(video) Wayve GAIA-1 Generating driving scenes previously unseen

To better understand the emerging capabilities of GAIA-1, it is helpful to see it in action.

As a true world model, we can even get GAIA-1 to imagine what might happen in scenarios that it has never been trained on. Here we show that the model can be forced to steer left or right, against its better judgement. The ability of GAIA-1 to predict driving scenes, previously unseen from the scenarios it trained on, shows its ability to extrapolate beyond the data it was trained on, which could aid in the safety evaluation of AI driving models. Safety assurance partly relies on testing driving behaviour in response to corner or “edge case” scenarios. Since these scenarios are rare and too dangerous to test in the real world, simulated testing provides a safer alternative.