LANTERN：基于时间锚定警告的VLM协作驾驶闭环基准
LANTERN: A Closed-Loop Benchmark for VLM-Based Cooperative Driving with Temporally Grounded Warnings
浏览论文内容
中文总结 AI 辅助
提出LANTERN闭环基准，通过配对警告/无警告评估分离警告贡献，引入安全门控指标CUS，微调VLM模型将评分从34.6提升至75.5。
中文摘要 AI 辅助
我们提出了LANTERN，一个用于时间锚定协作警告的闭环基准。LANTERN将警告开始、危险开始、警告终止和危险后恢复分开，并在匹配的警告和无警告执行下评估每个物理事件，从而单独衡量警告的贡献，而不与车载视觉混淆。该基准涵盖六个安全关键场景族，提供3,272个序列共236,309帧用于训练，以及120个匹配路线对用于闭环评估。每条危险路线在警告和无警告条件下进行评估，而其无危险对照则惩罚无条件制动。我们进一步引入了协作统一评分（CUS），一种安全门控指标，同时奖励路线进展、预判、净空和恢复。对代表性VLM驾驶模型进行微调，将CUS从无警告时的34.6提升至有警告时的75.5，证明了协作警告的价值以及配对协议的分辨能力。所有资源将公开提供。
英文摘要
We present LANTERN, a closed-loop benchmark for temporally grounded cooperative warnings. LANTERN separates warning onset, hazard onset, warning termination, and post-hazard recovery, and evaluates each physical event under matched warning and no-warning executions so that the warning's contribution is measured in isolation rather than confounded with onboard vision. The benchmark spans six safety-critical scenario families and provides 3,272 sequences with 236,309 frames for training, together with 120 matched route pairs for closed-loop evaluation. Each hazard route is evaluated under the warning and no-warning conditions, while its no-hazard control penalizes unconditional braking. We further introduce the Cooperative Unified Score (CUS), a safety-gated metric that jointly rewards route progress, anticipation, clearance, and recovery. Fine-tuning a representative VLM driving model raises CUS from 34.6 without warnings to 75.5 with them, demonstrating both the value of cooperative warnings and the discriminative power of the paired protocol. All resources will be made publicly available.
发表机构
- University of North Texas（北德克萨斯大学）
- Toyota Motor North America, InfoTech Labs（丰田汽车北美公司信息科技实验室）
机构由 AI 辅助整理，请以论文原文为准。
