Hacker News Reader

Comment by ssl-3 | Hacker News Reader

I mean, it's good that they're testing things in different places. Environments vary.

But hundreds of millions sounds like enough money to get some industrial or dead commercial space (even in/around SF) and outfit it to be like an apartment. Or six different ones, and six others two weeks from now, and two weeks after that. The cost of the space and the carpenters/painters/drywallers/handymen/managers/whatevers would seem to be something of such relative insignificance that it doesn't even show up on the budgetary radar.

View on HN

They want realistic randomness in the apartment layouts. This is a quick, effective way to get that. If they were honest with the hosts, it wouldn’t even be a bad idea.

Lack of honesty is only one issue. Destroying things, leaving mess and forcing someone else to fix it iw the big one.

And that is very much on brand for these groups.

You don't need that until the very end. They should be modeling many houses first, and they can get that by having employees measure their own house. They should also know something about the edge cases and have a lot of very unrealistic houses modeled.

Then they should have a lab with real furniture and movable walls so they can do controlled real world tests. Once the above tests are done you add confidence with random real world tests.

The types of problems seen here are things that your lab tests should fail and keep you out of real world tests. Particularly when the test subjects don't have some sort of test agreement

I assure you that if randomness is the order of the day, then involving handymen to arrange things is a sure-fire method of getting there.

The cheaper the handymen come, the better the randomness is.

One doesn't even have to tell them to be random; that part happens all on its own in the ways that real apartments ebb and flow.

And the handymen themselves can be rotated out every couple of weeks, as well. The cost of rotation is low. The handymen are plentiful, and they are happy to get hired for a day here or there for literal odd jobs.

(If anyone wants even more practical solutions for robot testing facilities that don't make headlines by pissing people off, please put your contact information in the space provided by pushing the "Reply" button. Thanks!)

Or, just throwing this out there, secretly list their own places and have robots clean up after the guests to evaluate -real places- that have -actually been used-. The key here though is that the places need to be theirs (or at least be a clear contract with the actual owner with full consent and understanding).

A robotics startup at this phase is unlikely to successfully clean an apartment. Usually it’s a lot more about data collection and training. Cleaning an apartment is very hard. The humanoid startup Figure showed their robot moving a few dishes from a nearly empty dishwasher to empty cabinets, and they’re an established company. Actually cleaning is very very hard and the systems are just not very capable yet.

Reply on news.ycombinator.com