プロンプトから舗装路へ、時間を越えて：エージェント型シーンから計画への推論における時間的接地
From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning
自動運転の高次シーン解釈と計画にLLM/LMMを使う際、時間的接地の欠如が問題となる。本研究では、エージェント間通信に時間的条件付けを導入した3つのプランナーアーキテクチャをBDD-Xデータセットで評価し、時間的接地の効果を検証した。
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: Ahmed Y. Gado, Omar Y. Goba, Alaa Hassanein, Catherine M. Elias, Ahmed Hussein
分類: cs.AI, cs.CL, cs.CV, cs.RO
原文アブストラクト
Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and Large Multimodal Models (LMMs) continue to treat time as a secondary property. This lack of temporal grounding leads to inconsistencies in reasoning about continuous actions, undermining both safety and interpretability. This work explores whether temporal conditioning within inter-agent communication can preserve or enhance coherence without introducing degradation in semantic or logical consistency. To investigate this, we introduce three planner architectures with progressively increasing temporal integration and evaluate them on curated subsets of the BDD-X dataset using semantic, syntactic, and logical metrics. Results show that while temporal conditioning reshapes reasoning style, it yields no statistically significant improvements in standard NLP-based correctness metrics. However, qualitative analysis reveals predictive hazard reasoning, stable corrective behavior, and strategic divergence in the Sentinel. These findings clarify the limits of prompt-based temporal grounding and establish the first empirical benchmark for temporal scene-to-plan reasoning.
