清華大学と Qwen チーム、自動運転向けビジョン言語基盤モデル「Qwen-Drive」を公開

Qwen-Drive-1.0-4B/          9.1 GB  the VLM, which on its own serves the VQA mode
├── planner-sft/            2.1 GB  Planning Expert, imitation-trained
├── planner-rl/             2.1 GB  Planning Expert after reward optimization
└── perception/             0.5 GB  BEV perception head

model = QwenDriveForPlanning.from_pretrained(
    "Qwen-Drive-1.0-4B", planner="Qwen-Drive-1.0-4B/planner-rl", dtype=torch.bfloat16
)

git clone <repository-url> qwen-drive && cd qwen-drive

# Any Python virtual environment works; conda is shown here
conda create -n qwen-drive python=3.10
conda activate qwen-drive

pip install -e. --no-build-isolation        # or: pip install -r requirements.txt

export PYTHONPATH=src
python scripts/demo.py --model Qwen-Drive-1.0-4B --planner Qwen-Drive-1.0-4B/planner-rl \
    --scenes data/demo/planning_scenes.jsonl --image-archive data/demo/frames.parquet \
    --plot demo.png

import torch
from qwen_drive import InferenceMode, QwenDriveForPlanning
from qwen_drive.benchmarks import read_scene_file
from qwen_drive.images import ImageArchive

model = QwenDriveForPlanning.from_pretrained(
    "Qwen-Drive-1.0-4B",
    planner="Qwen-Drive-1.0-4B/planner-rl",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
).to("cuda").eval()

scene = next(
    read_scene_file(
        "data/demo/planning_scenes.jsonl",
        image_archive=ImageArchive.open("data/demo/frames.parquet"),
    )
).scene

result = model.run(InferenceMode.REASONING_PLANNING, scene=scene, num_samples=6)
print(result.reasoning)
print(result.trajectories.shape)   # (6, 50, 3) -> (x, y, heading), 5 s at 10 Hz

qwen-drive/
├── src/qwen_drive/             # VQA + planning: model, scenes, benchmarks, metrics
├── src/qwen_drive_perception/  # perception mode (+ CUDA kernels under ops/)
├── scripts/                    # demo, prediction and scoring, visualization
├── data/demo/                  # bundled demo scenes and perception frames
├── data/benchmarks/            # the four benchmark scene files (relative frame paths)
├── assets/                     # figures
└── docs/

@misc{zhou2026qwendrive10initialstepvisionlanguage,
      title={Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving},
      author={Xin Zhou and Zongchuang Zhao and Zhibo Yang and Mingsheng Li and Humen Zhong and Shuai Bai and Du Chu and Ruizhe Chen and Zhaohai Li and Jun Tang and Qiuyue Wang and Mingkun Yang and Jiazhao Zhang and Dayiheng Liu and Dingkang Liang and Xiang Bai},
      year={2026},
      eprint={2609.00111},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2609.00111},
}