English

Ground Manipulator Primitive Tasks to Executable Actions using Large Language Models

Robotics 2023-10-03 v2 Artificial Intelligence

Abstract

Layered architectures have been widely used in robot systems. The majority of them implement planning and execution functions in separate layers. However, there still lacks a straightforward way to transit high-level tasks in the planning layer to the low-level motor commands in the execution layer. In order to tackle this challenge, we propose a novel approach to ground the manipulator primitive tasks to robot low-level actions using large language models (LLMs). We designed a program-function-like prompt based on the task frame formalism. In this way, we enable LLMs to generate position/force set-points for hybrid control. Evaluations over several state-of-the-art LLMs are provided.

Keywords

Cite

@article{arxiv.2308.06810,
  title  = {Ground Manipulator Primitive Tasks to Executable Actions using Large Language Models},
  author = {Yue Cao and C. S. George Lee},
  journal= {arXiv preprint arXiv:2308.06810},
  year   = {2023}
}

Comments

AAAI Fall Symposium on Unifying Representations for Robot Application Development, Arlington, VA, 2023

R2 v1 2026-06-28T11:54:39.828Z