发表机构
Computer Vision Center; Computer Science Department of Universitat Autònoma de Barcelona（计算机视觉中心; 巴塞罗那自治大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对自动驾驶端到端驾驶范式的可解释性挑战，提出LAIA数据集，通过CARLA模拟器收集含多种数据的驾驶数据，可用于训练注意力感知模型等多种应用，并用其比较人类与模型注意力以洞察模型行为。
AI 中文摘要
自动驾驶车辆的发展严重依赖数据驱动的人工智能模型，需要大量带真实标注的传感器数据。模块化架构虽广泛使用，但端到端驾驶范式通过直接将传感器输入映射到控制动作提供了有前景的替代方案，不过受限于可解释性挑战。为此我们提出LAIA，一个用人类注意力数据丰富端到端驾驶研究的新型合成数据集。它用CARLA模拟器在闭环环境收集，包含44名参与者在精心设计场景下超过15小时的驾驶数据，每个序列含六种天气条件下的RGB图像等多种数据。LAIA可用于多种应用，本文用它比较人类注意力与端到端驾驶模型中的感知注意力以洞察其行为。
英文摘要
The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of sensor data with ground-truth annotations. While modular architectures are widely used, end-to-end driving paradigms offer a promising alternative by directly mapping sensor inputs to control actions. However, their adoption is limited by challenges in interpretability and explainability. To address this, we present LAIA (Labelled Attention for Intelligent Automobiles), a novel synthetic dataset designed to enrich end-to-end driving research with human attention data. Collected using the CARLA simulator in closed-loop environments, LAIA comprises over 15 hours of driving from 44 participants across carefully crafted scenarios designed to evoke natural responses. Each sequence includes RGB images under six weather conditions, semantic and instance segmentation, depth, optical flow, CAN bus signals, and synchronized eye-tracking data. LAIA enables applications including training attention-aware end-to-end AI drivers, predicting driver behavior, developing methods to detect anomalous driver-attention patterns, and improving model explainability. In this work, we use LAIA to compare human attention with the perceptual attention emerging in our end-to-end driving models, thereby providing insight into their behavior.
Comments11 pages, 12 figures, 3 tables. Dataset and supplementary information available from the project website. Added an author who was inadvertently omitted from the previous version. No changes to the scientific content
