AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems
This work addresses the problem of enhancing scene understanding and decision-making in autonomous vehicles for improved safety and performance, representing a novel method for a known bottleneck.
This study tackled the challenge of training autonomous vehicles to capture regions of interest for scene understanding by introducing AEGIS, a framework that uses human attention from eye-tracking to guide reinforcement learning models, resulting in improved decision-making as demonstrated with data from 1.2 million frames across six scenarios.
Improving decision-making capabilities in Autonomous Intelligent Vehicles (AIVs) has been a heated topic in recent years. Despite advancements, training machines to capture regions of interest for comprehensive scene understanding, like human perception and reasoning, remains a significant challenge. This study introduces a novel framework, Human Attention-based Explainable Guidance for Intelligent Vehicle Systems (AEGIS). AEGIS utilizes human attention, converted from eye-tracking, to guide reinforcement learning (RL) models to identify critical regions of interest for decision-making. AEGIS uses a pre-trained human attention model to guide RL models to identify critical regions of interest for decision-making. By collecting 1.2 million frames from 20 participants across six scenarios, AEGIS pre-trains a model to predict human attention patterns.