ADriver-I: 自動運転のための汎用ワールドモデル
ADriver-I: A General World Model for Autonomous Driving
視覚と操作信号を統合した視覚-行動ペアを導入し、MLLMと拡散モデルで自己回帰的に未来フレームと制御信号を予測する自動運転ワールドモデルを構築した。
著者: Fan Jia, Weixin Mao, Yingfei Liu, Yucheng Zhao, Yuqing Wen, Chi Zhang, Xiangyu Zhang, Tiancai Wang
分類: cs.CV, cs.RO
原文アブストラクト
Typically, autonomous driving adopts a modular design, which divides the full stack into perception, prediction, planning and control parts. Though interpretable, such modular design tends to introduce a substantial amount of redundancy. Recently, multimodal large language models (MLLM) and diffusion techniques have demonstrated their superior performance on comprehension and generation ability. In this paper, we first introduce the concept of interleaved vision-action pair, which unifies the format of visual features and control signals. Based on the vision-action pairs, we construct a general world model based on MLLM and diffusion model for autonomous driving, termed ADriver-I. It takes the vision-action pairs as inputs and autoregressively predicts the control signal of the current frame. The generated control signals together with the historical vision-action pairs are further conditioned to predict the future frames. With the predicted next frame, ADriver-I performs further control signal prediction. Such a process can be repeated infinite times, ADriver-I achieves autonomous driving in the world created by itself. Extensive experiments are conducted on nuScenes and our large-scale private datasets. ADriver-I shows impressive performance compared to several constructed baselines. We hope our ADriver-I can provide some new insights for future autonomous driving and embodied intelligence.
関連論文
- 負例を活用した統合ワールドアクションモデルによるエンドツーエンド自動運転の安全強化自動運転/ワールドモデル
- 関係性に基づく潜在ワールドモデルによる自動運転自動運転/ワールドモデル
- インフラ中心のワールドモデル:路側知覚における時間的深さと空間的広がりの橋渡し自動運転/ワールドモデル
- 車両ダイナミクスを組み込んだ自動運転向けワールドモデル自動運転/ワールドモデル
- Imagine-2-Drive: マルチモーダル拡散ポリシーによる高忠実度ワールドモデル活用自動運転/ワールドモデル
