Wayve introduces GAIA-4 for closed-loop autonomous-driving simulation
Wayve introduced GAIA-4, a multimodal world model that places the Wayve AI Driver in a closed simulation loop so its actions change the sensor observations it receives next.
Evidence notes
- GAIA-4 reconstructs logged road scenes directly from recorded sensor data without HD maps, hand-built scene graphs or a separate annotation stack.
- Its world-on-rails mode changes the ego vehicle trajectory while holding other road users to their logged behaviour, providing a deterministic comparison baseline.
- The model generates coherent camera and radar observations and also supports reactive-agent scenarios for interactive safety evaluation.
Company context
UK-based autonomous driving company developing end-to-end AI driving systems trained directly from real-world data. Focuses on camera-first autonomy and generalizable driving intelligence deployable across vehicle platforms.