Why do so many home robots still suck? | Hacker News Reader

Why do so many home robots still suck?

techcrunch.com

14 pointsPaulHoule18 comments

My “litter robot” is one of my favorite purchases, although it’s more like an appliance than a robot. Combined with an air purifier, my home never smells like cat litter.

My Roomba works ok, the mapping feature is neat but it still gets tripped up on small objects, is regularly defeated by cat hair, and doesn’t clean as effectively as a manual vacuum cleaning. I’m glad I have it.

My mopping Roomba is a hassle and I wish I didn’t purchase it.

I really want a textile folding robot but that seems like one of the more difficult robotics problems to solve generally. The dexterity and visual understanding needed is incredibly high.

I've found the Roborock vacuum to be better than Roomba and other brands I've tried. All of these robot vacuums are gonna trip up on something, but mine seems to handle obstacles very well, and its mopping feature is very effective and low hassle.

I use a cheap Chinese one. I've used multiple since all my relatives have one of these, though the brand is always different. They never last more than 2-4 years, either the leg or some mechanism breaks, or the best case, they are battery operated devices so that becomes the issue. The cost to repair tends to be, likely intentionally, expensive enough you are better off buying a new one.

So that's what I do.

It is the only device I'm annoyed with, at the same time, I'd rather have it do it's work than cleaning the house myself.

Robots are hard. Not in the sexbot way, but mechanically difficult with more limitations than people imagine. The more powerful actuators are, e.g. for moving some weirdo humanoid robot, the heavier it is and the more power it will consume. There's no magical way around it. Mechanics also tend to break and will require maintenance, which sounds like a huge hassle. And some rolling "smart" screen loaded with sensors won't set foot, or wheel, in my home. The whole idea is f-ing creepy.

> The more powerful actuators are .. the heavier it is and the more power it will consume.

Point taken. I would expect a bathroom-scrubbing robot to get leverage by anchoring itself against a wall or the commode or something.

I’ve wanted to build a little companion robot that has internet connectivity through wifi and an android phone/tablet as a “face” combined with LLMs and all the other crazy AI tools launched lately to just be able to move around in a room and hold basic kid-friendly conversations. I realize this is probably an iceberg of a project with many complexities, but it does seem like the tooling/infrastructure is available now for something like this

Yes, this seems like a natural extension of the AI advancements over the past few years. I wouldn’t be surprised if there’s already an open-source project that accomplishes exactly this using Legos and Arduino

What things can do a robot in the house apart of vacuuming?

Wash dishes, wash laundry, and dry laundry. All significant labor and time saving devices.

Err, none of these are time consuming activities as there's a machine for each task.

Edit: On a second reading I think that's exactly what you are saying.

I wouldn't mind having a robot butler that is simply tasked with retrieving things, whether it's a drink from the fridge, pills from my medicine cabinet, or a tool I have laying around.

A robot chef would be also be pretty awesome and would pair well with the robot butler.

Inventory!

Keeping it realistic based on current technology I would hope-

Putting dishes in the dishwasher.

Putting laundry baskets of clothes in the washing machine-moving them to the dryer-collecting them and putting them somewhere to be folded (by a human)

Making simple dishes like an omelette or pizza if the ingredients are roughly placed on the counter

Opening the door for the dog

Picking up loose items off the floor so my robovac can clean

Taking the trash and recycling out etc.

Play with the cat ? Firing off paper wads and aluminum foil balls.

What about looking on these tasks through the lens of negentropy? As in how much effort is needed to go from disorder to order.

One can reasonably say the negentropy of collecting little pieces scattered on the ground into a bag is low, even simple draft of air can do most of it. More advanced manipulation of stuff like laundry needs much more of it. And it would help us understand Moravec's paradox.

Maybe it is possible to compare negentrpy required for various activities and focus the robotics r&d on those with lower negentropy first? To provide better optimization gradient than mere guessing.

>> Whoever builds the next great home robot won’t have done so in a vacuum.

Badum-tish.

A lot of old school robotics methods need to die. Older professors who refuse to get with the times are holding the field back. For example, the whole graph-based navigation stack is dumb. Lidar-based SLAM is dumb. The field needs to go all in on AI/ML for navigation, planning, reasoning, language, and everything else.

Well, gee, what do you think sounds better? Building a datacenter, burning gigawatts daily, spending millions in developer hours to train an 'AI' for a few years before you launch your product, and then to maintain said datacenter and its ridiculous energy requirements.

Or, put a 2W microcontroller in each widget and use proven classical methods that can solve the problem locally.

One of these is an obvious choice for anyone who has considered the question for longer than it takes to read 'AI'

Reply on news.ycombinator.com