# Driving through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving

arXiv: https://arxiv.org/abs/2310.16639 · HTML: https://mlsanity.com/paper/2310.16639/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [End-to-end Learning of Driving Models from Large-scale Video Datasets](https://mlsanity.com/paper/1612.01079/) (2016)
- [DRAMA: Joint Risk Localization and Captioning in Driving](https://mlsanity.com/paper/2209.10767/) (2022)
- [COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning](https://mlsanity.com/paper/2011.00597/) (2020)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [Learning Concise and Descriptive Attributes for Visual Recognition](https://mlsanity.com/paper/2308.03685/) (2023)
- [Grounding Human-to-Vehicle Advice for Self-driving Vehicles](https://mlsanity.com/paper/1911.06978/) (2019)
- [Deep Object-Centric Policies for Autonomous Driving](https://mlsanity.com/paper/1811.05432/) (2018)
- [Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather](https://mlsanity.com/paper/2210.15176/) (2022)
- [Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models](https://mlsanity.com/paper/2310.03182/) (2023)
- [Vehicle trajectory prediction works, but not everywhere](https://mlsanity.com/paper/2112.03909/) (2021)
- [A Commute in Data: The comma2k19 Dataset](https://mlsanity.com/paper/1812.05752/) (2018)
- [End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners](https://mlsanity.com/paper/1803.10158/) (2018)
- [Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning](https://mlsanity.com/paper/2303.00977/) (2023)

## Built on by (most cited first, 9 of 9)

- [Embodied Understanding of Driving Scenarios](https://mlsanity.com/paper/2403.04593/) (2024)
- [Embodied Scene Understanding for Vision Language Models via MetaVQA](https://mlsanity.com/paper/2501.09167/) (2025)
- [Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving](https://mlsanity.com/paper/2409.11182/) (2024)
- [Enhancing Concept Localization in CLIP-based Concept Bottleneck Models](https://mlsanity.com/paper/2510.07115/) (2025)
- [How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons](https://mlsanity.com/paper/2501.06196/) (2024)
- [PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior](https://mlsanity.com/paper/2507.18447/) (2025)
- [Can Multitask Learning Enhance Model Explainability?](https://mlsanity.com/paper/2508.06966/) (2025)
- [When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers](https://mlsanity.com/paper/2605.25304/) (2026)
- [An LLM-Explainable DRL Framework for Passenger-Directed Autonomous Driving](https://mlsanity.com/paper/2606.20640/) (2026)

## Abstract (arXiv)

Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability models can help user acceptance and understanding of decisions made by the autonomous vehicle, which can be used to rationalize and explain driver or vehicle behavior. We propose a new approach using concept bottlenecks as visual features for control command predictions and explanations of user and vehicle behavior. We learn a human-understandable concept layer that we use to explain sequential driving scenes while learning vehicle control commands. This approach can then be used to determine whether a change in a preferred gap or steering commands from a human (or autonomous vehicle) is led by an external stimulus or change in preferences. We achieve competitive performance to latent visual features while gaining interpretability within our model setup.