# Introducing RoadGPT: AI-Powered Scenario Generation for AV Testing

**URL:** <https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402>\
**Category:** Community Research & Projects Spotlight\
**Tags:** beamng-tech\
**Created:** [20 August 2025 09:49 UTC](https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402 "2025-08-20T09:49:37Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![epigova](https://forum.beamng.tech/user_avatar/forum.beamng.tech/epigova/32/18_2.png) [@epigova](https://forum.beamng.tech/u/epigova)\
**Post date:** [20 August 2025 09:49 UTC](https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402/1 "2025-08-20T09:49:38Z")

</div>

We’re excited to share a new research project: **RoadGPT** , a tool that can automatically generate **3D road scenarios for autonomous vehicle testing from simple text descriptions**.

**Highlights:**

- Turns **natural language prompts** into fully functional 3D roads in BeamNG.tech.

- Powered by **OpenAI’s ChatGPT** , combining AI with high-fidelity simulation.

- Validated with expert user studies — showing strong usability and potential.

- Could become a **standard tool for AV scenario creation** , making testing faster and more flexible.

This opens up interesting possibilities for the community: creating custom test scenarios, experimenting with unusual road layouts, or even training AV systems in diverse environments, all from a textual description!

We’d love to hear your thoughts:

- How would you use something like RoadGPT in your projects?

- Any ideas for scenarios you’d like to generate automatically?

**Explore More:**

For a deeper dive into RoadGPT, including access to simulation videos and survey data, visit the [Zenodo repository](https://zenodo.org/records/13918407) and / or check out the paper here: [BeamNG.tech Research](https://beamng.tech/research/)

✍ Authors:  
**[Alessio Gambi](https://www.linkedin.com/in/alessio-gambi-8126072/)**, **[Dejan Nickovic](https://www.linkedin.com/in/dejan-nickovic-4643b962/),** **[Benedikt Steininger](https://www.linkedin.com/in/benedikt-steininger/),** Chrysanthi Papamichail, David Stark

Let’s start a conversation! 🚗💨

---

<div class="post-metadata">

**Author:** ![Neverless](https://forum.beamng.tech/user_avatar/forum.beamng.tech/neverless/32/66_2.png) [@Neverless](https://forum.beamng.tech/u/Neverless)\
**Post date:** [22 August 2025 14:00 UTC](https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402/2 "2025-08-22T14:00:15Z")

</div>

Just wanted to point out that the link to the research paper points to the list of research papers, that however doesnt seem to contain a paper about this project. Maybe im just not looking right?

---

<div class="post-metadata">

**Author:** ![epigova](https://forum.beamng.tech/user_avatar/forum.beamng.tech/epigova/32/18_2.png) [@epigova](https://forum.beamng.tech/u/epigova)\
**Post date:** [25 August 2025 07:07 UTC](https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402/3 "2025-08-25T07:07:55Z")

</div>

Yes, you are right. You can find it under this title “**[Automatically Generating Content for Testing Autonomous Vehicles from User Descriptions](https://conf.researchr.org/details/icse-2025/icse-2025-nier/12/Automatically-Generating-Content-for-Testing-Autonomous-Vehicles-from-User-Descriptio)”.**

---

<div class="post-metadata">

**Author:** ![alfredgu001324](https://forum.beamng.tech/user_avatar/forum.beamng.tech/alfredgu001324/32/111_2.png) [@alfredgu001324](https://forum.beamng.tech/u/alfredgu001324)\
**Post date:** [8 September 2025 21:20 UTC](https://forum.beamng.tech/t/introducing-roadgpt-ai-powered-scenario-generation-for-av-testing/402/4 "2025-09-08T21:20:47Z")

</div>

This would be interesting, previously I saw some BeamNG work that uses NLPs to re-generate scenarios from crash report. It would be nice to see those scenarios being generated with the powerful LLMs we have right now.