TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Learning bimanual mobile manipulation with low-cost whole-body teleoperation

126 pointsby tristenharrover 1 year ago

12 comments

xg15over 1 year ago
I was wondering if at some point an evolution of &quot;cloud kitchens&quot; could be &quot;edge kitchens&quot;:<p>Imagine a high-end apartment or condo building. In the basement of the building, there is a fully equipped professional kitchen - however, it&#x27;s not supposed to be used by humans. Instead, the kitchen is fully automated with smart&#x2F;wired-up devices wherever possible. The actual chopping, cooking etc is performed by robotic arms like the ones in the OP. The kitchen has a human-accessible storeroom on one end (that must be regularly restocked by the condo administration) and is connected to the apartments by a system of service lifts.<p>Residents can order food through a an appliance or an app or something and choose from some menu of predefined meals (or possibly even create their own recipes through some sort of building block system). Once they submitted the order (and all ingredients are available), the kitchen springs into action, prepares the dish and places it in a service elevator. In the apartment, the dish appears, fresh and hot, like right out of a Star Trek replicator.<p>I guess we&#x27;ve just gotten one step closer to that vision :)
tristenharrover 1 year ago
The coolest thing to me was watching it do laundry in the video it takes a jacket and puts it on a hanger and then zips the jacket. Watching it get the zipper was pretty satisfying.<p>It’s also amazing that there’s just instructions and it’s open to anyone. Kudos to the builders. They sauté shrimp, do laundry, and wash dishes with this robot you can build at home.<p>If that isn’t cool I don’t know what is.
评论 #38877872 未加载
evanjrowleyover 1 year ago
The video recordings give me the impression that piloting this robot to perform mundane household tasks is much more fun than doing so in real life.
评论 #38877488 未加载
btbuildemover 1 year ago
Look, it&#x27;s the perfect roommate!<p>Jokes aside -- something like this could be a fantastic breakthrough for people who&#x27;ve lost the use of their limbs. A wearable &#x2F; chair-attached exo, driven to do complex tasks through simple commands.
评论 #38879605 未加载
canadiantimover 1 year ago
ah I thought we were this close |---| to &quot;low-cost whole-body teleportation&quot;.
评论 #38877211 未加载
评论 #38877560 未加载
jamestimminsover 1 year ago
Can someone with expertise explain why this is so difficult?<p>As an outsider with no knowledge of robotics, I&#x27;ve always been surprised that manipulation tasks (or just smooth robotic movement) are so challenging and seem to progress so slowly, especially when compared to IT.
评论 #38876594 未加载
评论 #38878656 未加载
评论 #38876692 未加载
评论 #38877412 未加载
regularfryover 1 year ago
Well, they got the most critical component correct: an appropriate number of googly eyes is vital for this sort of application.
YeGoblynQueenneover 1 year ago
Just for some context here&#x27;s a video of &quot;outtakes&quot; from the authors:<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;tonyzzhao&#x2F;status&#x2F;1743378437174366715" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;tonyzzhao&#x2F;status&#x2F;1743378437174366715</a><p>In another tweet [1] the authors give a count of the successful (but not the failed) attempts at various tasks:<p><pre><code> Our robot can consistently handle these tasks, succeeding: - 9 times in a row for Wipe Wine - 5 times for Call Elevator - robust against distractors for Use Cabinet - extrapolate to chairs unseen during training </code></pre> <a href="https:&#x2F;&#x2F;twitter.com&#x2F;zipengfu&#x2F;status&#x2F;1742602883256943040" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;zipengfu&#x2F;status&#x2F;1742602883256943040</a><p>___________________<p>[1] How do you call those now? Exes?
评论 #38893003 未加载
1letterunixnameover 1 year ago
Baby steps. I wouldn&#x27;t give a human-operated robot control of dangerous tasks now, but some less dangerous tasks would be okay. Eventually, through iteration, the interfaces, robots, and operators will improve to where full body teleoperation, AI-assisted, and AI-operated robots will be achieved.
rattatosskover 1 year ago
I can just see it now. Massacre. All the oil from the pan in the plate. Set the hot pan down on the counter top.
评论 #38878637 未加载
Wingman4l7over 1 year ago
...or they&#x27;ll just cut out the behavior training part, and we&#x27;ll have <i>Sleep Dealer</i>: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Sleep_Dealer" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Sleep_Dealer</a>
YeGoblynQueenneover 1 year ago
That&#x27;s all kind of pathetically underwhelming. The video is at 6x speed and the robot is shown pushing some chairs forward, placing a pot in an empty cupboard and ... frying one prawn? <i>One prawn</i>?<p>All those are toy tasks that have no application in a real environment, even the constrained and save environment of a home. Most homes don&#x27;t have such large empty spaces. Most of the time when you need to tidy up a bunch of chairs they&#x27;re not put in a neat straight line by a RA, they&#x27;re left in a jumbled mess by a stampede of students and you have to do a lot more pushing and pulling and turning around (and there&#x27;s tables and possibly empty cups and stuff). Most of the time you need to cook a lot more than one measly prawn. And let&#x27;s not talk about the primordial chaos of kitchen cupboards.<p>What&#x27;s worse with all those demonstrations: the robots can only do exactly what you see in the video. Change the parameters even slightly: different shape pan, different height cupboard, different room configuration; and the magick -poof- vanishes, into thin air.<p>That stuff doesn&#x27;t work. We aren&#x27;t even close to solving autonomous robotic behaviour. RL doesn&#x27;t work and the older techniques aren&#x27;t working either (planning). All that stuff ever does is get published into papers, advertised with fanfare and then forgotten because it never makes it to the real world, because it&#x27;s all unreliable and unpredictable and costs too much if you want to do anything real, and that&#x27;s always something trivial. So the state-of-the-art in robotics is in hand-coded industrial robots that do one thing and do it over and over again and nobody asks them to generalise, or to come into your house and cook you a prawn.
评论 #38878205 未加载
评论 #38879584 未加载
评论 #38878971 未加载