الملخص
Although vision-language-action (VLA) policies have advanced rapidly, long-horizon execution may still progress to the next task stage before the required physical effect has been established. We call this a mismatch between semantic commitments, physical conditions that a stage must establish or maintain, and the actual physical state. Because an action command alone cannot confirm such a condition, local deviations can propagate and cause task failure. To address this problem, we present CommitFlow, a closed-loop execution framework that combines commitment monitoring with local correction while keeping the base policy frozen. CommitFlow integrates three components. A Semantic Commitment Monitor (SCM) compares stage requirements against current state evidence and holds back dependent actions when a required condition is unmet or violated. BoundaryFlow then generates a local correction conditioned on the current state and base action, and Relation and Gain Calibration (RGC) selects the smallest correction strength that satisfies the relevant constraints. Across the ten common RoboTwin 2.0 benchmark tasks, CommitFlow achieves a mean success rate of 75.9 percent, improving on the base policy pi0.5 by 22.7 percent. Cross-policy experiments show consistent gains, pointing toward reliable long-horizon robot execution.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhao, Z., Feng, Y., Yang, Y., Wang, C., Xiao, H., Zhang, H., Cheng, C., & Ma, J. (2026). CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution. https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution
MLA 9
Zhao, Zixiang, et al. "CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution." https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution.
شيكاغو (المؤلف–التاريخ)
Zhao, Zixiang, Yansong Feng, Yang Yang, Chaoyu Wang, Haoran Xiao, Hui Zhang, Chuang Cheng, and Jianjun Ma. 2026. "CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution." https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution.
هارفارد
Zhao, Z., Feng, Y., Yang, Y., Wang, C., Xiao, H., Zhang, H., Cheng, C. and Ma, J. (2026) 'CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution', Available at: https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution.
فانكوفر
Zhao Z, Feng Y, Yang Y, Wang C, Xiao H, Zhang H, et al. CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution. https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution
IEEE
Z. Zhao, Y. Feng, Y. Yang, C. Wang, H. Xiao, H. Zhang, C. Cheng, and J. Ma, "CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution," https://omanscience.com/ar/articles/commitflow-semantic-commitment-verification-and-local-correction-for-long-horizon-robot-manipulation-vla-execution.