arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.14062cs.AIcs.LG
收藏

ChatScene:面向自动驾驶的基于知识的安全关键场景生成

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles

UIUC(伊利诺伊大学厄巴纳-香槟分校);UChicago(芝加哥大学)

Jiawei Zhang, Chejian Xu, Bo Li

AI总结:

提出基于LLM的ChatScene智能体,通过知识检索将文本场景转为代码,生成安全关键场景,提升碰撞率15%,微调模型降低碰撞率9%。

摘要:

我们提出了ChatScene,一种基于大型语言模型(LLM)的智能体,利用LLM的能力为自动驾驶车辆生成安全关键场景。给定非结构化的语言指令,该智能体首先使用LLM生成文本描述的交通场景。随后,这些场景描述被分解为若干子描述,以指定车辆行为和位置等细节。然后,该智能体将文本描述的子场景独特地转换为领域特定语言,进而生成用于模拟器中预测和控制的实际代码,从而促进在CARLA模拟环境中创建多样且复杂的场景。我们智能体的一个关键部分是全面的知识检索组件,该组件通过训练包含场景描述和代码对的知识数据库,高效地将特定文本描述转换为相应的领域特定代码片段。大量实验结果强调了ChatScene在提升自动驾驶车辆安全性方面的有效性。例如,与最先进的基线相比,ChatScene生成的场景在针对不同的基于强化学习的自车进行测试时,碰撞率增加了15%。此外,我们表明,通过使用我们生成的安全关键场景对不同的基于RL的自动驾驶模型进行微调,它们可以实现9%的碰撞率降低,超越了当前的SOTA方法。ChatScene有效地弥合了交通场景文本描述与实际CARLA模拟之间的差距,提供了一种统一的方式,方便地为自动驾驶车辆的安全测试和改进生成安全关键场景。

英文摘要:

We present ChatScene, a Large Language Model (LLM)-based agent that leverages the capabilities of LLMs to generate safety-critical scenarios for autonomous vehicles. Given unstructured language instructions, the agent first generates textually described traffic scenarios using LLMs. These scenario descriptions are subsequently broken down into several sub-descriptions for specified details such as behaviors and locations of vehicles. The agent then distinctively transforms the textually described sub-scenarios into domain-specific languages, which then generate actual code for prediction and control in simulators, facilitating the creation of diverse and complex scenarios within the CARLA simulation environment. A key part of our agent is a comprehensive knowledge retrieval component, which efficiently translates specific textual descriptions into corresponding domain-specific code snippets by training a knowledge database containing the scenario description and code pairs. Extensive experimental results underscore the efficacy of ChatScene in improving the safety of autonomous vehicles. For instance, the scenarios generated by ChatScene show a 15% increase in collision rates compared to state-of-the-art baselines when tested against different reinforcement learning-based ego vehicles. Furthermore, we show that by using our generated safety-critical scenarios to fine-tune different RL-based autonomous driving models, they can achieve a 9% reduction in collision rates, surpassing current SOTA methods. ChatScene effectively bridges the gap between textual descriptions of traffic scenarios and practical CARLA simulations, providing a unified way to conveniently generate safety-critical scenarios for safety testing and improvement for AVs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑