LLM-MARS：面向多智能体机器人系统中行为树生成与 NLP 增强对话的大语言模型
LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems
AI总结：
提出 LLM-MARS，利用 Falcon 7B 与双 LoRa 适配器实现行为树生成和机器人问答，在双机器人 Eurobot 2023 实验中验证了较高任务执行与回答性能。
摘要：
本文介绍了 LLM-MARS，这是首个将基于大语言模型的人工智能用于多智能体机器人系统的技术。LLM-MARS 支持人与机器人之间的动态对话，使机器人能够根据操作员指令生成行为，并就自身动作提供信息丰富的回答。LLM-MARS 构建于基于 Transformer 的大语言模型之上，由 Falcon 7B 模型微调得到。我们采用多模态方法，为不同任务使用 LoRa 适配器。第一个 LoRa 适配器通过在行为树及其对应指令的示例上微调基础模型而开发；第二个 LoRa 适配器则通过在问答示例上微调而开发。在 Eurobot 2023 比赛规则下、由两台机器人组成的多智能体系统上进行的实际试验展示了良好结果。机器人在复合指令中的平均任务执行准确率达到 79.28%；对于包含至多两个任务的指令，准确率超过 90%。评估证实，该系统对操作员问题的回答具有较高的准确性、相关性和信息性。LLM-MARS 及类似的多智能体机器人系统在变革物流、支持自主探索任务以及推进 Industry 5.0 方面具有巨大潜力。
英文摘要：
This paper introduces LLM-MARS, first technology that utilizes a Large Language Model based Artificial Intelligence for Multi-Agent Robot Systems. LLM-MARS enables dynamic dialogues between humans and robots, allowing the latter to generate behavior based on operator commands and provide informative answers to questions about their actions. LLM-MARS is built on a transformer-based Large Language Model, fine-tuned from the Falcon 7B model. We employ a multimodal approach using LoRa adapters for different tasks. The first LoRa adapter was developed by fine-tuning the base model on examples of Behavior Trees and their corresponding commands. The second LoRa adapter was developed by fine-tuning on question-answering examples. Practical trials on a multi-agent system of two robots within the Eurobot 2023 game rules demonstrate promising results. The robots achieve an average task execution accuracy of 79.28% in compound commands. With commands containing up to two tasks accuracy exceeded 90%. Evaluation confirms the system's answers on operators questions exhibit high accuracy, relevance, and informativeness. LLM-MARS and similar multi-agent robotic systems hold significant potential to revolutionize logistics, enabling autonomous exploration missions and advancing Industry 5.0.
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。
