ModuLoop: モジュラーシンセサイザと閉ループデバッガを用いたロボット制御のための低レベルコード生成
ModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control
事前学習済みLLMをタスク固有の微調整なしで使い、モジュール単位のコード生成と実行結果のデバッグを繰り返す閉ループフレームワークを提案し、RGB-Dカメラとロボットアームのキャリブレーションおよびピックアンドプレース作業で有効性を実証した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Gina Yoon, Sumin Lee, Joo Yong Sim
分類: cs.RO, cs.MA
原文アブストラクト
Large Language Models (LLMs) have demonstrated impressive performance across various domains, including code generation and problem solving. However, their application in robotic control, particularly in low-level tasks that require precise manipulation, real-time feedback, and environment-dependent execution, remains limited. To address this challenge, we propose the Closed-Loop Modular Code Synthesizer framework. This framework leverages a pre-trained LLM without any task-specific fine-tuning to perform modular code planning and generation, and iteratively executes the generated code while inserting debugging probes to observe its behavior. This closed-loop structure facilitates systematic debugging and refinement, ultimately producing executable control programs. We apply the proposed framework to the calibration of an RGB-D camera and a robotic arm, validating its effectiveness in real-world settings. Furthermore, through a subsequent pick-and-place task, we demonstrate not only the accuracy of the calibration but also the potential extensibility of the framework. Across both tasks, the framework achieved high execution accuracy and autonomy, illustrating the practicality and scalability of LLM-based robotic control using our framework.
