日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

VLAarXiv:2504.09843

ST-Booster: 連続環境における視覚言語ナビゲーションのための反復的時空間知覚強化手法

ST-Booster: An Iterative SpatioTemporal Perception Booster for Vision-and-Language Navigation in Continuous Environments

シェア:XThreadsFacebookLINEはてブBluesky

連続環境での視覚言語ナビゲーションにおいて、トポロジカルグラフとグリッドマップを組み合わせた階層的時空間符号化と、指示に基づく経路点生成により、知覚精度とナビゲーション性能を向上させる手法を提案した。

著者: Lu Yue, Dongliang Zhou, Liang Xie, Erwei Yin, Feitian Zhang

分類: cs.CV, cs.RO

原文アブストラクト

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to navigate unknown, continuous spaces based on natural language instructions. Compared to discrete settings, VLN-CE poses two core perception challenges. First, the absence of predefined observation points leads to heterogeneous visual memories and weakened global spatial correlations. Second, cumulative reconstruction errors in three-dimensional scenes introduce structural noise, impairing local feature perception. To address these challenges, this paper proposes ST-Booster, an iterative spatiotemporal booster that enhances navigation performance through multi-granularity perception and instruction-aware reasoning. ST-Booster consists of three key modules -- Hierarchical SpatioTemporal Encoding (HSTE), Multi-Granularity Aligned Fusion (MGAF), and ValueGuided Waypoint Generation (VGWG). HSTE encodes long-term global memory using topological graphs and captures shortterm local details via grid maps. MGAF aligns these dualmap representations with instructions through geometry-aware knowledge fusion. The resulting representations are iteratively refined through pretraining tasks. During reasoning, VGWG generates Guided Attention Heatmaps (GAHs) to explicitly model environment-instruction relevance and optimize waypoint selection. Extensive comparative experiments and performance analyses are conducted, demonstrating that ST-Booster outperforms existing state-of-the-art methods, particularly in complex, disturbance-prone environments.

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. 3GXO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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  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

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI