I personally enjoy playing with the progress of autopilot over the years and I'd be sad to see it more restricted.
I understand that it can be unsafe if left unsupervised but in reality I've never met someone who drives like that.
If you offered me a car that drove itself, and statistically, it killed people at the same rate as humans, but let me not have to drive, I'd take that. Nobody everybody agrees.
That's not how it even works though. When people crash or drive drunk there is a system to hand out consequences. What do you do when a Tesla drives into a monorail pole and causes millions in damage if the structural integrity is compromised?
>statistically, it killed people at the same rate as humans
You can't tell me a car that's at best an average not-murderer is a good sell.
There are also so many ways to self-determine your risk while driving or traveling in general. A clear example is seat belts. Less than 10% of people in the US don't wear seat belts but a full 47% of the people that died in car accidents were not wearing one. [1]
Look at the American Gun debate as an example; carrying for self defense makes you drastically less safe by most metrics. But people prefer to have the modicum of self determinism over more consistent statistical safety.
You're probably referencing studies such as Investigating the Link Between Gun Possession and Gun Assault[1], which looked at whether people who were shot were carrying a gun at the time. It did not differentiate between criminals who were carrying illegally and law-abiding citizens who had concealed carry permits. The selection effect in such studies is clear: Many criminals who carry guns are involved in shootings. Also, many people carry guns because they are at a higher risk of being a victim of violent crime. I have yet to find a study that corrects for these confounders.
But the reverse is true. Humans receive driving bans and even criminal penalties for the sort of driving errors autonomous systems make without penalty.