论文/arXiv 2610.07949·22 天前

在未来一致时提交：面向后果的机器人操作自适应动作分块

针对动作块应执行多长再重规划的问题，CA^3C用世界模型想象后果，并在仿真与真机操作中验证。

AI 整理

• 本体 SDK 与控制
• 仿真与训练
• 具身模型

原文链接：Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation（arXiv 2610.07949 · 发布日期：2026-10-06）

Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation

针对动作块应执行多长再重规划的问题，CA^3C用世界模型想象后果，并在仿真与真机操作中验证。

核心要点

• 动作分块策略需决定重规划前执行多长，固定前缀假设各状态可信时域相同。
• CA^3C在推理时利用动作条件世界模型，比较多个候选动作块的想象后果。
• 方法将执行时域估计表述为贝叶斯变点推断，并通过未来共识选择执行候选。
• 在多个仿真基准和真实机器人操作任务中，CA^3C持续改进多种动作分块策略。

验证范围与局限：验证范围为多个仿真基准和真实世界机器人操作任务。

英文摘要 (Abstract)

Action-chunking policies predict multi-step control sequences, but a fundamental question remains: how much of a predicted action chunk should be committed before replanning? Existing systems typically execute a fixed-length prefix, implicitly assuming that the same execution horizon remains trustworthy across states. Some adaptive methods estimate this horizon from the similarity or stability of predicted actions. However, different actions may lead to the same successful outcome, whereas similar actions can produce different futures, suggesting that commitment should be determined by agreement among imagined futures rather than by similarity in action space. To this end, we propose Consequence-Aware Adaptive Action Chunking (CA$^3$C), an inference-time framework built on a simple principle: commit while imagined futures agree, and replan when they diverge. Without modifying or retraining the base policy, CA$^3$C uses an action-conditioned world model to imagine the future consequences of multiple candidate action chunks under the same sampling noise. Using these imagined consequences, we formulate execution-horizon estimation as a Bayesian change-point inference problem and select the execution candidate through future consensus. Across multiple simulation benchmarks and real-world robot manipulation tasks, CA$^3$C consistently improves diverse action-chunking policies, achieving up to a 71.8% relative reduction in failure rate over the corresponding base policies.

作者：Yuyan Li, Yujia Wang, Yusong Huang, Junjie Yang, Yanggang Sheng, Ziyi Shi, Wenpeng Xu, Xiaoyang Zhou, Haoang Li, Hongliang Lu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.07949：Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation访问 2026-10-21