5th Year Master's Thesis Presentation - Alex Tianyi Xu

— 11:00am

Location:
In Person - Gates Hillman 9115

Speaker:
ALEX TIANYI XU , Master's Student, Computer Science Department, Carnegie Mellon University
https://alextxu.github.io/

Automating Real-to-Sim Traffic Scene Generation with Large Language Models

 Simulation-based evaluation of autonomous driving (AD) offers a scalable and reproducible alternative to real-world testing, yet current scenario generation methods often prioritize coverage over realism. This thesis presents an exploration in enabling open-source models to automatically generate realistic traffic scenarios from natural language descriptions of real-world crashes. I conducted a series of experiments to investigate the effectiveness of different inference-time methods in this domain, and proposed a framework for leveraging these approaches to create a dataset that can be used to finetune open-source models with fewer parameters. I found that open-source models can effectively learn from synthetic data generated by closed-source LLMs in the simulator code generation domain: an open-source model finetuned on this new dataset achieves a 92.5% success rate in generating syntactically correct scenarios. This work demonstrates the feasibility of LLM-assisted scenario reconstruction at scale and lays the foundation for open, realistic, and automated evaluation pipelines for AD algorithms. 

Thesis Committee

Chenyan Xiong (Chair)
Reid Simmons

Additional Information

Add event to Google
Add event to iCal