Qwen-Drive-1.0 connects vision and language for autonomous driving
· By Antonio Sedino, CTRO · Published by Reinventy Solutions Corp.
The project combines 3D perception and visual question answering during pretraining, with an extension to motion planning.
Qwen describes Qwen-Drive-1.0 as a vision-language foundation model for autonomous driving. Built on Qwen3.5-4B, it connects 3D perception and visual question answering during pretraining and extends to motion planning. The account states that two external modules are attached while the pretrained vision-language architecture remains unchanged.