mlsanityData to 7 Oct 2026

Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review

arXiv 2402.10086 ↗First posted 8 Feb 2024cs.RO cs.AI cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) shows promising applications for the perception and planning tasks in autonomous driving (AD) due to its superior performance compared to conventional methods. However, inscrutable AI systems exacerbate the existing challenge of safety assurance of AD. One way to mitigate this challenge is to utilize explainable AI (XAI) techniques. To this end, we present the first comprehensive systematic literature review of explainable methods for safe and trustworthy AD. We begin by analyzing the requirements for AI in the context of AD, focusing on three key aspects: data, model, and agency. We find that XAI is fundamental to meeting these requirements. Based on this, we explain the sources of explanations in AI and describe a taxonomy of XAI. We then identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. Finally, we propose a modular framework called SafeX to integrate these contributions, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 89 of its 206 references that are in the map. First posted on arXiv 8 Feb 2024.

Builds on

89 of 206 references.

References · 89

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  11. 2019Attention is not Explanationcited by 916
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
38 more
  1. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  2. 2019Attention is not not Explanationcited by 629
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  5. 2018The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systemscited by 276
  6. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  7. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 239
  8. 2018Techniques for Interpretable Machine Learningcited by 237
  9. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  10. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  11. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  12. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 211
  13. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  14. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  15. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  16. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  17. 2020Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representationscited by 150
  18. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 144
  19. 2019The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersectionscited by 137
  20. 2022Data Banzhaf: A Robust Data Valuation Framework for Machine Learningcited by 126
  21. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  22. 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
  23. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  24. 2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102
  25. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 99
  26. 2020Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learningcited by 91
  27. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  28. 2020Explainable Object-induced Action Decision for Autonomous Vehiclescited by 88
  29. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  30. 2021Explanations in Autonomous Driving: A Surveycited by 80
  31. 2017Predicting the Driver's Focus of Attention: the DR(eye)VE Projectcited by 79
  32. 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
  33. 2022Impossibility Theorems for Feature Attributioncited by 78
  34. 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
  35. 2019DADA: Driver Attention Prediction in Driving Accident Scenarioscited by 69
  36. 2017Predicting Driver Attention in Critical Situationscited by 61
  37. 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
  38. 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 22; 2026: 17.

52 papers.

Sort:

By area:

  1. 2024AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Drivingcited by 35
  2. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Drivingcited by 32
  3. 2025Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learningcited by 11
  4. 2025CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantificationcited by 9
  5. 2025Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challengecited by 8
  6. 2024Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Drivingcited by 7
  7. 2024Advancing Explainable Autonomous Vehicle Systems: A Comprehensive Review and Research Roadmapcited by 6
  8. 2024Feature Map Convergence Evaluation for Functional Modulecited by 6
  9. 2024TalkWithMachines: Enhancing Human-Robot Interaction for Interpretable Industrial Robotics Through Large/Vision Language Modelscited by 4
  10. 2025Interpretable Decision-Making for End-to-End Autonomous Drivingcited by 4
  11. 2025HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generationcited by 3
  12. 2025Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviourcited by 3
38 more
  1. 2024People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AIcited by 2
  2. 2024Hybrid Convolutional Neural Networks with Reliability Guaranteecited by 2
  3. 2024The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysiscited by 2
  4. 2025PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applicationscited by 2
  5. 2025Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systemscited by 2
  6. 2025VLM-UDMC: VLM-Enhanced Unified Decision-Making and Motion Control for Urban Autonomous Drivingcited by 2
  7. 2026Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraintscited by 2
  8. 2026Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Drivingcited by 2
  9. 2024Real-Time Incremental Explanations for Object Detectors in Autonomous Drivingcited by 1
  10. 2024Explainable deep learning improves human mental models of self-driving carscited by 1
  11. 2025Evaluating Scenario-based Decision-making for Interactive Autonomous Driving Using Rational Criteria: A Surveycited by 1
  12. 2025How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomycited by 1
  13. 2025There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformerscited by 1
  14. 2025Taming Silent Failures: A Framework for Verifiable AI Reliabilitycited by 1
  15. 2025SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identificationcited by 1
  16. 2025Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directionscited by 1
  17. 2026X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehiclescited by 1
  18. 2026An End-to-End Decision-Aware Multi-Scale Attention-Based Model for Explainable Autonomous Drivingcited by 1
  19. 2024The Explanation Necessity for Healthcare AIcited by 0
  20. 2024XAI-based Feature Ensemble for Enhanced Anomaly Detection in Autonomous Driving Systemscited by 0
  21. 2024Methodology for an Analysis of Influencing Factors on 3D Object Detection Performancecited by 0
  22. 2025Compliance of AI Systemscited by 0
  23. 2025What Do People Want to Know About Artificial Intelligence (AI)? The Importance of Answering End-User Questions to Explain Autonomous Vehicle (AV) Decisionscited by 0
  24. 2025Explaining Autonomous Vehicles with Intention-aware Policy Graphscited by 0
  25. 2025UniSTPA: A Safety Analysis Framework for End-to-End Autonomous Drivingcited by 0
  26. 2025Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networkscited by 0
  27. 2025Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Modelscited by 0
  28. 2026Hybrid Approach for Driver Behavior Analysis with Machine Learning, Feature Optimization, and Explainable AIcited by 0
  29. 2026Kinematics-Aware Latent World Models for Data-Efficient Autonomous Drivingcited by 0
  30. 2026Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistancecited by 0
  31. 2026Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehiclescited by 0
  32. 2026Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deploymentcited by 0
  33. 2026A Task-Agnostic Algebraic Integrity Metric for Event-Camera Streams Toward SOTIF-Compliant Perception using Pearson Correlation Coefficientcited by 0
  34. 2026Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safetycited by 0
  35. 2026Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Modelscited by 0
  36. 2026Concept-based Visual Counterfactual Explanations with Diffusion Modelscited by 0
  37. 2026Explainable Reinforcement Learning via Physics-Aware Policy Distillationcited by 0
  38. 2026A Review of Vision-Based Vehicle Detection for UAV-Based Traffic Monitoring: Experimental Insights and Future Directionscited by 0

50 most cited of 52 All 52 (JSON)