2026Qwen Team & Huazhong University of Science and Technologyopen source
Qwen-Drive-1.0
v1.0
Autonomous Driving
Vision-Language Model
Qwen-Drive-1.0 is a vision-language foundation model for autonomous driving that integrates 3D perception, visual question answering, and motion planning into a unified framework. It leverages the Qwen3.5-4B vision-language model as a base, attaching specialized heads for BEV perception and trajectory planning to enable comprehensive driving scene understanding and ego-vehicle control.
Unified framework for 3D perception, visual question answering, and motion planning
BEV Perception Head for 3D object detection, semantic occupancy, and map segmentation
Planning Expert utilizing flow matching for future ego trajectory generation