arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14438cs.ROcs.MA
收藏

RoboSolver: 一种基于多智能体大语言模型的机器人臂问题求解框架

RoboSolver: A Multi-Agent Large Language Model Framework for Solving Robotic Arm Problems

Sharif University of Technology(谢里夫理工大学);Islamic Azad University(伊斯兰阿扎德大学)

Hamid Khabazi, Ali F. Meghdari, Alireza Taheri

AI总结:

RoboSolver通过多智能体框架结合LLM和VLM,实现机器人臂问题的自动求解,准确率达0.97。

摘要:

本研究提出了一种基于大语言模型(LLM)和视觉语言模型(VLM)的智能多智能体框架,专门针对机器人领域进行优化。目标是将LLM和VLM的优势与计算工具相结合,自动分析和解决与机器人机械臂相关的问题。我们开发的框架能够接受文本和视觉输入,并能自动执行正向和反向运动学计算,计算关键点的速度和加速度,生成机器人的3D模拟,并最终在模拟环境中执行运动控制,所有这些操作均根据用户查询进行。为了评估该框架,设计了三个基准测试,每个测试包含十个问题。在第一个基准测试中,框架连接到GPT-4o、DeepSeek-V3.2和Claude-Sonnet-4.5及其对应的原始模型进行评估。目标是从文本描述中直接提取机器人的正向运动学。结果显示,与GPT-4o集成的框架在计算最终解决方案的准确性上最高,达到0.97,而单独的原始模型在相同任务上的准确性仅为0.30。同样,对于其他两个模型,该框架在准确性方面也始终优于对应的原始模型。第二个基准测试与第一个相同,只是输入以视觉形式提供。在此次测试中,GPT-4o LLM与Gemini 2.5 Pro VLM一起使用。结果显示,该框架在获得最终答案的准确性上达到0.93,比对应的原始模型高约20%。第三个基准测试涵盖了范围广泛的机器人任务,包括模拟、控制、速度和加速度计算,以及反向运动学和雅可比计算,该框架在这些任务上的准确性达到0.97。

英文摘要:

This study proposes an intelligent multi-agent framework built on LLMs and VLMs and specifically tailored to robotics. The goal is to integrate the strengths of LLMs and VLMs with computational tools to automatically analyze and solve problems related to robotic manipulators. Our developed framework accepts both textual and visual inputs and can automatically perform forward and inverse kinematics, compute velocities and accelerations of key points, generate 3D simulations of the robot, and ultimately execute motion control within the simulated environment, all according to the user's query. To evaluate the framework, three benchmark tests were designed, each consisting of ten questions. In the first benchmark test, the framework was evaluated while connected to GPT-4o, DeepSeek-V3.2, and Claude-Sonnet-4.5, as well as their corresponding raw models. The objective was to extract the forward kinematics of robots directly from textual descriptions. The results showed that the framework integrated with GPT-4o achieved the highest accuracy, reaching 0.97 in computing the final solution, whereas the raw model alone attained an accuracy of only 0.30 for the same task. Similarly, for the other two models, the framework consistently outperformed the corresponding raw models in terms of accuracy. The second benchmark test was identical to the first, except that the input was provided in visual form. In this test, the GPT-4o LLM was used alongside the Gemini 2.5 Pro VLM. The results showed that the framework achieved an accuracy of 0.93 in obtaining the final answer, which is approximately 20% higher than that of the corresponding raw model. The third benchmark test encompassed a range of robotic tasks, including simulation, control, velocity and acceleration computation, as well as inverse kinematics and Jacobian calculation, for which the framework achieved an accuracy of 0.97.

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。

↑