Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the LAIA dataset, a synthetic collection designed to enhance end-to-end driving research by incorporating human attention data alongside traditional sensor inputs. By utilizing the CARLA simulator, the dataset captures over 15 hours of driving data from 44 participants across various scenarios, including synchronized eye-tracking and multiple environmental conditions. Key findings reveal that comparing human attention with the perceptual attention of AI models can significantly improve the interpretability and explainability of autonomous driving systems.
Human attention data can dramatically enhance the interpretability of end-to-end driving models, revealing insights that traditional datasets miss.
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.