一种感知，所有操作：面向操作级信号意图预测的方向性交通信号理解
One Perception, All Maneuvers: Directional Traffic Signal Understanding for Maneuver-Level Signal Intent Prediction
浏览论文内容
中文总结 AI 辅助
本文提出方向性交通信号理解任务，从单前视图像预测各操作（直行、左右转、掉头）的信号颜色与可通行性，并构建方向级基准与基线，实验证明其优于现有方法，为下游规划提供直接接口。
中文摘要 AI 辅助
交通灯是自动驾驶在城区交叉路口的关键监管信号，然而现有的交通信号感知仍主要被表述为实例级检测或颜色识别。这些表述能识别交通灯的位置及其显示的颜色，但在下游规划之前留下了一个关键的语义空白：每个可见信号控制哪个自车操作，以及该信号对该操作表达的动态许可。在本文中，我们提出了方向性交通信号理解，这是一个面向决策的任务，从前视图像预测直行、左转、右转和掉头操作的结构化信号状态。每个状态包含相关的信号颜色和信号隐含的可通行性。基于OpenLane-V2，我们提供了一个方向级基准，具有操作级监督和用于颜色识别、可通行性、全帧一致性和安全关键错误的指标。一个方向感知基线结合了全局上下文、局部交通灯证据和操作特定表示。实验表明，方向级建模在可通行性预测上优于图像级分类器和检测导向的流水线，特别是在复杂的多信号交叉路口。所得的表示提供了一个直接且可解释的交通信号接口，用于下游规划，结合拓扑、路线和周围智能体信息。
英文摘要
Traffic lights are a key regulatory signal for autonomous driving at urban intersections, yet existing traffic signal perception is still predominantly formulated as instance-level detection or color recognition. Such formulations identify where traffic lights are and what colors they display, but leave a critical semantic gap before downstream planning: which ego maneuver is controlled by each visible signal and what dynamic permission the signal expresses for that maneuver. In this paper, we formulate Directional Traffic Signal Understanding, a decision-oriented task that predicts structured signal states for straight, left-turn, right-turn, and U-turn maneuvers from a front-view image. Each state contains the associated signal color and signal-implied passability. Based on OpenLane-V2, we provide a direction-level benchmark with maneuver-level supervision and metrics for color recognition, passability, full-frame consistency, and safety-critical errors. A direction-aware baseline combines global context, localized traffic-light evidence, and maneuver-specific representations. Experiments show that direction-level modeling improves passability prediction over image-level classifiers and detection-oriented pipelines, particularly at complex multi-signal intersections. The resulting representation provides a direct and interpretable traffic-signal interface for downstream planning together with topology, route, and surrounding-agent information.
