# AutoPreview: A Framework for Autopilot Behavior Understanding

arXiv: https://arxiv.org/abs/2102.13034 · HTML: https://mlsanity.com/paper/2102.13034/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 25 Feb 2021.

## Builds on (most cited first, 8 of 8)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Textual Explanations for Self-Driving Vehicles](https://mlsanity.com/paper/1807.11546/) (2018)
- [TACO: Learning Task Decomposition via Temporal Alignment for Control](https://mlsanity.com/paper/1803.01840/) (2018)
- [Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations](https://mlsanity.com/paper/1912.09007/) (2019)
- [Establishing Appropriate Trust via Critical States](https://mlsanity.com/paper/1810.08174/) (2018)
- [To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles](https://mlsanity.com/paper/2006.11684/) (2020)
- [RoCUS: Robot Controller Understanding via Sampling](https://mlsanity.com/paper/2012.13615/) (2020)
- [How the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games](https://mlsanity.com/paper/1711.06953/) (2017)

## Built on by (most cited first, 2 of 2)

- [A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges](https://mlsanity.com/paper/2211.06665/) (2022)
- [Building Mental Models through Preview of Autopilot Behaviors](https://mlsanity.com/paper/2104.05470/) (2021)

## Abstract (arXiv)

The behavior of self driving cars may differ from people expectations, (e.g. an autopilot may unexpectedly relinquish control). This expectation mismatch can cause potential and existing users to distrust self driving technology and can increase the likelihood of accidents. We propose a simple but effective framework, AutoPreview, to enable consumers to preview a target autopilot potential actions in the real world driving context before deployment. For a given target autopilot, we design a delegate policy that replicates the target autopilot behavior with explainable action representations, which can then be queried online for comparison and to build an accurate mental model. To demonstrate its practicality, we present a prototype of AutoPreview integrated with the CARLA simulator along with two potential use cases of the framework. We conduct a pilot study to investigate whether or not AutoPreview provides deeper understanding about autopilot behavior when experiencing a new autopilot policy for the first time. Our results suggest that the AutoPreview method helps users understand autopilot behavior in terms of driving style comprehension, deployment preference, and exact action timing prediction.