Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912259898343424 |
|---|---|
| author | Cai, Xuan Bai, Xuesong Cui, Zhiyong Xie, Danmu Fu, Daocheng Yu, Haiyang Ren, Yilong |
| author_facet | Cai, Xuan Bai, Xuesong Cui, Zhiyong Xie, Danmu Fu, Daocheng Yu, Haiyang Ren, Yilong |
| contents | Autonomous driving (AD) testing constitutes a critical methodology for assessing performance benchmarks prior to product deployment. The creation of segmented scenarios within a simulated environment is acknowledged as a robust and effective strategy; however, the process of tailoring these scenarios often necessitates laborious and time-consuming manual efforts, thereby hindering the development and implementation of AD technologies. In response to this challenge, we introduce Text2Scenario, a framework that leverages a Large Language Model (LLM) to autonomously generate simulation test scenarios that closely align with user specifications, derived from their natural language inputs. Specifically, an LLM, equipped with a meticulously engineered input prompt scheme functions as a text parser for test scenario descriptions, extracting from a hierarchically organized scenario repository the components that most accurately reflect the user's preferences. Subsequently, by exploiting the precedence of scenario components, the process involves sequentially matching and linking scenario representations within a Domain Specific Language corpus, ultimately fabricating executable test scenarios. The experimental results demonstrate that such prompt engineering can meticulously extract the nuanced details of scenario elements embedded within various descriptive formats, with the majority of generated scenarios aligning closely with the user's initial expectations, allowing for the efficient and precise evaluation of diverse AD stacks void of the labor-intensive need for manual scenario configuration. Project page: https://caixxuan.github.io/Text2Scenario.GitHub.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02911 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test Cai, Xuan Bai, Xuesong Cui, Zhiyong Xie, Danmu Fu, Daocheng Yu, Haiyang Ren, Yilong Software Engineering Artificial Intelligence Computation and Language Autonomous driving (AD) testing constitutes a critical methodology for assessing performance benchmarks prior to product deployment. The creation of segmented scenarios within a simulated environment is acknowledged as a robust and effective strategy; however, the process of tailoring these scenarios often necessitates laborious and time-consuming manual efforts, thereby hindering the development and implementation of AD technologies. In response to this challenge, we introduce Text2Scenario, a framework that leverages a Large Language Model (LLM) to autonomously generate simulation test scenarios that closely align with user specifications, derived from their natural language inputs. Specifically, an LLM, equipped with a meticulously engineered input prompt scheme functions as a text parser for test scenario descriptions, extracting from a hierarchically organized scenario repository the components that most accurately reflect the user's preferences. Subsequently, by exploiting the precedence of scenario components, the process involves sequentially matching and linking scenario representations within a Domain Specific Language corpus, ultimately fabricating executable test scenarios. The experimental results demonstrate that such prompt engineering can meticulously extract the nuanced details of scenario elements embedded within various descriptive formats, with the majority of generated scenarios aligning closely with the user's initial expectations, allowing for the efficient and precise evaluation of diverse AD stacks void of the labor-intensive need for manual scenario configuration. Project page: https://caixxuan.github.io/Text2Scenario.GitHub.io. |
| title | Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test |
| topic | Software Engineering Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.02911 |