu, Yumeng Xiao, Chuyang Yang, Zemin Wang, Youzhuo Zhu, Yufei Shi, Ye Sun, Yujing Zhu, Xinge Ma, Yuexin |
| contents | Learning effective visuomotor policies for robotic manipulation is challenging, as it requires generating precise actions while maintaining computational efficiency. Existing methods remain unsatisfactory due to inherent limitations in the essential action representation and the basic network architectures. We observe that representing actions in the frequency domain captures the structured nature of motion more effectively: low-frequency components reflect global movement patterns, while high-frequency components encode fine local details. Additionally, robotic manipulation tasks of varying complexity demand different levels of modeling precision across these frequency bands. Motivated by this, we propose a novel paradigm for visuomotor policy learning that progressively models hierarchical frequency components. To further enhance precision, we introduce continuous latent representations that maintain smoothness and continuity in the action space. Extensive experiments across diverse 2D and 3D robotic manipulation benchmarks demonstrate that our approach outperforms existing methods in both accuracy and efficiency, showcasing the potential of a frequency-domain autoregressive framework with continuous tokens for generalized robotic manipulation.Code is available at https://github.com/4DVLab/Freqpolicy |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01583 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens Zhong, Yiming Liu, Yumeng Xiao, Chuyang Yang, Zemin Wang, Youzhuo Zhu, Yufei Shi, Ye Sun, Yujing Zhu, Xinge Ma, Yuexin Robotics Artificial Intelligence Computer Vision and Pattern Recognition Learning effective visuomotor policies for robotic manipulation is challenging, as it requires generating precise actions while maintaining computational efficiency. Existing methods remain unsatisfactory due to inherent limitations in the essential action representation and the basic network architectures. We observe that representing actions in the frequency domain captures the structured nature of motion more effectively: low-frequency components reflect global movement patterns, while high-frequency components encode fine local details. Additionally, robotic manipulation tasks of varying complexity demand different levels of modeling precision across these frequency bands. Motivated by this, we propose a novel paradigm for visuomotor policy learning that progressively models hierarchical frequency components. To further enhance precision, we introduce continuous latent representations that maintain smoothness and continuity in the action space. Extensive experiments across diverse 2D and 3D robotic manipulation benchmarks demonstrate that our approach outperforms existing methods in both accuracy and efficiency, showcasing the potential of a frequency-domain autoregressive framework with continuous tokens for generalized robotic manipulation.Code is available at https://github.com/4DVLab/Freqpolicy |
| title | FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.01583 |