FRAMES：仿人机器人移动操作技能失败恢复与监控
FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation
- Duke University（杜克大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
FRAMES提出一个针对Unitree G1仿人机器人的失败感知监督框架，通过视觉语言模型监控技能执行并触发恢复，在MuJoCo中达到94%的监控准确率。
AI中文摘要：
大语言模型（LLM）规划器能够分解自然语言指令并选择可复用的机器人技能，但选择正确的技能并不能保证物理执行的成功。这一差距在仿人机器人移动操作中尤为重要，因为在接近、抓取、运输或放置过程中的错误可能会使长时程计划的其余部分失效。我们提出了FRAMES，一个针对Unitree G1仿人机器人的失败感知监督框架，运行在CEER全身控制器之上。规划器代理通过参数化的中层技能选择子任务，而基于视觉语言模型的监控代理则利用时间多视角观测以及结构化的机器人和接触证据来评估每项技能。检测到的失败会停止当前技能，并向恢复代理提供基于事实的反馈。该框架还包括一个记忆模块，用于复用先前的技能经验，并通过深度和分割实现几何接地。我们在MuJoCo中独立评估了该框架的监控模块，使用100次试验，涵盖五个任务的50次失败和50次成功执行。监控器检测到50次失败中的48次，正确接受50次成功执行中的46次，总体准确率达到94.0%。这些结果为监控组件提供了初步证据，而完整恢复回路的端到端评估仍在进行中。
英文摘要：
Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does not guarantee successful physical execution. This gap is especially important in humanoid loco-manipulation, where errors during approach, grasping, transport, or placement can invalidate the remainder of a long-horizon plan. We present FRAMES, a failure-aware supervisory framework for the Unitree G1 humanoid that operates above the CEER whole-body controller. A Planner Agent selects subtasks through parameterized mid-level skills, while a vision-language-model-based Monitor Agent evaluates each skill using temporal multi-view observations and structured robot and contact evidence. Detected failures stop the active skill and provide grounded feedback to a Recovery Agent. The framework further includes a Memory Module for reusing prior skill experience, and geometric grounding via depth and segmentation. We independently evaluate the monitoring module of the framework in MuJoCo using 100 trials comprising 50 failed and 50 successful executions across five tasks. The monitor detects 48 of 50 failures, correctly accepts 46 of 50 successful executions, and achieves 94.0% overall accuracy. These results provide initial evidence for the monitoring component, while end-to-end evaluation of the complete recovery loop remains ongoing.
