GameVLM:視覚言語モデルとゼロサムゲームによるロボットタスク計画の意思決定フレームワーク
GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games
GPT-4Vなどの視覚言語モデルを複数エージェントで活用し、ゼロサムゲーム理論で計画の不一致を解消することで、ロボットのタスク計画の意思決定を強化するフレームワークを提案した。実機実験で平均83.3%の成功率を達成。
著者: Aoran Mei, Jianhua Wang, Guo-Niu Zhu, Zhongxue Gan
分類: cs.RO, cs.AI
原文アブストラクト
With their prominent scene understanding and reasoning capabilities, pre-trained visual-language models (VLMs) such as GPT-4V have attracted increasing attention in robotic task planning. Compared with traditional task planning strategies, VLMs are strong in multimodal information parsing and code generation and show remarkable efficiency. Although VLMs demonstrate great potential in robotic task planning, they suffer from challenges like hallucination, semantic complexity, and limited context. To handle such issues, this paper proposes a multi-agent framework, i.e., GameVLM, to enhance the decision-making process in robotic task planning. In this study, VLM-based decision and expert agents are presented to conduct the task planning. Specifically, decision agents are used to plan the task, and the expert agent is employed to evaluate these task plans. Zero-sum game theory is introduced to resolve inconsistencies among different agents and determine the optimal solution. Experimental results on real robots demonstrate the efficacy of the proposed framework, with an average success rate of 83.3%.
