ITSC 2025 Paper Abstract

Paper WE-EA-T14.4

Cai, Qingchao (Xi'an Jiaotong University), Su, Yuanqi (Xi'an Jiaotong University), Zhang, Xiaoning (Xi’an Jiaotong University), Hu, Hao (China Academy of Railway Sciences Corporation Limited), Lu, HaoAng (Xi'an Jiaotong University)

End-To-End Autonomous Driving Network Guided by Human Perceptual Experience

Scheduled for presentation during the Regular Session "S14b-Human Factors and Human Machine Interaction in Automated Driving" (WE-EA-T14), Wednesday, November 19, 2025, 14:30−14:50, Currumbin

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Keywords Human-Machine Interaction Systems for Enhanced Driver Assistance and Safety, Deep Learning for Scene Understanding and Semantic Segmentation in Autonomous Vehicles

Abstract

Human drivers excel at dynamically prioritizing safety-critical cues through rapid saccadic gaze shifts—an essential capability often lacking in autonomous systems. To address this gap, we propose a human-inspired framework that simulates saccadic gaze behavior to guide visual attention in driving scenarios. Specifically, our {Recurrent Perception Network} iteratively predicts human-like gaze regions via multi-round training, achieving 85% coverage of annotated human gaze points on validation datasets. These gaze maps are then integrated into a novel {Perception-Guided Driving Network}, which employs cascaded attention refinement to amplify safety-critical features. Experimental results demonstrate substantial improvements over baseline methods, including 19% higher driving scores, 81.1% better traffic signal compliance, 83.3% fewer pedestrian collisions and 88.8% reduction in red light violations.

These findings validate that incorporating human perceptual priors enables autonomous systems to adaptively focus on task-relevant regions in a biologically inspired manner. Our approach bridges machine perception with human cognitive strategies, paving the way for safer, human-aligned autonomous driving without sacrificing generalization.