arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01196cs.RO
收藏

EduSim-LLM: 一个整合大语言模型和机器人模拟的教育平台,用于初学者

EduSim-LLM: An Educational Platform Integrating Large Language Models and Robotic Simulation for Beginners

Hangzhou Dianzi University Information Engineering College(杭州电子科技大学信息工程学院)

Shenqi Lu, Liangwei Zhang

AI总结:

EduSim-LLM通过整合大语言模型与机器人模拟,实现自然语言到机器人行为的转换,提升初学者在人机交互和多机器人协作中的控制与操作能力。

摘要:

近年来,大语言模型(LLMs)的快速发展显著增强了自然语言理解和人机交互能力,在机器人领域创造了新的机遇。然而,将自然语言理解整合到机器人控制中是人机交互和智能自动化产业快速发展的关键挑战。这一挑战阻碍了对复杂机器人系统的直观人类控制,限制了其教育和实际应用的可访问性。为此,我们提出了EduSim-LLM教育平台,该平台整合了LLMs与机器人模拟,并构建了一个语言驱动的控制模型,将自然语言指令转换为可在CoppeliaSim中执行的机器人行为序列。我们设计了两种人机交互模型:直接控制和自主控制,基于多种语言模型进行了系统模拟,并评估了多机器人协作、运动规划和操作能力。实验结果表明,LLMs能够可靠地将自然语言转换为结构化的机器人动作;在应用提示工程模板指令后,解析准确性显著提高;随着任务复杂性的增加,总体准确率在最高复杂度测试中超过88.9%。

英文摘要:

In recent years, the rapid development of Large Language Models (LLMs) has significantly enhanced natural language understanding and human-computer interaction, creating new opportunities in the field of robotics. However, the integration of natural language understanding into robotic control is an important challenge in the rapid development of human-robot interaction and intelligent automation industries. This challenge hinders intuitive human control over complex robotic systems, limiting their educational and practical accessibility. To address this, we present the EduSim-LLM, an educational platform that integrates LLMs with robot simulation and constructs a language-drive control model that translates natural language instructions into executable robot behavior sequences in CoppeliaSim. We design two human-robot interaction models: direct control and autonomous control, conduct systematic simulations based on multiple language models, and evaluate multi-robot collaboration, motion planning, and manipulation capabilities. Experiential results show that LLMs can reliably convert natural language into structured robot actions; after applying prompt-engineering templates instruction-parsing accuracy improves significantly; as task complexity increases, overall accuracy rate exceeds 88.9% in the highest complexity tests.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑