AutoTAMP：以大型语言模型作为翻译器和检查器的自回归任务与运动规划
AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers
- Massachusetts Institute of Technology（麻省理工学院）
- Harvard University（哈佛大学）
- MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出AutoTAMP框架，利用大型语言模型将自然语言任务描述少样本翻译为中间任务表示，交由TAMP算法联合求解，并通过自回归重新提示纠正语法和语义错误，显著提升了复杂任务下机器人动作序列的完成率。
AI中文摘要：
为了实现有效的人机交互，机器人需要理解、规划和执行由自然语言描述的复杂、长时程任务。大型语言模型（LLMs）的最新进展已展现出将自然语言转化为复杂任务机器人动作序列的潜力。然而，现有方法要么将自然语言直接转化为机器人轨迹，要么通过将语言分解为任务子目标并依赖运动规划器执行每个子目标来分解推理过程。当涉及复杂的环境和时间约束时，必须使用传统的任务与运动规划（TAMP）算法将规划任务的推理与运动计划联合执行，这使得子目标分解变得不可行。我们没有使用LLMs直接规划任务子目标，而是执行从自然语言任务描述到中间任务表示的少样本翻译，该表示随后可由TAMP算法使用以联合求解任务和运动计划。为了改善翻译，我们通过自回归重新提示自动检测并纠正语法和语义错误，从而在任务完成方面取得显著改进。我们表明，在复杂任务领域中，我们的方法优于几种使用LLMs作为规划器的方法。请参阅我们的项目网站 https://yongchao98.github.io/MIT-REALM-AutoTAMP/ 获取提示、视频和代码。
英文摘要：
For effective human-robot interaction, robots need to understand, plan, and execute complex, long-horizon tasks described by natural language. Recent advances in large language models (LLMs) have shown promise for translating natural language into robot action sequences for complex tasks. However, existing approaches either translate the natural language directly into robot trajectories or factor the inference process by decomposing language into task sub-goals and relying on a motion planner to execute each sub-goal. When complex environmental and temporal constraints are involved, inference over planning tasks must be performed jointly with motion plans using traditional task-and-motion planning (TAMP) algorithms, making factorization into subgoals untenable. Rather than using LLMs to directly plan task sub-goals, we instead perform few-shot translation from natural language task descriptions to an intermediate task representation that can then be consumed by a TAMP algorithm to jointly solve the task and motion plan. To improve translation, we automatically detect and correct both syntactic and semantic errors via autoregressive re-prompting, resulting in significant improvements in task completion. We show that our approach outperforms several methods using LLMs as planners in complex task domains. See our project website https://yongchao98.github.io/MIT-REALM-AutoTAMP/ for prompts, videos, and code.
