Hacker News Reader

Comment by umeshunni | Hacker News Reader

The thing I don't get about how most companies are approaching self driving cars is why they are trying to first get them to run on regular roads. It seems like getting them to work well on contained campuses with limited traffic like old age homes, universities, hospitals, corporate campuses etc seem like they'd be ideal places to test and deploy low speed self driving vehicles rather than setting them free on public roads as their first market.

View on HN

From my limited understanding of the technology involved I would guess there's some risk of overfitting.

That is, it requires significant work to train a car to drive period, whether you train it in a relatively "orderly" environment (as we would think of it) or not. However, the training to drive in a chaotic city center should generalize to handle orderly environments, whereas the inverse may not be true.

The whole idea of driverless cars is not to be people movers on tracks, but to actually provide the versatility of a human driver in a car, so getting one that can do "everything a human driver can do" seems like the bar everyone needs to hit for it to be commercially viable.

As far as I can tell, these companies convinced their investors that they're going to be the next Uber, so they need to look like they're making direct progress toward that goal. Driving around a retirement home might seem like a distraction when Tesla claims to be shipping a fully autonomous car by the end of 2019.

Tesla claims things, and this is a perpetually moving goal. IIRC, they first announced it in 2015, to be completed by 2016. Well...I assume it could be a business tactic, to force competitors' energy in this direction, just as you have noted.

I wonder about that too. Is Tesla's corporate campus fully equipped with autonomous vehicles?

The campus is so full of parked cars that there's no space for cars to move, let alone autonomous cars.

The easiest case is freeways. City streets are vastly harder.

That is what the article is about

Reply on news.ycombinator.com