LSRE: 潜在意味ルール符号化による自動運転のリアルタイム意味的リスク検出
LSRE: Latent Semantic Rule Encoding for Real-Time Semantic Risk Detection in Autonomous Driving
VLMの判断を世界モデルの潜在空間上の決定境界に変換し、毎フレームVLMを使わずに10Hzで意味的リスクを検出する手法を提案。
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: Qian Cheng, Weitao Zhou, Cheng Jing, Nanshan Deng, Junze Wen, Zhaoyang Liu, Kun Jiang, Diange Yang
分類: cs.RO, cs.AI
原文アブストラクト
Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers' gestures, or stopping for school buses, are intuitive for humans yet difficult to encode explicitly. Although large vision-language models (VLMs) can interpret such semantics, their inference cost makes them impractical for real-time deployment. This work proposes LSRE, a Latent Semantic Rule Encoding framework that converts sparsely sampled VLM judgments into decision boundaries within the latent space of a recurrent world model. By encoding language-defined safety semantics into a lightweight latent classifier, LSRE enables real-time semantic risk assessment at 10 Hz without per-frame VLM queries. Experiments on six semantic-failure scenarios in CARLA demonstrate that LSRE attains semantic risk detection accuracy comparable to a large VLM baseline, while providing substantially earlier hazard anticipation and maintaining low computational latency. LSRE further generalizes to rarely seen semantic-similar test cases, indicating that language-guided latent classification offers an effective and deployable mechanism for semantic safety monitoring in autonomous driving.
