arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.18588cs.ROcs.AIcs.SYeess.SY
收藏

一个段落即可:来自交互式、可信LLM的丰富机器人行为

A Paragraph is All It Takes: Rich Robot Behaviors from Interacting, Trusted LLMs

OpenMind

OpenMind, Shaohong Zhong, Adam Zhou, Boyuan Chen, Homin Luo, Jan Liphardt

AI总结:

本文提出由四个LLM通过自然语言数据总线通信控制物理机器人的系统,结合Ethereum不可变账本存储行为约束,实现了1Hz融合周期下丰富的机器人行为、可升级性与人类持久对齐。

摘要:

大型语言模型(LLMs)是我们物理环境以及动物和人类行为所有公共知识的紧凑表示。将LLMs应用于机器人技术,可能为打造在大多数人类任务中表现良好、且仅需有限甚至零微调的高能力机器人提供一条路径。除了日益复杂的推理和任务规划,(经过适当设计的)LLMs网络还提供了升级能力的便利性,并允许人类直接观察机器人的思考过程。在此,我们探讨了使用LLMs控制物理机器人的优势、局限性和特殊性。基本系统由四个LLM组成,它们通过由web sockets和ROS2消息传递实现的人类语言数据总线进行通信。令人惊讶的是,尽管机器人的数据融合周期仅以1Hz运行,且中央数据总线以人类大脑的极有限速率(约40 bits/s)运行,但仍然能够实现丰富的机器人行为和跨不同任务的良好性能。使用自然语言进行LLM间的通信,使得机器人的推理和决策能够被人类直接观察,并且通过用纯英文编写的规则集来偏置系统行为变得轻而易举。这些规则被不可变地写入Ethereum,这是一台全球性、公开且抗审查的图灵完备计算机。我们建议,通过使用自然语言作为交互式AI之间的数据总线,并使用不可变的公共账本来存储行为约束,有可能构建出结合了出乎意料的丰富性能、可升级性以及与人类持久对齐的机器人。

英文摘要:

Large Language Models (LLMs) are compact representations of all public knowledge of our physical environment and animal and human behaviors. The application of LLMs to robotics may offer a path to highly capable robots that perform well across most human tasks with limited or even zero tuning. Aside from increasingly sophisticated reasoning and task planning, networks of (suitably designed) LLMs offer ease of upgrading capabilities and allow humans to directly observe the robot's thinking. Here we explore the advantages, limitations, and particularities of using LLMs to control physical robots. The basic system consists of four LLMs communicating via a human language data bus implemented via web sockets and ROS2 message passing. Surprisingly, rich robot behaviors and good performance across different tasks could be achieved despite the robot's data fusion cycle running at only 1Hz and the central data bus running at the extremely limited rates of the human brain, of around 40 bits/s. The use of natural language for inter-LLM communication allowed the robot's reasoning and decision making to be directly observed by humans and made it trivial to bias the system's behavior with sets of rules written in plain English. These rules were immutably written into Ethereum, a global, public, and censorship resistant Turing-complete computer. We suggest that by using natural language as the data bus among interacting AIs, and immutable public ledgers to store behavior constraints, it is possible to build robots that combine unexpectedly rich performance, upgradability, and durable alignment with humans.

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。

↑