Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model

Ruan, Bo-Kai, Tsui, Hao-Tang, Li, Yung-Hui, Shuai, Hong-Han

arXiv.org Artificial Intelligence 

Text-to-scene generation, transforming textual descriptions into detailed scenes, typically relies on generating key scenarios along predetermined paths, constraining environmental diversity and limiting customization flexibility. To address these limitations, we propose a novel text-to-traffic scene framework that leverages a large language model to generate diverse traffic scenarios within the Carla simulator based on natural language descriptions. Users can define specific parameters such as weather conditions, vehicle types, and road signals, while our pipeline can autonomously select the starting point and scenario details, generating scenes from scratch without relying on predetermined locations or trajectories. Furthermore, our framework supports both critical and routine traffic scenarios, enhancing its applicability. Experimental results indicate that our approach promotes diverse agent planning and road selection, enhancing the training of autonomous agents in traffic environments. Notably, our methodology has achieved a 16% reduction in average collision rates. Our work is made publicly available at https://basiclab.github.io/TTSG.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found