LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Qingyuan, Meng, Qingwen, Cheng, Hao, Xu, Qing, Wang, Jianqiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908584447574016
author Shi, Qingyuan
Meng, Qingwen
Cheng, Hao
Xu, Qing
Wang, Jianqiang
author_facet Shi, Qingyuan
Meng, Qingwen
Cheng, Hao
Xu, Qing
Wang, Jianqiang
contents The generation of testing and training scenarios for autonomous vehicles has drawn significant attention. While Large Language Models (LLMs) have enabled new scenario generation methods, current methods struggle to balance command adherence accuracy with the realism of real-world driving environments. To reduce scenario description complexity, these methods often compromise realism by limiting scenarios to 2D, or open-loop simulations where background vehicles follow predefined, non-interactive behaviors. We propose LinguaSim, an LLM-based framework that converts natural language into realistic, interactive 3D scenarios, ensuring both dynamic vehicle interactions and faithful alignment between the input descriptions and the generated scenarios. A feedback calibration module further refines the generation precision, improving fidelity to user intent. By bridging the gap between natural language and closed-loop, interactive simulations, LinguaSim constrains adversarial vehicle behaviors using both the scenario description and the autonomous driving model guiding them. This framework facilitates the creation of high-fidelity scenarios that enhance safety testing and training. Experiments show LinguaSim can generate scenarios with varying criticality aligned with different natural language descriptions (ACT: 0.072 s for dangerous vs. 3.532 s for safe descriptions; comfortability: 0.654 vs. 0.764), and its refinement module effectively reduces excessive aggressiveness in LinguaSim's initial outputs, lowering the crash rate from 46.9% to 6.3% to better match user intentions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08046
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
Shi, Qingyuan
Meng, Qingwen
Cheng, Hao
Xu, Qing
Wang, Jianqiang
Artificial Intelligence
The generation of testing and training scenarios for autonomous vehicles has drawn significant attention. While Large Language Models (LLMs) have enabled new scenario generation methods, current methods struggle to balance command adherence accuracy with the realism of real-world driving environments. To reduce scenario description complexity, these methods often compromise realism by limiting scenarios to 2D, or open-loop simulations where background vehicles follow predefined, non-interactive behaviors. We propose LinguaSim, an LLM-based framework that converts natural language into realistic, interactive 3D scenarios, ensuring both dynamic vehicle interactions and faithful alignment between the input descriptions and the generated scenarios. A feedback calibration module further refines the generation precision, improving fidelity to user intent. By bridging the gap between natural language and closed-loop, interactive simulations, LinguaSim constrains adversarial vehicle behaviors using both the scenario description and the autonomous driving model guiding them. This framework facilitates the creation of high-fidelity scenarios that enhance safety testing and training. Experiments show LinguaSim can generate scenarios with varying criticality aligned with different natural language descriptions (ACT: 0.072 s for dangerous vs. 3.532 s for safe descriptions; comfortability: 0.654 vs. 0.764), and its refinement module effectively reduces excessive aggressiveness in LinguaSim's initial outputs, lowering the crash rate from 46.9% to 6.3% to better match user intentions.
title LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2510.08046