mlsanityData to 13 Oct 2026

Towards Safe, Explainable, and Regulated Autonomous Driving

arXiv 2111.10518 ↗First posted 20 Nov 2021cs.AIcited by 7

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

Abstract (arXiv)

There has been recent and growing interest in the development and deployment of autonomous vehicles, encouraged by the empirical successes of powerful artificial intelligence techniques (AI), especially in the applications of deep learning and reinforcement learning. However, as demonstrated by recent traffic accidents, autonomous driving technology is not fully reliable for safe deployment. As AI is the main technology behind the intelligent navigation systems of self-driving vehicles, both the stakeholders and transportation regulators require their AI-driven software architecture to be safe, explainable, and regulatory compliant. In this paper, we propose a design framework that integrates autonomous control, explainable AI (XAI), and regulatory compliance to address this issue, and then provide an initial validation of the framework with a critical analysis in a case study. Moreover, we describe relevant XAI approaches that can help achieve the goals of the framework.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 25 of its 59 references that are in the map. First posted on arXiv 20 Nov 2021.

Builds on

25 of 59 references.

References · 25

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,434
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,455
  4. 2016End to End Learning for Self-Driving Carscited by 1,002
  5. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 938
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 699
  7. 2017Dynamic Routing Between Capsulescited by 689
  8. 2016The Option-Critic Architecturecited by 439
  9. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 374
  10. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  11. 2019End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordancescited by 149
  12. 2016End-to-end Learning of Driving Models from Large-scale Video Datasetscited by 147
13 more
  1. 2017Visualizing and Understanding Atari Agentscited by 141
  2. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 107
  3. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  4. 2020Unsupervised part representation by Flow Capsulescited by 25
  5. 2018QUOTA: The Quantile Option Architecture for Reinforcement Learningcited by 13
  6. 2015Temporal-Difference Networkscited by 12
  7. 2016VisualBackProp: efficient visualization of CNNscited by 10
  8. 2018Improved Explainability of Capsule Networks: Relevance Path by Agreementcited by 6
  9. 2020Learning predictive representations in autonomous driving to improve deep reinforcement learningcited by 6
  10. 2017An Introduction to Deep Visual Explanationcited by 4
  11. 2017Using KL-divergence to focus Deep Visual Explanationcited by 3
  12. 2020Perception as prediction using general value functions in autonomous driving applicationscited by 3
  13. 2019When is a Prediction Knowledge?cited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 3.

7 papers.

  1. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
  2. 2021Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directionscited by 73
  3. 2024Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Directioncited by 46
  4. 2023A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviorscited by 13
  5. 2022Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Reviewcited by 7
  6. 2024SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarioscited by 3
  7. 2024On the Road to Clarity: Exploring Explainable AI for World Models in a Driver Assistance Systemcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving
  2. 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies
  3. 2022Robust AI Driving Strategy for Autonomous Vehicles
  4. 2025Knowledge Integration Strategies in Autonomous Vehicle Prediction and Planning: A Comprehensive Survey
  5. 2022Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of Experts
  6. 2024Compositionally Safe Construction of Autonomous Driving Systems
  7. 2020A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning
  8. 2024Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning