外观
论文arXiv 2610.0886223 天前
CIRRA：面向交互式家庭任务中具身机器人智能体的结合执行过程的双层持续指令协调
针对家庭机器人执行任务时接收新指令易出现规划歧义等问题，提出双层框架CIRRA，在基准数据集和Unitree G1人形机器人上验证了性能优势。
宇树 G1原文链接：CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks（arXiv 2610.08862 · 发布日期：2026-10-05）
CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks
针对家庭机器人执行任务时接收新指令易出现规划歧义等问题，提出双层框架CIRRA，在基准数据集和Unitree G1人形机器人上验证了性能优势。
核心要点
- 现有机器人智能体处理中途新指令时易出现规划歧义、逻辑不一致与执行冗余问题，实用性受限。
- 提出CIRRA双层框架，结合大模型语义推理与规则约束的结构整合，保留原有执行主干仅局部调整。
- 构建CHIRP文本基准，CIRRA在该基准上决策一致性达74.2%，领先最优重规划基线30个百分点。
- 在Unitree G1人形机器人测试中，CIRRA可准确中断当前技能，各项指标均显著优于基线方法。
验证范围与局限：在文本基准CHIRP和Unitree G1人形机器人的家庭交互任务场景下验证。
英文摘要 (Abstract)
Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution. We formulate continual instruction reconciliation and propose CIRRA (Continual Instruction Reconciliation for Robot Agents), a dual-level framework combining LLM-based semantic reasoning with rule-constrained structural integration. CIRRA first grounds incoming instructions to unique executable skills and resolves underspecified actions and execution locations. It then preserves the ongoing subtask sequence as an execution backbone and generates integration candidates by inserting incoming subtasks into location-matched segments. The semantic reasoner evaluates only modified segments to identify dependencies and conflicts and select the most logically coherent local integration. This structure-preserving process maintains alignment with ongoing execution, mitigates ambiguity and inconsistency, and reuses shared subtasks to reduce redundant execution. We also introduce CHIRP (Continual Household Instruction Reconciliation and Planning), a text-based benchmark of 120 episodes across eight household environments and six categories of everyday activities. On CHIRP, CIRRA achieves 74.2% decision agreement, exceeding the strongest replanning baseline by 30 percentage points; every correct fusion decision yields a correctly placed, conflict-free schedule. On a Unitree G1 humanoid, CIRRA interrupts ongoing skills at the correct moment in every trial and significantly outperforms all baselines on every metric.
作者：Zhang Ci, Enfu Nan, Arman Akbari, Lin Zhao, Li Wang, Chen Wang, Weiwei Chen, Yanzhi Wang, Geng Yuan
来源
本页事实对应的公开页面，以原文为准。