Advancements in Autonomous Driving and Eye Tracking

The field of autonomous driving and eye tracking is moving towards enhanced robustness and reliability in adverse weather conditions and complex environments. Researchers are focusing on developing innovative approaches to improve the accuracy and calibration of predictive uncertainty estimates, which is crucial for safety-critical applications. Noteworthy papers in this regard include: Enhancing Self-Driving Segmentation in Adverse Weather Conditions, which introduces a dual uncertainty-aware training approach to improve segmentation robustness. Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation, which shows that mixtures of experts can yield more reliable uncertainty estimates than ensembles. Other notable works include the development of adaptive scoring frameworks for attention assessment in children with Neurodevelopmental Disorders and personalized inhibition training with eye-tracking for educational games.

Sources

Weather-Dependent Variations in Driver Gaze Behavior: A Case Study in Rainy Conditions

Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization

Extracting Uncertainty Estimates from Mixtures of Experts for Semantic Segmentation

Privacy Preservation and Identity Tracing Prevention in AI-Driven Eye Tracking for Interactive Learning Environments

An Adaptive Scoring Framework for Attention Assessment in NDD Children via Serious Games

Personalized Inhibition Training with Eye-Tracking: Enhancing Student Learning and Teacher Assessment in Educational Games

Built with on top of