日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ワールドモデルarXiv:2503.20523

GAIA-2: 自動運転のための制御可能なマルチビュー生成ワールドモデル

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

シェア:XThreadsFacebookLINEはてブBluesky

自動運転向けに、自車挙動やエージェント配置、環境要因、道路意味論などの構造化入力で制御可能な、マルチカメラで時空間的に一貫した高解像度動画を生成する潜在拡散ワールドモデルを提案。

著者: Lloyd Russell, Anthony Hu, Lorenzo Bertoni, George Fedoseev, Jamie Shotton, Elahe Arani, Gianluca Corrado

分類: cs.CV, cs.AI, cs.RO

原文アブストラクト

Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2.

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