Asking whether an entity has modeled and evaluated a specific situation, using that evaluation to inform its decisions, is not about subjective experience.
If you're asking whether their training data includes situations like this, and whether their trained model/other pieces of runtime that drive the car include that feature as part of their model, the answer is yes. But not in the way a normal human driver would think about it; many of the details of its decision making process are based on large statistical collections, rather than "I'm in a school zone and need to anticipate children may be obscured and run out into traffic." There are many places where the car needs to take caution without knowing specifically it's within 50 feet of a school zone.
I used to work at a biomedical institution that did cancer treatment experiments on dogs. There was basically a kennel and periodically they would take a dog and irradiate it.
That was fine in the abstract, but there were computational labs above the kennel and periodically you'd just get this huge outporing of dogs barking and howling and it was really hard to get any work done.
In this situation, the car was already driving under the legal speed required for a school zone (25mph when children are present) [edit: some comments in the post suggest there is a 15mph sign, which is sometimes posted; to me, driving 17mph in a 15mph zone is acceptable).
I think any fair evaluation of this (once the data was available) would conclude that Waymo was taking reasonable precautions.
That's exactly part of the problem. If it is programmed to be over-cautious and go 17 in a 25 zone, that feels like it is safe. Is it?
It takes human judgment of the entire big picture to say meaningfully whether that is too slow or too fast. Taking the speed limit literally is too rigid, something a computer would do.
Need to take into account the flow of the kids (all walking in line vs. milling around going in all directions), their age (younger ones are a lot more likely to randomly run off in an unsafe direction), what are they doing (e.g. just walking, vs. maybe holding a ball that might bounce and make them run off after it), their clustering and so on.
Driving past a high school with groups of kids chatting on the sidewalk, sure 20mph is safe enough. Driving past an elementary school with a mass of kids with toys moving in different directions on the same sidewalk, 17mph is too fast.
And if I'm watching some smaller kids disappear behind a visual obstruction that makes me nervous they might pop up ahead of it on the street, I slow down to a crawl until I can clearly see that won't happen.
None of this context is encoded in the "25mph when children are present" sign, but for most humans it is quite normal context to consider.
But would be great to see video of the Waymo scene to see if any of these factors was present.
I think this is one of the expected outcomes of "Science by Press Release" (universities motivated to maximize their grants and IP), combined with media/press that wants clicks (articles that talk about cures for cancer get clicks).
This sounds ethically questionable to me. I wouldn't rule it out entirely, but I'd want to see a well-reasoned argument, both technical and moral, that it was likely to lead to greatly reduced suffering for patients. Even then.... growing a body without a brain likely would not produce a model organism with predictive ability for human diseases.
I believe it could for a large number of tests. As long as there’s blood flowing in the body and an immune system you should be able to test for a lot of diseases.
Cool project, but just how many polygons are you talking about? Also, my guess is you did meshes, instead of breps- they are far more efficient in my experience.
The largest mesh I worked with in Fusion 360 is a digital elevation map of California, it has 2.8M vertices and 5.6M faces and it's still possible to get things done (like making a CAM to carve a 2 foot x 2 foot map with reasonable details).
FreeCAD via AstoCAD (https://www.astocad.com/ - 4€/month) is quite more user friendly too, compared to the vanilla experience, for those who want to do CAD sometimes and forget things between uses. It's made by FreeCAD contributors who push things upstream too.
I see it as a donation to developer who work on FreeCAD, not a "subscription service", just a different way of funding FOSS.
I'd agree that FreeCAD's UI isn't horrible, but it is a lot to take in at a first glance, and for people who don't use it frequently. If I was using it daily, I'd probably prefer FreeCAD as-is too, better feature density and everything at a glance.
The challenge with CAD kernels is mainly in the edge-cases. There's a lot of person-years invested to make the existing kernels robust in weird situations. Those come up surprisingly frequently when modelling.
reply