自律ロボットの認知アーキテクチャへの大規模言語モデルの統合
Integration of Large Language Models within Cognitive Architectures for Autonomous Robots
自律ロボット用認知アーキテクチャMERLIN2に大規模言語モデルを統合し、PDDLベースの計画を自然言語計画に置き換える手法を提案・評価した。
著者: Miguel Á. González-Santamarta, Irene González-Fernández, Francisco J. Rodríguez-Lera, Ángel Manuel Guerrero-Higueras, Vicente Matellán-Olivera
分類: cs.RO
原文アブストラクト
Symbolic reasoning systems have been used in cognitive architectures to provide inference and planning capabilities. However, defining domains and problems has proven difficult and prone to errors. Moreover, Large Language Models (LLMs) have emerged as tools to process natural language for different tasks. In this paper, we propose the use of LLMs to tackle these problems. This way, this paper proposes the integration of LLMs in the ROS 2-integrated cognitive architecture MERLIN2 for autonomous robots. Specifically, we present the design, development and deployment of how to leverage the reasoning capabilities of LLMs inside the deliberative processes of MERLIN2. As a result, the deliberative system is updated from a PDDL-based planner system to a natural language planning system. This proposal is evaluated quantitatively and qualitatively, measuring the impact of incorporating the LLMs in the cognitive architecture. Results show that a classical approach achieves better performance but the proposed solution provides an enhanced interaction through natural language.
関連論文
- 動機づけられた情動的マインドの数理モデル:認知的身体化システム認知アーキテクチャ
- 自律ロボットのためのイベント依存認知処理と学習による連続的認知カバレッジ認知アーキテクチャ
- 因果的世界モデリングに基づく自己進化型認知フレームワーク:身体化された科学的知能に向けて認知アーキテクチャ
- 感覚変調ネットワーク:物体指向現象学の建築的基盤としての停止可能性認知アーキテクチャ
- 熟練技能のモデル化:Vergnaudのスキームと認知アーキテクチャの統合認知アーキテクチャ
- EGO:再帰的・自己言及的な汎用人工知能の認知アーキテクチャ認知アーキテクチャ
