CARE：视觉-语言-动作策略的经验引导原子纠正执行
CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies
- Dalian University of Technology（大连理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对VLA策略执行偏差问题，提出CARE框架，通过收集失败轨迹并建模偏差分布来生成纠正示范，结合3D监控触发原子调整，在模拟和真实任务中分别提升14.5和15.9个百分点成功率。
AI中文摘要：
视觉-语言-动作（VLA）策略在机器人操作中表现出强大的性能，但一旦执行偏离标称轨迹，它们仍然脆弱。我们提出了CARE（纠正性原子机器人执行），这是一个通过从执行过程中遇到的失败中学习来提高恢复能力的框架。CARE不是从手动设计或随机扰动中生成纠正数据，而是收集失败的轨迹，建模阶段条件下的失败后偏差，并利用由此产生的经验分布来合成代表性的失败状态和纠正示范。在推理时，CARE结合了阶段级规划与物理基础的3D监控，以触发原子调整或重新操作，同时保持任务进展。我们进一步引入了失败状态恢复基准（FSR-Bench），该基准评估在局部偏差和结构异常下从中间失败状态恢复的能力。在多个VLA骨干网络、模拟基准和真实世界双臂任务上的实验显示了一致的改进，模拟中平均任务成功率提高了14.5个百分点，真实世界中提高了15.9个百分点。代码、模型和数据可在以下https URL获取。
英文摘要：
Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution. Instead of generating corrective data from manually designed or random perturbations, CARE collects failed rollouts, models stage-conditioned post-failure deviations, and uses the resulting empirical distributions to synthesize representative failure states and corrective demonstrations. At inference time, CARE combines stage-wise planning with physically grounded 3D monitoring to trigger atomic adjustments or re-operations while preserving task progress. We further introduce the Failure State Recovery Benchmark (FSR-Bench), which evaluates recovery from intermediate failure states under local deviations and structural anomalies. Experiments across multiple VLA backbones, simulation benchmarks, and real-world dual-arm tasks show consistent improvements, with average task-success gains of 14.5 points in simulation and 15.9 points in the real world. Code, models, and data are available at https://github.com/xiaojunlan/care
