TPS-Drive: タスク誘導型表現精製によるVLMベース自動運転
TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving
VLMベースの自動運転計画において、空間的推論と3D予測のギャップを埋めるため、タスク誘導型表現精製フレームワークTPS-Driveを提案。エージェント中心トークナイザで背景冗長性を除去し、精製された空間語彙を用いてシーン理解・未来予測・行動生成を段階的に行う。
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: Jiaxiang Li, Yumao Liu, Ke Ma
分類: cs.RO
原文アブストラクト
Vision-Language Models (VLMs) provide a promising foundation for autonomous driving planning, yet bridging semantic reasoning and precise 3D spatial forecasting remains a critical challenge. Existing representation strategies generally follow two paths: text-aligned methods flatten continuous spatial states into symbols, which compromises geometric structure and induces "spatial hallucinations"; dense visual methods preserve spatial topology but overwhelm standard tokenizers with redundant background textures, leading to "representation interference". To address these limitations, we introduce TPS-Drive, a novel framework centered on Task-Guided Representation Purification that empowers VLMs to Think in Purified Space. At its core, an Agent-Centric Tokenizer utilizes a task-guided vector quantization mechanism supervised by a frozen 3D detection head, which explicitly reallocates limited codebook capacity from pervasive static backgrounds to critical dynamic agents and effectively isolates spatial redundancy. Leveraging this purified spatial vocabulary, TPS-Drive employs a decoupled reasoning pipeline that sequentially performs scene understanding, future forecasting, and action generation. The framework is optimized via a progressive three-stage training paradigm, culminating in reward-driven refinement that surpasses pure imitation learning. Extensive experiments validate our approach: TPS-Drive achieves accurate agent spatial state forecasting and reduces collision rates in open-loop nuScenes evaluations, while establishing new safety records on the rigorous closed-loop NAVSIMv1 and NAVSIMv2 benchmarks.
