arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.15938cs.RO
收藏

VADF:面向高效机器人操作的视觉自适应扩散策略框架

VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation

Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院)

Xinglei Yu, Zhenyang Liu, Shufeng Nan, Simo Wu, Yanwei Fu

AI总结:

本文提出VADF框架,通过视觉驱动的双适应方法减少训练收敛步骤并提升推理早期成功率,采用通用设计可无缝集成至任何扩散策略架构。

摘要:

扩散策略正成为机器人操作中的主流方法,但因均匀采样和缺乏样本难度意识而面临严重的硬负类不平衡问题,导致训练收敛缓慢和频繁的推理超时失败。我们提出了VADF(视觉自适应扩散策略框架),一种由视觉驱动的双适应框架,显著减少了收敛步骤并在推理早期实现了更高的成功率,具有模型无关的设计,可无缝集成到任何扩散策略架构中。在训练过程中,我们引入了轻量级的MLP基于损失预测器Adaptive Loss Network(ALN),它能够实时量化每一步样本的难度。通过硬负类挖掘进行引导,它执行加权采样以优先处理高损失区域,实现自适应权重更新和更快的收敛。在推理过程中,我们设计了分层视觉任务分割器(HVTS),它根据视觉输入将高层任务指令分解为多阶段低层子指令。它通过为简单动作分配较短的噪声调度和较长的直接执行序列,以及为复杂动作分配较长的噪声步骤和较短的执行序列,自适应地将动作序列分割为简单和复杂子任务,从而大幅减少计算开销并显著提高早期成功率。

英文摘要:

Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sample difficulty awareness, leading to slow training convergence and frequent inference timeout failures. We propose VADF (Vision-Adaptive Diffusion Policy Framework), a vision-driven dual-adaptive framework that significantly reduces convergence steps and achieves early success in inference, with model-agnostic design enabling seamless integration into any diffusion policy architecture. During training, we introduce Adaptive Loss Network (ALN), a lightweight MLP-based loss predictor that quantifies per-step sample difficulty in real time. Guided by hard negative mining, it performs weighted sampling to prioritize high-loss regions, enabling adaptive weight updates and faster convergence. In inference, we design the Hierarchical Vision Task Segmenter (HVTS), which decomposes high-level task instructions into multi-stage low-level sub-instructions based on visual input. It adaptively segments action sequences into simple and complex subtasks by assigning shorter noise schedules with longer direct execution sequences to simple actions, and longer noise steps with shorter execution sequences to complex ones, thereby dramatically reducing computational overhead and significantly improving the early success rate.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑