核心信息
Qwen 推出 Qwen-Drive-1.0-4B，这是一个采用 Apache 2.0 许可证的自动驾驶视觉语言基础模型，在单一框架内完成 3D 感知、驾驶 VQA 和运动规划，同时保持 Qwen3.5-4B 主干网络完全不变。
要点
- 通过两个即插即用模块实现驾驶能力：BEV 头负责 3D 感知，流匹配 Planning Expert 负责轨迹生成。
- 在驾驶 VQA 评测中表现领先，如 LingoQA 上取得 77.8 分，并实现最低的 Ego3D 距离误差。
Qwen 进军自动驾驶：发布 Qwen-Drive-1.0-4B
原始推文
RT @ModelScope2022: Qwen just stepped into autonomous driving! 🚗 Qwen-Drive-1.0-4B is a vision-language foundation model that handles 3D perception, driving VQA, and motion planning in one framework, with the Qwen3.5-4B backbone left fully unmodified. Apache 2.0. 🤖 https://t.co/dWXStVVlQA ⚙️ Two plug-in modules do the driving: a BEV head for 3D perception, and a flow matching Planning Expert for trajectories. 📊 Leads driving VQA across the board: 77.8 on LingoQA, lowest Ego3D distance error, and 41.3 on causal reasoning where others score under 5. 🏁 The RL planner hits 90.7 PDMS on NAVSIM, ahead of AutoVLA and SpanVLA. 🧠 No catastrophic forgetting: general benchmarks stay on par with the base model.