mlsanityData to 7 Oct 2026

Explainability of deep vision-based autonomous driving systems: Review and challenges

arXiv 2101.05307 ↗First posted 13 Jan 2021cs.CV cs.AI cs.LGcited by 80

Not on the map. Why?

Abstract (arXiv)

This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific to this application. Second, methods providing explanations to a black-box self-driving system in a post-hoc fashion are comprehensively organized and detailed. Third, approaches from the literature that aim at building more interpretable self-driving systems by design are presented and discussed in detail. Finally, remaining open-challenges and potential future research directions are identified and examined.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 189 of its 289 references that are in the map. First posted on arXiv 13 Jan 2021.

Builds on

189 of 289 references.

References · 189

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2013Auto-Encoding Variational Bayescited by 3,980
  11. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  12. 2015VQA: Visual Question Answeringcited by 2,489
38 more
  1. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  2. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  3. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  6. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  8. 2016Generative Adversarial Imitation Learningcited by 1,576
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  10. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  12. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  13. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  14. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  15. 2018Sanity Checks for Saliency Mapscited by 1,149
  16. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  17. 2016End to End Learning for Self-Driving Carscited by 1,000
  18. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  19. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  20. 2019Attention is not Explanationcited by 916
  21. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  22. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  23. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  24. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  25. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  26. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  27. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  28. 2016The Mythos of Model Interpretabilitycited by 716
  29. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  30. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  31. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  32. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  33. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  34. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  35. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  36. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  37. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  38. 2018Pyramid Stereo Matching Networkcited by 486

50 most cited of 189 All 189 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 11; 2023: 20; 2024: 22; 2025: 10; 2026: 2.

80 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  2. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 310
  3. 2022Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baselinecited by 247
  4. 2021Trustworthy AI: From Principles to Practicescited by 206
  5. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  6. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 91
  7. 2021Explanations in Autonomous Driving: A Surveycited by 80
  8. 2023Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveyscited by 75
  9. 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
  10. 2024Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Reviewcited by 52
  11. 2021A Review on Explainability in Multimodal Deep Neural Netscited by 46
  12. 2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
38 more
  1. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  2. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  3. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  4. 2022OCTET: Object-aware Counterfactual Explanationscited by 28
  5. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviorscited by 25
  6. 2021Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Camerascited by 24
  7. 2021SurvNAM: The machine learning survival model explanationcited by 16
  8. 2022Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmarkcited by 16
  9. 2023Explaining Autonomous Driving Actions with Visual Question Answeringcited by 16
  10. 2023Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Modelscited by 15
  11. 2022Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake Systemcited by 14
  12. 2023Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UKcited by 13
  13. 2023Energy-based Potential Games for Joint Motion Forecasting and Controlcited by 9
  14. 2024Research on the Application of Computer Vision Based on Deep Learning in Autonomous Driving Technologycited by 9
  15. 2021Ensembles of Random SHAPscited by 8
  16. 2021Towards Safe, Explainable, and Regulated Autonomous Drivingcited by 7
  17. 2022Slim-neck by GSConv: A lightweight-design for real-time detector architecturescited by 7
  18. 2022LiDAR-as-Camera for End-to-End Drivingcited by 7
  19. 2023Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigationcited by 7
  20. 2023OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detectioncited by 7
  21. 2024Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Drivingcited by 7
  22. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6
  23. 2021Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidentscited by 6
  24. 2021Raising context awareness in motion forecastingcited by 6
  25. 2023Fully Automatic Neural Network Reduction for Formal Verificationcited by 6
  26. 2023Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitationscited by 6
  27. 2024Advancing Explainable Autonomous Vehicle Systems: A Comprehensive Review and Research Roadmapcited by 6
  28. 2024Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencodercited by 6
  29. 2024Feature Map Convergence Evaluation for Functional Modulecited by 6
  30. 2021A Versatile and Efficient Reinforcement Learning Framework for Autonomous Drivingcited by 5
  31. 2024DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Drivingcited by 5
  32. 2024Hierarchical End-to-End Autonomous Driving: Integrating BEV Perception with Deep Reinforcement Learningcited by 5
  33. 2025A Comprehensive LLM-powered Framework for Driving Intelligence Evaluationcited by 5
  34. 2025SurgXBench: Explainable Vision-Language Model Benchmark for Surgerycited by 5
  35. 2022Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimatescited by 4
  36. 2023Towards Pragmatic Semantic Image Synthesis for Urban Scenescited by 4
  37. 2023On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactionscited by 4
  38. 2024Improving Explainable Object-induced Model through Uncertainty for Automated Vehiclescited by 4

50 most cited of 80 All 80 (JSON)