I strongly believe this would improve safety for autonomous vehicles by 1000x.
The “self-driving” infrastructure would not be magically any better than the “human-driving” infrastructure, and how to handle conflicting data from the infra in terms of sensor fusion is not at all clear.
In short, it creates as many problems as it solves, and doesn’t really solve the problems that it sets out to in the real-world.
Even simpler things like supplemental signaling that could be used in special circumstances like road work and emergency vehicles, if they are not used properly and consistently in all cases, it doesn’t change the fact that the system needs to correctly handle these cases internally.
At least we do have a model for this one (physics). I wonder what additional signals the car would need to accurately simulate trash movement? Wind?
And you cannot “play it safe and assume it’ll collide with us”. You get phantom breaking, which is very dangerous.
Trash is irregularly shaped, even with the highest resolution cameras, it’d be impossible to know what the far side of the trash is shaped like. Then on top of that there’s no way to predict highly localized gusts of wind.
The best way to deal with trash is to just have an ML model deal with lots of it so it can make predictions about what it is likely to do (which is basically what Tesla is already doing).