الملخص
Learning chunk-based visuomotor policies for long-horizon robot manipulation remains challenging. Recent action-chunking methods have shown promising performance by predicting temporally extended action sequences. However, their failures are often dominated by prediction errors at a small number of critical timesteps rather than uniformly poor predictions across the entire action chunk, making uniform refinement inefficient and insufficiently targeted. To address this bottleneck, we propose Uncertainty-Guided Refinement (UGR), a sparse refinement framework for chunk-based visuomotor policies. Specifically, UGR follows a coarse-to-refine design: it first predicts a full action chunk, estimates per-step temporal uncertainty from the coarse hidden states, and applies residual correction only to the most uncertain timesteps selected by a binary mask. The uncertainty branch is decoupled from the coarse action predictor, enabling clean attribution of the refinement gains to uncertainty-guided correction rather than additional predictor capacity. Extensive experiments on five dual-arm manipulation tasks from the RoboTwin benchmark show that UGR achieves the best success rate on four tasks, improves over the ACT baseline by up to 13% absolute, and outperforms both full-chunk and position-agnostic block refinement in ablation studies.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Wang, C., Wang, Y., Yang, X., Jiang, D., Liu, S., & Liu, Y. (2026). Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies. https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies
MLA 9
Wang, Chenyang, et al. "Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies." https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies.
شيكاغو (المؤلف–التاريخ)
Wang, Chenyang, Yuntian Wang, Xiaoxiong Yang, Dingde Jiang, Siao Liu, and Yang Liu. 2026. "Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies." https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies.
هارفارد
Wang, C., Wang, Y., Yang, X., Jiang, D., Liu, S. and Liu, Y. (2026) 'Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies', Available at: https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies.
فانكوفر
Wang C, Wang Y, Yang X, Jiang D, Liu S, Liu Y. Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies. https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies
IEEE
C. Wang, Y. Wang, X. Yang, D. Jiang, S. Liu, and Y. Liu, "Uncertainty-Guided Sparse Refinement for Action Chunking Transformer Policies," https://omanscience.com/ar/articles/uncertainty-guided-sparse-refinement-for-action-chunking-transformer-policies.