LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914990978498560 |
|---|---|
| author | Lykov, Artem Dronova, Maria Naglov, Nikolay Litvinov, Mikhail Satsevich, Sergei Bazhenov, Artem Berman, Vladimir Shcherbak, Aleksei Tsetserukou, Dzmitry |
| author_facet | Lykov, Artem Dronova, Maria Naglov, Nikolay Litvinov, Mikhail Satsevich, Sergei Bazhenov, Artem Berman, Vladimir Shcherbak, Aleksei Tsetserukou, Dzmitry |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_09348 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems Lykov, Artem Dronova, Maria Naglov, Nikolay Litvinov, Mikhail Satsevich, Sergei Bazhenov, Artem Berman, Vladimir Shcherbak, Aleksei Tsetserukou, Dzmitry Robotics 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. |
| title | LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems |
| topic | Robotics |
| url | https://arxiv.org/abs/2312.09348 |