mlsanityData to 14 Oct 2026

Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions

arXiv 2112.11561 ↗First posted 21 Dec 2021cs.AI cs.CYcited by 73

On the map: End-to-end autonomous driving → End-to-end system architecture

Abstract (arXiv)

Autonomous driving has achieved significant milestones in research and development over the last two decades. There is increasing interest in the field as the deployment of autonomous vehicles (AVs) promises safer and more ecologically friendly transportation systems. With the rapid progress in computationally powerful artificial intelligence (AI) techniques, AVs can sense their environment with high precision, make safe real-time decisions, and operate reliably without human intervention. However, intelligent decision-making in such vehicles is not generally understandable by humans in the current state of the art, and such deficiency hinders this technology from being socially acceptable. Hence, aside from making safe real-time decisions, AVs must also explain their AI-guided decision-making process in order to be regulatory compliant across many jurisdictions. Our study sheds comprehensive light on the development of explainable artificial intelligence (XAI) approaches for AVs. In particular, we make the following contributions. First, we provide a thorough overview of the state-of-the-art and emerging approaches for XAI-based autonomous driving. We then propose a conceptual framework that considers the essential elements for explainable end-to-end autonomous driving. Finally, we present XAI-based prospective directions and emerging paradigms for future directions that hold promise for enhancing transparency, trustworthiness, and societal acceptance of AVs.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 96 of its 361 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

96 of 361 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Towards Safe, Explainable, and Regulated Autonomous Driving20 Nov
  2. 2021Autonomy 2.0: Why is self-driving always 5 years away?16 Jul
  3. 2021Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation18 Apr
  4. 2021End-to-end Interpretable Neural Motion Planner17 Jan

Other references · 92

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  10. 2015VQA: Visual Question Answeringcited by 2,506
  11. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
38 more
  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  2. 2016Concrete Problems in AI Safetycited by 1,642
  3. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  4. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  6. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  7. 2016End to End Learning for Self-Driving Carscited by 1,009
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  9. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  10. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 744
  11. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  12. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
  13. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  14. 2016The Option-Critic Architecturecited by 448
  15. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  16. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 397
  17. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  18. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  19. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  20. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 254
  21. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 253
  22. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  23. 2019INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Mapscited by 231
  24. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  25. 2021MP3: A Unified Model to Map, Perceive, Predict and Plancited by 212
  26. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  27. 2016Generating Visual Explanationscited by 158
  28. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 149
  29. 2019Self-Driving Cars: A Surveycited by 148
  30. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  31. 2018Explaining Explanations in AIcited by 137
  32. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  33. 2020A Survey of End-to-End Driving: Architectures and Training Methodscited by 123
  34. 2019Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Modelscited by 118
  35. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 107
  36. 2021Reward (Mis)design for Autonomous Drivingcited by 104
  37. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 103
  38. 2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 25; 2025: 21; 2026: 13.

73 papers.

Sort:

By area:

  1. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 461
  2. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 190
  3. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  4. 2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 91
  5. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  6. 2024Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Reviewcited by 53
  7. 2024Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Directioncited by 46
  8. 2024AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learningcited by 40
  9. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviorscited by 25
  10. 2025Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directionscited by 23
  11. 2023Explaining Autonomous Driving Actions with Visual Question Answeringcited by 16
  12. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 15
38 more
  1. 2025DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Modelscited by 12
  2. 2024CREW: Facilitating Human-AI Teaming Researchcited by 11
  3. 2023Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act?cited by 10
  4. 2024HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Modelcited by 9
  5. 2024Large-scale moral machine experiment on large language modelscited by 9
  6. 2024A Survey on Human-AI Collaboration with Large Foundation Modelscited by 7
  7. 2024Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Drivingcited by 7
  8. 2024Advancing Explainable Autonomous Vehicle Systems: A Comprehensive Review and Research Roadmapcited by 6
  9. 2025Has the Creativity of Large-Language Models peaked? An analysis of inter- and intra-LLM variabilitycited by 6
  10. 2024DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Drivingcited by 5
  11. 2025H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Drivingcited by 5
  12. 2023Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detectioncited by 4
  13. 2025ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systemscited by 4
  14. 2023Navigating Uncertainty: The Role of Short-Term Trajectory Prediction in Autonomous Vehicle Safetycited by 3
  15. 2024ShapG: new feature importance method based on the Shapley valuecited by 3
  16. 2024SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarioscited by 3
  17. 2025TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Modelscited by 3
  18. 2025CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objectscited by 3
  19. 2026Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAscited by 3
  20. 2023Machine Learning Meets Advanced Robotic Manipulationcited by 2
  21. 2024SwapTransformer: highway overtaking tactical planner model via imitation learning on OSHA datasetcited by 2
  22. 2024Incorporating Explanations into Human-Machine Interfaces for Trust and Situation Awareness in Autonomous Vehiclescited by 2
  23. 2024Developing Situational Awareness for Joint Action with Autonomous Vehiclescited by 2
  24. 2024Scene-Aware Explainable Multimodal Trajectory Predictioncited by 2
  25. 2025RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learningcited by 2
  26. 2025Urban Computing in the Era of Large Language Modelscited by 2
  27. 2025TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbationcited by 2
  28. 2025Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanationscited by 2
  29. 2026How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Studycited by 2
  30. 2023STEAM & MoSAFE: SOTIF Error-and-Failure Model & Analysis for AI-Enabled Driving Automationcited by 1
  31. 2024Certified ℓ2 Attribution Robustness via Uniformly Smoothed Attributionscited by 1
  32. 2024Fast Explanations via Policy Gradient-Optimized Explainercited by 1
  33. 2024Real-Time Incremental Explanations for Object Detectors in Autonomous Drivingcited by 1
  34. 2024Explainability in AI Based Applications: A Framework for Comparing Different Techniquescited by 1
  35. 2024Explainable deep learning improves human mental models of self-driving carscited by 1
  36. 2025Safe and Efficient Social Navigation through Explainable Safety Regions Based on Topological Featurescited by 1
  37. 2025Exploring the Impact of Explainable AI and Cognitive Capabilities on Users' Decisionscited by 1
  38. 2025KEPT: Knowledge-Enhanced Prediction of Trajectories from Consecutive Driving Frames with Vision-Language Modelscited by 1

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning
  2. 2023End-to-end Autonomous Driving: Challenges and Frontiers
  3. 2025Knowledge Integration Strategies in Autonomous Vehicle Prediction and Planning: A Comprehensive Survey
  4. 2023Towards Knowledge-driven Autonomous Driving
  5. 2022Exiting the Simulation: The Road to Robust and Resilient Autonomous Vehicles at Scale
  6. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey
  7. 2023Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directions
  8. 2025Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects