Qwen-Drive-1.0：迈向自动驾驶视觉语言基础模型的初步探索

摘要

我们提出了 Qwen-Drive-1.0，这是迈向自动驾驶视觉语言基础模型的初步探索。Qwen-Drive-1.0 保留了预训练视觉语言模型（VLM）的架构，并在统一框架内整合了三维感知、视觉问答与运动规划。一个外部的鸟瞰图（BEV）感知头联合执行三维目标检测、语义占用预测和 BEV 地图分割。它作为对共享表示中可用三维信息的探针，并为三维场景结构提供显式且可检查的接口。一个规划专家（Planning Expert）以共享的 VLM 表示为条件，生成未来的自车轨迹。分阶段的训练策略将驾驶监督与通用视觉语言数据相结合，以获取驾驶特定能力，同时帮助保持广泛的视觉理解与指令跟随能力。实验表明，该方法展现出强大的三维感知与驾驶场景理解能力，同时在很大程度上保持了通用视觉语言能力。在开环、伪闭环和闭环设置下的综合评估进一步显示，其运动规划性能具有很强的竞争力。

English

We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-language model (VLM) and integrates 3D perception, visual question answering, and motion planning within a unified framework. An external bird's-eye-view (BEV) perception head jointly performs 3D object detection, semantic occupancy prediction, and BEV map segmentation. It serves as a probe of the 3D information accessible from the shared representations and provides an explicit, inspectable interface to 3D scene structure. A Planning Expert conditions on shared VLM representations to generate future ego trajectories. A staged training recipe combines driving supervision with general-purpose vision-language data to acquire driving-specific competence while helping preserve broad visual understanding and instruction-following capabilities. Experiments demonstrate strong 3D perception and driving scene understanding while largely preserving general vision-language capability. Comprehensive evaluations across open-loop, pseudo-closed-loop, and closed-loop settings further show highly competitive motion-planning performance.

Qwen-Drive-1.0：迈向自动驾驶视觉语言基础模型的初步探索

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

摘要

Support