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.

翻译：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核心挑战，旨在规划安全且舒适的行驶轨迹。现有运动规划器主要依赖启发式方法来预测行驶轨迹，但这类方法在面对新颖且未见过的驾驶场景时表现出泛化能力的不足。本文提出了一种利用大型语言模型（LLM）强大推理能力和泛化潜力的新型运动规划方法。该方法的核心见解是将运动规划重新表述为语言建模问题，这一视角此前未被探索。具体而言，我们将规划器输入与输出表示为语言令牌，并利用LLM通过坐标位置的语言描述生成行驶轨迹。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不仅能描述高精度的轨迹坐标，还能以自然语言呈现其内部决策过程。我们在大规模nuScenes数据集上评估了该方法，大量实验验证了基于GPT的运动规划器的有效性、泛化能力及可解释性。代码现已开源：https://github.com/PointsCoder/GPT-Driver。