Here’s an interesting piece from Waymo looking at how the Waymo Driver would handle scenarios from fatal accidents that occurred within the operational area. I’m not at all surprised that it prevented collision as the crash initiator (that’s to be expected), but the fact that it did so well as the responding vehicle shows it’s a very capable defensive driver.
From the paper:
The results of these simulations showed that the Waymo Driver was successful in avoiding all collisions when replacing the crash initiator, that is, the road user who made the initial, unexpected maneuver leading to a collision. Replacing the driver reacting (the responder) to the actions of the crash initiator with the Waymo Driver resulted in an estimated 82% of simulations where a collision was prevented and an additional 10% of simulations where the collision severity was mitigated (reduction in crash-level serious injury risk). The remaining 8% of simulations with the Waymo Driver in the responder role had a similar outcome to the original collision.
I’m excited to see how the SF rollout goes, I think the big question to be answered is on scalability & expanding the geofenced areas so that will be a good test.