# From Spoken Thoughts to Automated Driving Commentary: Predicting and Explaining Intelligent Vehicles' Actions

arXiv: https://arxiv.org/abs/2204.09109 · HTML: https://mlsanity.com/paper/2204.09109/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 19 Apr 2022.

## Builds on (most cited first, 9 of 9)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [Explaining Explanations in AI](https://mlsanity.com/paper/1811.01439/) (2018)
- [Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning](https://mlsanity.com/paper/1811.02307/) (2018)
- [Explainable Object-induced Action Decision for Autonomous Vehicles](https://mlsanity.com/paper/2003.09405/) (2020)
- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [The Emerging Landscape of Explainable AI Planning and Decision Making](https://mlsanity.com/paper/2002.11697/) (2020)

## Built on by (most cited first, 8 of 8)

- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [Textual Explanations for Automated Commentary Driving](https://mlsanity.com/paper/2304.08178/) (2023)
- [Advancing Explainable Autonomous Vehicle Systems: A Comprehensive Review and Research Roadmap](https://mlsanity.com/paper/2404.00019/) (2024)
- [From Feature Importance to Natural Language Explanations Using LLMs with RAG](https://mlsanity.com/paper/2407.20990/) (2024)
- [Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness](https://mlsanity.com/paper/2403.14641/) (2024)
- [Effects of Explanation Specificity on Passengers in Autonomous Driving](https://mlsanity.com/paper/2307.00633/) (2023)
- [An End-to-End Decision-Aware Multi-Scale Attention-Based Model for Explainable Autonomous Driving](https://mlsanity.com/paper/2605.00291/) (2026)
- [A Transparency Paradox? Investigating the Impact of Explanation Specificity and Autonomous Vehicle Perceptual Inaccuracies on Passengers](https://mlsanity.com/paper/2408.08785/) (2024)

## Abstract (arXiv)

In commentary driving, drivers verbalise their observations, assessments and intentions. By speaking out their thoughts, both learning and expert drivers are able to create a better understanding and awareness of their surroundings. In the intelligent vehicle context, automated driving commentary can provide intelligible explanations about driving actions, thereby assisting a driver or an end-user during driving operations in challenging and safety-critical scenarios. In this paper, we conducted a field study in which we deployed a research vehicle in an urban environment to obtain data. While collecting sensor data of the vehicle's surroundings, we obtained driving commentary from a driving instructor using the think-aloud protocol. We analysed the driving commentary and uncovered an explanation style; the driver first announces his observations, announces his plans, and then makes general remarks. He also makes counterfactual comments. We successfully demonstrated how factual and counterfactual natural language explanations that follow this style could be automatically generated using a transparent tree-based approach. Generated explanations for longitudinal actions (e.g., stop and move) were deemed more intelligible and plausible by human judges compared to lateral actions, such as lane changes. We discussed how our approach can be built on in the future to realise more robust and effective explainability for driver assistance as well as partial and conditional automation of driving functions.