用对话式AI让非程序员也能生成自动驾驶测试场景。
Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles
- 用大模型将自然语言对话转为自动驾驶测试程序。
- 对话交流使测试生成成功率提升4.5倍。
- 适合无编程背景的汽车测试人员使用。
自动驾驶等网络物理系统在部署前需通过仿真测试，使用领域特定程序定义测试场景。为辅助自动驾驶仿真测试，我们设计了一个自然语言接口，基于指令跟随的大规模语言模型，帮助非编程领域的专家生成所需场景与车辆行为。尽管训练数据极小，实验表明将对话转化为符号程序是可行的。人类实验显示，持续对话对成功生成仿真至关重要，相比无对话生成，成功率提高4.5倍。
原文摘要 · Abstract (English)
Cyber-physical systems like autonomous vehicles are tested in simulation before deployment, using domain-specific programs for scenario specification. To aid the testing of autonomous vehicles in simulation, we design a natural language interface, using an instruction-following large language model, to assist a non-coding domain expert in synthesising the desired scenarios and vehicle behaviours. We show that using it to convert utterances to the symbolic program is feasible, despite the very small training dataset. Human experiments show that dialogue is critical to successful simulation generation, leading to a 4.5 times higher success rate than a generation without engaging in extended conversation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。