Action chunking has become a standard design in modern robot policies, from diffusion/flow policies to vision-language-action models, where the policy predicts a sequence of actions and executes a fixed number of them instead of acting one step at a time. However, this paradigm relies on a key assumption: a fixed execution horizon. During chunk execution, the policy operates open-loop, which is particularly problematic for fine-grained manipulation tasks that require frequent replanning. In practice, the execution horizon is typically chosen through empirical tuning and is highly task-dependent. To this end, we propose Dynamic Execution Horizon Prediction (DEHP), an effective method that trains a lightweight execution-horizon prediction branch using online reinforcement learning while keeping the pretrained chunk policy completely frozen. This makes the method compatible with black-box chunk policies and isolates the effect of adapting the execution horizon from changes to the underlying action generator. Across our evaluations, DEHP improves the success rate of different high-precision and long-horizon manipulation tasks by a large margin. Our qualitative analysis further shows that DEHP predicts shorter execution horizons during fine-grained stages of the task and longer horizons during free-space motion. In this way, DEHP balances the efficiency of open-loop chunk execution with the reactivity of closed-loop single-step control. Project page: https://dehp-chunking.github.io/

翻译：动作切块已成为现代机器人策略的标准设计，从扩散/流策略到视觉-语言-动作模型，策略预测一系列动作并执行其中固定数量的动作，而非逐步执行。然而，这一范式依赖于一个关键假设：固定的执行时域。在切块执行期间，策略以开环方式运行，这对于需要频繁重新规划的精细操作任务而言尤为棘手。实践中，执行时域通常通过经验调参选择，且高度依赖具体任务。为此，我们提出动态执行时域预测（DEHP），一种有效方法，通过在线强化学习训练轻量级的执行时域预测分支，同时完全冻结预训练切块策略。这使得该方法与黑盒切块策略兼容，并将执行时域调整的影响与底层动作生成器的变化相隔离。在多项评估中，DEHP显著提升了不同高精度和长时域操作任务的成功率。我们的定性分析进一步表明，DEHP在任务的精细阶段预测较短的执行时域，而在自由空间运动时预测较长的执行时域。通过这种方式，DEHP平衡了开环节块执行的高效性与闭环节单步控制的反应性。项目页面：https://dehp-chunking.github.io/