AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 98 references that are in the map. First posted on arXiv 8 Apr 2025.
Builds on
49 of 98 references.
References · 49
- 2017Attention Is All You Needcited by 59,932
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2015Prioritized Experience Replaycited by 1,070
- 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
37 more
- 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
- 2017End-to-end Driving via Conditional Imitation Learningcited by 479
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
- 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 211
- 2016What do different evaluation metrics tell us about saliency models?cited by 184
- 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 147
- 2017Visualizing and Understanding Atari Agentscited by 141
- 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
- 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 101
- 2023ReasonNet: End-to-End Driving with Temporal and Global Reasoningcited by 92
- 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
- 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
- 2017Predicting the Driver's Focus of Attention: the DR(eye)VE Projectcited by 79
- 2019DADA: Driver Attention Prediction in Driving Accident Scenarioscited by 69
- 2017Predicting Driver Attention in Critical Situationscited by 61
- 2019DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmarkcited by 57
- 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
- 2018Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoningcited by 51
- 2020Neuroevolution of Self-Interpretable Agentscited by 48
- 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimizationcited by 44
- 2018AGIL: Learning Attention from Human for Visuomotor Taskscited by 32
- 2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinkingcited by 30
- 2019MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learningcited by 29
- 2020IS-CAM: Integrated Score-CAM for axiomatic-based explanationscited by 29
- 2021Keyframe-Focused Visual Imitation Learningcited by 25
- 2023Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matchingcited by 24
- 2021Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Drivingcited by 21
- 2020Machine versus Human Attention in Deep Reinforcement Learning Taskscited by 16
- 2019Free-Lunch Saliency via Attention in Atari Agentscited by 12
- 2019Gaze Training by Modulated Dropout Improves Imitation Learningcited by 10
- 2021Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learningcited by 9
- 2021Behavioral Research and Practical Models of Drivers' Attentioncited by 9
- 2021MAAD: A Model and Dataset for "Attended Awareness" in Drivingcited by 9
- 2021CoCAtt: A Cognitive-Conditioned Driver Attention Datasetcited by 8
- 2022DReyeVR: Democratizing Virtual Reality Driving Simulation for Behavioural & Interaction Researchcited by 8
- 2024Understanding Disparities in Post Hoc Machine Learning Explanationcited by 6
- 2022Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithmscited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.