用大模型补全机器人任务中的常识细节，提升真实场景下执行成功率。
Enhancing Cognitive Robotics with Commonsense through LLM-Generated Preconditions and Subgoals
- 用大模型生成任务所需的隐含前提和子目标
- 在仿真中成功执行率显著高于基线方法
- 适合需要理解常识的智能机器人研发
机器人常因指令省略常识性细节（如隐藏前提和微小子目标）而失败。传统符号规划需手动写出这些细节，耗时且不完整。本研究将大语言模型与符号规划结合：给定自然语言任务，由大模型推断合理前提与子目标，并转化为形式化规划模型，在仿真中执行。相比无大模型辅助的基线系统，该方法生成更多有效计划，任务成功率更高，且环境变化时适应能力更强。结果表明，为经典规划引入大模型的常识推理，可显著提升机器人在真实场景中的行为可靠性。
原文摘要 · Abstract (English)
Robots often fail at everyday tasks because instructions skip commonsense details like hidden preconditions and small subgoals. Traditional symbolic planners need these details to be written explicitly, which is time consuming and often incomplete. In this project we combine a Large Language Model with symbolic planning. Given a natural language task, the LLM suggests plausible preconditions and subgoals. We translate these suggestions into a formal planning model and execute the resulting plan in simulation. Compared to a baseline planner without the LLM step, our system produces more valid plans, achieves a higher task success rate, and adapts better when the environment changes. These results suggest that adding LLM commonsense to classical planning can make robot behavior in realistic scenarios more reliable.
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。