I don’t know about the equipment of Waymo cars, but I would be surprised if they didn’t have LIDARs or some other form of distance based environment detection.
And that should be sufficient to implement basic obstacle detection. You don’t need to use machine learning if you can use sensors telling you that “something is too close”.
The car collided after hitting the brakes, seems there wasn’t any real damage.
It seems the system is designed to only lessen the impact when it detects the obstacle as non-human.
If it would have recognized the robot as human, it would have probably acted differently.
Better to hit the object and lessen the impact than to fully brake/avoid and risk worse.
I don’t know about the equipment of Waymo cars, but I would be surprised if they didn’t have LIDARs or some other form of distance based environment detection.
And that should be sufficient to implement basic obstacle detection. You don’t need to use machine learning if you can use sensors telling you that “something is too close”.
The article title is misleading as usual.
The car collided after hitting the brakes, seems there wasn’t any real damage. It seems the system is designed to only lessen the impact when it detects the obstacle as non-human. If it would have recognized the robot as human, it would have probably acted differently.
Better to hit the object and lessen the impact than to fully brake/avoid and risk worse.