Alibaba's Qwen-Drive-1.0 unifies 3D perception and planning, loses under 1 point of general ability
heypearlai · x · 2026-09-07
Qwen released Qwen-Drive-1.0, its first driving model that handles 3D perception, scene question answering and route planning in a single system rather than stitched-together models. Built on Qwen3.5-4B with driving skills added on top and core architecture untouched, Qwen claims it stays within 1 point of the base model's general scores — retaining general capability while learning to drive.
Related event: Alibaba Open-Sources Qwen-Drive-1.0-4B for Autonomous Driving(3 posts)→
More from Embodied
- New tendon-based robotic hand designs trained with PPO to learn one-armed catch — _krishna_murthy · 2026-10-23
- Rivian acquires world model startup Third Dimension to accelerate its self-driving push — emmanuelvivier · 2026-10-23
- Nvidia's Berlin GTC spotlights humanoid robots and Vera Rubin AI supercomputing — emmanuelvivier · 2026-10-23
- XPeng commissions 80%-automated line for IRON humanoid, mass production by end-2026 — ingliguori · 2026-10-23
- HKU's TILDE Distills Embodied Foundation Models into Robot Policies — hkuhk · 2026-10-23
- 10 of 12 Beta Robots Worked Without Fine-Tuning — Do We Still Need It? — micoolcho · 2026-10-23