面向视觉-语言-动作模型的推理时自适应动作分块
Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
提出用动作熵作为推理时自适应选择动作分块大小的线索，可被其他 VLA 模型直接复用，以平衡响应速度与动作一致性。
原文依据 we propose a novel Adaptive Action Chunking (AAC) strategy, which exploits action entropy as the cue to adaptively determine the chunk size based on current predictions.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在视觉-语言-动作（VLA）模型中，动作分块（即执行一系列动作而无需中间重新规划）是提升机器人操作能力的关键技术。然而，较大的分块尺寸会降低模型对新信息的响应能力，而较小的分块尺寸则会增加模式跳变的可能性，即由于分块之间的不连续性而产生的抖动行为。因此，选择最优分块尺寸是平衡模型反应性与一致性的迫切需求。遗憾的是，当前 VLA 模型的一个主导趋势是在推理时采用经验固定的分块长度，这阻碍了它们在不同操作任务中的优越性和可扩展性。为解决这一问题，我们提出了一种新颖的自适应动作分块（AAC）策略，该策略利用动作熵作为线索，根据当前预测自适应地确定分块尺寸。在广泛的模拟和真实世界机器人操作任务上进行的大量实验表明，我们的方法相比最优的替代方案显著提升了性能。视频和源代码已公开于 https://lance-lot.github.io/adaptive-chunking.github.io。
英文原文摘要 1203 字符
In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique to improve robotic manipulation abilities. However, a large chunk size reduces the model's responsiveness to new information, while a small one increases the likelihood of mode-jumping, jerky behavior resulting from discontinuities between chunks. Therefore, selecting the optimal chunk size is an urgent demand to balance the model's reactivity and consistency. Unfortunately, a dominant trend in current VLA models is an empirical fixed chunk length at inference-time, hindering their superiority and scalability across diverse manipulation tasks. To address this issue, we propose a novel Adaptive Action Chunking (AAC) strategy, which exploits action entropy as the cue to adaptively determine the chunk size based on current predictions. Extensive experiments on a wide range of simulated and real-world robotic manipulation tasks have demonstrated that our approach substantially improves performance over the state-of-the-art alternatives. The videos and source code are publicly available at https://lance-lot.github.io/adaptive-chunking.github.io.