Scholarlink

Large language models (LLMs) understand human user requests and generate plausible responses. However, generic LLMs usually lack the capability to derive task plans with executable actions for robots in real-world scenarios. This review highlights prompt engineering and explores the current literature on integrating LLMs into pick-and-place robots. The results include state-of-the-art requirements, a framework to enhance robotics with LLMs through prompt engineering, and the identification of research gaps and key research areas for implementation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Large Language Models for Robotics: A Systematic Literature Review on Prompt Engineering

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jakob Wolber,
  • Lv Muyang,
  • Dominik Koch,
  • Lucas Bretz,
  • Gisela Lanza,
  • Felix Baer

摘要

Large language models (LLMs) understand human user requests and generate plausible responses. However, generic LLMs usually lack the capability to derive task plans with executable actions for robots in real-world scenarios. This review highlights prompt engineering and explores the current literature on integrating LLMs into pick-and-place robots. The results include state-of-the-art requirements, a framework to enhance robotics with LLMs through prompt engineering, and the identification of research gaps and key research areas for implementation.