Alibaba's Qwen Team Releases Open-Source Autonomous Driving Model Qwen-Drive-1.0-4B
Alibaba's Qwen team, in collaboration with Huazhong University of Science and Technology, released the open-source autonomous driving model Qwen-Drive-1.0-4B. The model integrates driving scene understanding with vehicle motion planning, built on the Qwen3.5-4B vision-language base with additional 3D perception and trajectory generation components. Two planning variants are offered, one trained via imitation learning and another further optimized with reinforcement learning. Code, model weights, and demo data are available under the Apache 2.0 license.
Alibaba's Qwen team has released the open-source autonomous driving model Qwen-Drive-1.0-4B, which combines driving scene understanding with vehicle motion planning. The model was developed jointly by the Qwen team and Huazhong University of Science and Technology. It uses Qwen3.5-4B as its vision-language foundation and adds dedicated components for 3D perception and driving trajectory generation.
The release includes two versions of the planning component: one trained by imitating driving examples, and another that further optimizes the imitation-based approach through reinforcement learning. Both versions share the same underlying vision-language model, which retains its original architecture and its ability to answer visual questions. The project provides code, model weights, and demo data under the Apache 2.0 license.
Why this event matters
The event has a measured impact on 2 industrys. The strongest current signal is positive for Artificial Intelligence, with intensity 70/100 and 80% confidence over a short term horizon.
Artificial Intelligence
- Direction
- positive
- Intensity
- 70
- Confidence
- 80%
- Horizon
- Short term
New Energy Vehicles
- Direction
- positive
- Intensity
- 60
- Confidence
- 70%
- Horizon
- Medium term
Impact figures are analytical estimates that combine direction, intensity, confidence and event importance. They are not investment advice.