用大模型生成机器人程序并自动修复执行错误，避免重复失败动作。
Creating and Repairing Robot Programs in Open-World Domains
- 通过追踪程序执行路径定位错误点，生成针对性修复方案。
- 在11个任务上测试，修复效率接近拥有预知能力的最优计划。
- 适合需要自主纠错的开放世界机器人应用。
利用大型语言模型（LLMs）从自然语言生成机器人程序，使机器人能够完成更多样化的任务。然而，由LLM生成的程序可能因指令模糊、任务理解偏差或环境状态信息缺失而存在缺陷。随着程序运行，环境状态发生变化，程序也会获取新信息。当发生故障时，重要的是能基于当前环境状态进行恢复，并避免重复此前成功执行过的步骤。我们提出RoboRepair系统：在错误发生前追踪程序执行过程，随后运行由LLM生成的修复程序，以最小化重复动作。为评估系统有效性，我们构建了一个包含11个任务的基准测试集，涵盖多种错误情境，需生成修复程序。我们将修复程序的效率与一个拥有未来错误预知能力的最优计划（oracle）进行对比。
原文摘要 · Abstract (English)
Using Large Language Models (LLMs) to produce robot programs from natural language has allowed for robot systems that can complete a higher diversity of tasks. However, LLM-generated programs may be faulty, either due to ambiguity in instructions, misinterpretation of the desired task, or missing information about the world state. As these programs run, the state of the world changes and they gather new information. When a failure occurs, it is important that they recover from the current world state and avoid repeating steps that they they previously completed successfully. We propose RoboRepair, a system which traces the execution of a program up until error, and then runs an LLM-produced recovery program that minimizes repeated actions. To evaluate the efficacy of our system, we create a benchmark consisting of eleven tasks with various error conditions that require the generation of a recovery program. We compare the efficiency of the recovery program to a plan built with an oracle that has foreknowledge of future errors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。