arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.01415cs.CVcs.AIcs.CLcs.RO
收藏

GPT-Driver:使用 GPT 学习驾驶

GPT-Driver: Learning to Drive with GPT

University of Southern California(南加州大学);Tsinghua University(清华大学)

Jiageng Mao, Yuxi Qian, Junjie Ye, Hang Zhao, Yue Wang

AI总结:

本文提出 GPT-Driver,将运动规划重构为语言建模问题,利用 GPT-3.5 生成坐标轨迹,并通过提示—推理—微调提升数值推理与可解释性。

摘要:

我们提出了一种简单而有效的方法,可将 OpenAI GPT-3.5 模型转化为用于自动驾驶车辆的可靠运动规划器。运动规划是自动驾驶中的一项核心挑战,其目标是规划安全且舒适的驾驶轨迹。现有的运动规划器主要利用启发式方法来预测驾驶轨迹,但这些方法在面对新颖且未见过的驾驶场景时表现出不足的泛化能力。本文中,我们提出了一种新颖的运动规划方法,该方法利用大型语言模型(LLM)固有的强大推理能力和泛化潜力。我们方法的基本洞见是将运动规划重新表述为语言建模问题,这是此前尚未探索的视角。具体而言,我们将规划器的输入和输出表示为语言 token,并利用 LLM 通过对坐标位置的语言描述来生成驾驶轨迹。此外,我们提出了一种新颖的提示—推理—微调策略,以激发 LLM 的数值推理潜力。借助该策略,LLM 能够描述高度精确的轨迹坐标,并以自然语言说明其内部决策过程。我们在大规模 nuScenes 数据集上评估了所提方法,大量实验证实了我们基于 GPT 的运动规划器的有效性、泛化能力和可解释性。代码现已发布于 https://github.com/PointsCoder/GPT-Driver。

英文摘要:

We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs). The fundamental insight of our approach is the reformulation of motion planning as a language modeling problem, a perspective not previously explored. Specifically, we represent the planner inputs and outputs as language tokens, and leverage the LLM to generate driving trajectories through a language description of coordinate positions. Furthermore, we propose a novel prompting-reasoning-finetuning strategy to stimulate the numerical reasoning potential of the LLM. With this strategy, the LLM can describe highly precise trajectory coordinates and also its internal decision-making process in natural language. We evaluate our approach on the large-scale nuScenes dataset, and extensive experiments substantiate the effectiveness, generalization ability, and interpretability of our GPT-based motion planner. Code is now available at https://github.com/PointsCoder/GPT-Driver.

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。

↑