日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ナビゲーションarXiv:2606.04907

WAM-Nav: 非対称潜在世界行動モデリングによる統合視覚ナビゲーション

WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation

シェア:XThreadsFacebookLINEはてブBluesky

視覚ナビゲーションのための潜在世界行動モデルを提案し、行動生成と視覚予測を共同で学習することで、推論効率を保ちつつ先見的な障害物回避を実現した。

詳しい要約

1. どんなもの?

- WAM-Navはembodied visual navigationのためのLatent World-Action Model - 行動生成とlatent visual foresightをjointlyに学習 - 単一policyでImage-Goal, Point-Goal, No-Goal explorationをサポート - 推論効率を損なわず先読み可能なナビゲーション決定を実現

2. 先行研究と比べてどこがすごい?

- 既存のreactive policiesは観測から行動への直接写像で先読み推論が欠如 - visual imaginationは予測的先見性を持つが、従来のmodular approachはscene predictionとpolicy learningを分離 - その結果、error accumulationと非効率な推論が生じる - WAM-Navはこれらを統合し、推論効率を維持しつつ堅牢で先読み的なナビゲーションを実現

3. 技術・手法の肝は?

- 共有Diffusion Transformerによるasymmetric joint diffusion - long-horizon actionsとshort-horizon visual foresightを同時生成 - multi-step autoregressive rolloutsの推論遅延とvisual error accumulationを低減 - dual-stream contextual conditioning mechanismでepisode-level ego-motion historyとsequential visual observationsを統合 - unified goal alignment moduleでgoal types間のバランスの取れた表現を保持

4. どうやって有効だと検証した?

- ClutterScenesとInternScenesベンチマークで広範な実験 - Image-GoalとPoint-Goalナビゲーションで成功率がそれぞれ15.7%と3.3%向上 - 実世界展開でzero-shot sim-to-real transferを検証 - 多様な屋内・屋外環境で平均85%のタスク成功率を達成

5. 議論はある?

- 要旨からは不明

6. 次に読むべき論文は?

- Diffusion Transformer - visual imagination - reactive policies - modular approaches - Image-Goal, Point-Goal, No-Goal navigation - ClutterScenes, InternScenes benchmarks

※ 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: Ning Yang, Yan Huang, Kaiwen Peng, Ziheng He, Kai Wang, Cui Miao, Kailin Lyu, Guo Li, Xiaofeng Wang, Zheng Zhu, Jing Liu, Nianfeng Liu

分類: cs.RO

原文アブストラクト

Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints. Existing reactive policies that directly map observations to actions lack anticipatory reasoning, limiting their ability to proactively avoid obstacles. While visual imagination offers predictive foresight, conventional modular approaches separate scene prediction from policy learning, often leading to error accumulation and inefficient inference. To address these limitations, we propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight, enabling more robust and foresighted navigation decisions without compromising inference efficiency. Specifically, WAM-Nav utilizes a shared Diffusion Transformer for asymmetric joint diffusion to concurrently generate long-horizon actions and short-horizon visual foresight, reducing the inference latency and visual error accumulation inherent in multi-step autoregressive rollouts. To further encourage smooth and consistent trajectory generation, we introduce a dual-stream contextual conditioning mechanism that integrates episode-level ego-motion history with sequential visual observations. Combined with a unified goal alignment module that preserves balanced representations across goal types, WAM-Nav naturally supports Image-Goal, Point-Goal, and No-Goal exploration within a single policy. Extensive experiments on the challenging ClutterScenes and InternScenes benchmarks demonstrate strong generalization of WAM-Nav, particularly on Image-Goal and Point-Goal navigation, where it improves success rates by 15.7% and 3.3%, respectively. Real-world deployment further validates effective zero-shot sim-to-real transfer, achieving an average 85% task success rate across diverse indoor and outdoor 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. 2GXO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
  3. 3newmo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
  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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI