日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

タスク計画arXiv:2501.15214

小さく考え、賢く計画する:LLM誘導タスク計画のための最小記号的抽象化とヒューリスティック部分空間探索

Think Small, Plan Smart: Minimalist Symbolic Abstraction and Heuristic Subspace Search for LLM-Guided Task Planning

シェア:XThreadsFacebookLINEはてブBluesky

LLMと記号プランナを組み合わせたタスク計画において、冗長な記号表現を最小化しメタヒューリスティック部分空間探索を並列反復的に行うPLAHXを提案し、ブロック積み上げや移動マニピュレーションなどで成功率を平均21.47%改善した。

著者: Junfeng Tang, Yuping Yan, Zihan Ye, Zhenshou, Song, Zeqi Zheng, Yaochu Jin

分類: cs.RO, cs.LG

原文アブストラクト

Reliable task planning is pivotal for achieving long-horizon autonomy in real-world robotic systems. Large language models (LLMs) offer a promising interface for translating complex and ambiguous natural language instructions into actionable plans. However, their probabilistic and opaque nature often leads to logically inconsistent or infeasible outputs. To address these limitations, recent frameworks combine LLMs with symbolic planners by first generating action models (Planning Domain Definition Language) and then applying heuristic search. Although promising, such systems still suffer from representation redundancy and exponential search complexity, often resulting in inefficient or overly long plans. To improve planning efficiency and effectiveness, we propose PLAHX (Planning from Language using Abstraction and Heuristic eXploration), a two-stage LLM-symbolic planning framework that integrates abstract symbolic representations with meta-heuristic subspace search in a parallel and iterative fashion. Rather than relying on verbose LLM-generated domain models, we introduce a minimalist symbolic abstraction pipeline that preserves semantic fidelity while eliminating redundancy. Our approach redefines LLM-symbolic planning not by making LLMs smarter, but by reducing the symbolic search space adaptively. Empirical results across four challenging domains, including block stacking and robotic mobile grasping, show that our approach improves the success rate by 21.47% on average, while reducing token consumption by 13% compared to state-of-the-art baselines.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI