LLM Trainer：利用大语言模型通过演示增强自动生成机器人数据
LLM Trainer: Automated Robotic Data Generation via Demonstration Augmentation using LLMs
AI总结：
提出LLM Trainer，一种利用大语言模型的世界知识将少量人类演示自动扩展为大规模机器人数据集的管道，通过离线标注和在线关键姿势重定向生成新轨迹，并采用汤普森采样优化标注。
摘要：
我们提出LLM Trainer，一个全自动管道，利用大语言模型（LLM）的世界知识，将少量人类演示（少至一个）转化为用于模仿学习的大型机器人数据集。我们的方法将演示生成分解为两个步骤：（1）离线演示标注，提取关键帧、显著物体和姿态-物体关系；（2）在线关键姿势重定向，在给定初始观察的情况下将这些关键帧适应到新场景。使用这些修改后的关键点，我们的系统对原始演示进行扭曲以生成新轨迹，然后执行该轨迹，如果成功，则保存生成的演示。由于标注可跨场景重用，我们使用汤普森采样优化标注，显著提高了生成成功率。我们在多种任务上评估了我们的方法，发现我们的数据标注方法始终优于专家设计的基线。我们进一步展示了一种集成策略，将优化的LLM前馈计划与学习到的反馈模仿学习控制器相结合。最后，我们在Franka Emika Panda机器人上演示了硬件可行性。更多材料和演示视频，请参见项目网站：https://sites.google.com/andrew.cmu.edu/llm-trainer
英文摘要：
We present LLM Trainer, a fully automated pipeline that leverages the world knowledge of Large Language Models (LLMs) to transform a small number of human demonstrations (as few as one) into a large robot dataset for imitation learning. Our approach decomposes demonstration generation into two steps: (1) offline demonstration annotation that extracts keyframes, salient objects, and pose-object relations; and (2) online keypose retargeting that adapts those keyframes to a new scene, given an initial observation. Using these modified keypoints, our system warps the original demonstration to generate a new trajectory, which is then executed, and the resulting demo, if successful, is saved. Because the annotation is reusable across scenes, we use Thompson sampling to optimize the annotation, significantly improving generation success rate. We evaluate our method on a range of tasks, and find that our data annotation method consistently outperforms expert-engineered baselines. We further show an ensemble policy that combines the optimized LLM feed-forward plan with a learned feedback imitation learning controller. Finally, we demonstrate hardware feasibility on a Franka Emika Panda robot. For additional materials and demonstration videos, please see the project website: https://sites.google.com/andrew.cmu.edu/llm-trainer
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
