Views
No views yet
TL;DR: introduce Coarse-to-Fine AutoRegressive Policy (CARP), a novel paradigm for visuomotor policy learning that redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach.
The left panel shows the final predicted trajectories for each task, with CARP producing smoother and more consistent paths than Diffusion Policy (DP). The right panel visualizes intermediate trajectories during the refinement process for CARP (top-right) and DP (bottom-right). DP displays considerable redundancy, resulting in slower processing and unstable training, as illustrated by 6 selected steps among 100 denoising steps. In contrast, CARP achieves efficient trajectory refinement across all 4 scales, with each step contributing meaningful updates.
1@misc{gong2024carpvisuomotorpolicylearning,
2 title={CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction},
3 author={Zhefei Gong and Pengxiang Ding and Shangke Lyu and Siteng Huang and Mingyang Sun and Wei Zhao and Zhaoxin Fan and Donglin Wang},
4 year={2024},
5 eprint={2412.06782},
6 archivePrefix={arXiv},
7 primaryClass={cs.RO},
8 url={https://arxiv.org/abs/2412.06782},
9}