AnchorVLA: 離散的な意思決定と連続的な軌道を橋渡しする視覚言語行動計画
AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning
自動運転の計画において、高レベルの意思決定を表すアンカートークンと、その残差空間での連続軌道生成を組み合わせたVLA計画フレームワークを提案した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ 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: Qi Liu, Yabei Li, Hongsong Wang, Heng Zhang, Lei He
分類: cs.RO, cs.AI
原文アブストラクト
Autonomous driving planning requires translating navigation intent, traffic rules, dynamic interactions, and language instructions into executable continuous trajectories. Vision-Language-Action models have been introduced into driving planning to improve long-tail generalization, commonsense reasoning, high-level semantic understanding, and explainability. However, existing VLA planners mainly follow planning-head-based trajectory prediction or full-trajectory autoregressive generation. The former only weakly constrains continuous trajectory generation with VLA reasoning, while the latter relies on long sequences of low-information-density coordinate tokens, making semantic-action alignment difficult and leading to discretization errors and inefficient inference. To address these limitations, we propose AnchorVLA, a hierarchical decision-anchored VLA planning framework that uses trajectory-pattern anchors as an explicit interface between high-level VLA reasoning and continuous trajectory execution. Specifically, Decision-as-Anchor Representation represents behavior-level driving decisions with anchor tokens, each encoding an entire local motion pattern rather than a single coordinate point. Decision-Anchored Residual Flow then generates fine-grained continuous trajectories in the selected anchor-defined residual space, capturing multi-modal execution refinements after high-level decision making. By reasoning over compact and semantically meaningful anchors instead of autoregressively generating waypoint sequences, AnchorVLA preserves LLM-based decision making while improving inference efficiency, semantic-action alignment, and continuous generation flexibility. Experiments on the Bench2Drive closed-loop benchmark show that AnchorVLA achieves a state-of-the-art Success Rate of 77.28 and a competitive Driving Score of 89.92.
関連論文
- 知覚しているのにブレーキを踏まない：推論型VLA運転モデルにおける知覚-行動バインディングのギャップ自動運転/VLA
- 運転用VLAの異なる車体構成へのゼロショット転移に向けて自動運転/VLA
- Geo-VLA: 地図セマンティクスの内在化による幾何認識型視覚言語行動計画自動運転/VLA
- FIRE-VLA: 自動運転における視覚言語行動モデルの失敗情報に基づく自己進化自動運転/VLA
- FactorDrive: 計画重要因子に基づく適応的多段階推論によるエンドツーエンド自動運転自動運転/VLA
- S-squared-VLA: 自動運転のための視覚言語行動モデルにおける意味ストリームと空間ストリームの分離自動運転/VLA
