arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.07162cs.ROcs.CL
收藏

像人类一样驾驶:用大型语言模型重新思考自动驾驶

Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

Shanghai AI Lab(上海人工智能实验室);East China Normal University(华东师范大学)

Daocheng Fu, Xin Li, Licheng Wen, Min Dou, Pinlong Cai, Botian Shi, Yu Qiao

AI总结:

本文提出用 LLM 赋予自动驾驶推理、解释与记忆能力,并通过闭环系统验证其处理长尾场景的类人驾驶潜力。

摘要:

在本文中,我们探索了使用大型语言模型(LLM)以类人方式理解驾驶环境的潜力,并分析了其在面对复杂场景时的推理、解释和记忆能力。我们认为,传统的基于优化和模块化的自动驾驶(AD)系统在处理长尾极端情况时面临固有的性能限制。为了解决这一问题,我们提出理想的自动驾驶系统应当像人类一样驾驶,通过持续驾驶积累经验,并运用常识解决问题。为实现这一目标,我们确定了自动驾驶系统所需的三项关键能力:推理、解释和记忆。我们通过构建一个闭环系统来展示 LLM 在驾驶场景中的理解能力和环境交互能力,从而证明了在驾驶场景中采用 LLM 的可行性。大量实验表明,LLM 展现出令人印象深刻的推理和解决长尾案例的能力,为类人自动驾驶的发展提供了宝贵见解。相关代码可在 https://github.com/PJLab-ADG/DriveLikeAHuman 获取。

英文摘要:

In this paper, we explore the potential of using a large language model (LLM) to understand the driving environment in a human-like manner and analyze its ability to reason, interpret, and memorize when facing complex scenarios. We argue that traditional optimization-based and modular autonomous driving (AD) systems face inherent performance limitations when dealing with long-tail corner cases. To address this problem, we propose that an ideal AD system should drive like a human, accumulating experience through continuous driving and using common sense to solve problems. To achieve this goal, we identify three key abilities necessary for an AD system: reasoning, interpretation, and memorization. We demonstrate the feasibility of employing an LLM in driving scenarios by building a closed-loop system to showcase its comprehension and environment-interaction abilities. Our extensive experiments show that the LLM exhibits the impressive ability to reason and solve long-tailed cases, providing valuable insights for the development of human-like autonomous driving. The related code are available at https://github.com/PJLab-ADG/DriveLikeAHuman .

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。

↑