用大模型代理实现机器人自主规划与环境适应
LA-RCS: LLM-Agent-Based Robot Control System
- 双代理架构让机器人自主规划并动态调整任务
- 自然语言指令转化成功率90%，减少人工干预
- 适合需低代码交互的智能机器人应用
LA-RCS（LLM-Agent-based robot control system）是一种基于大模型代理的机器人控制系统，可依据用户需求自主规划、执行任务并分析外部环境。系统采用双代理框架，根据用户请求生成计划，观测外部环境，执行任务，并在环境变化时动态调整计划。同时，系统能理解自然语言指令，并转换为机器人可执行命令，实现任务闭环。过程中系统自动评估观测结果，反馈任务进展，并基于实时监测执行决策，显著降低用户干预需求。我们将应用场景分为四类，并进行量化评估，平均成功率达90%，证明其有效满足用户请求的能力。更多结果详见项目页面：https://la-rcs.github.io
原文摘要 · Abstract (English)
LA-RCS (LLM-agent-based robot control system) is a sophisticated robot control system designed to autonomously plan, work, and analyze the external environment based on user requirements by utilizing LLM-Agent. Utilizing a dual-agent framework, LA-RCS generates plans based on user requests, observes the external environment, executes the plans, and modifies the plans as needed to adapt to changes in the external conditions. Additionally, LA-RCS interprets natural language commands by the user and converts them into commands compatible with the robot interface so that the robot can execute tasks and meet user requests properly. During his process, the system autonomously evaluates observation results, provides feedback on the tasks, and executes commands based on real-time environmental monitoring, significantly reducing the need for user intervention in fulfilling requests. We categorized the scenarios that LA-RCS needs to perform into four distinct types and conducted a quantitative assessment of its performance in each scenario. The results showed an average success rate of 90 percent, demonstrating the system capability to fulfill user requests satisfactorily. For more extensive results, readers can visit our project page: https://la-rcs.github.io
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。