Rendered at 18:14:01 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
donpdonp 11 hours ago [-]
$6,500 for OpenArm v2. Incredibly smooth movement, 4kg of load per arm. Its unclear how far the level of autonomous control has come so far. The video shows mostly tele-operated operation. I have to agree with other comments here that folding laundry is the killer app.
euroderf 9 minutes ago [-]
It's cleaning the dang bathroom.
CompoundEyes 1 hours ago [-]
In the movie Idiocracy they have a dispenser with fresh clothes to put on covered in advertising — assuming free. I’m surprised that doesn’t exist and perhaps made of recycled plastic?
altruios 4 hours ago [-]
Respectfully, that's the corporate-washed killer app.
Intimacy between people in a long distance relationship: that's the killer app.
That's a niche inside a niche. It's a step up from existing solutions, but not an enormous one.
XorNot 2 hours ago [-]
No it's definitely folding laundry.
My intimacy with my partner in a short difference marriage would improved it we could eliminate folding washing from the weekly chores.
moffkalast 10 hours ago [-]
One would expect it to at least have calibration and inverse kinematics solved. That's still a massive pain point for the SO-ARM101 despite it being so common now, since there's no base_link to gripper calibration nor sag compensation and every center offset stacks.
Lerobot banked on having full DL control of each joint so they wouldn't have to do that properly, but now VLAs just use inverse kinematics as a crutch and predict gripper offsets, so we're back to square one.
drapado 9 hours ago [-]
Hi! do you have any references for VLAs using inverse kinematics? I'm very curious and can't find much
moffkalast 9 hours ago [-]
I'm not super up to date on new releases, the one I'm most familiar with is X-VLA which predicts gripper poses and relative movement deltas for kinematics to move to instead of joints, and trains on forward kinematic gripper poses. I think Intern and Octo have the same approach.
PowerElectronix 8 hours ago [-]
I hope someone teaches it to perform a highly sophisticated secret handshake.
phkahler 2 hours ago [-]
Are these stepper motors or torque/force commanded?
teamolHuang 10 hours ago [-]
Finally, automatic hand for single man
subscribed 6 hours ago [-]
That came out more sexist than funny.
5 hours ago [-]
NegativeLatency 12 hours ago [-]
Crosses fingers for a general purpose laundry folding bot
smokel 12 hours ago [-]
We've come a long way from watching 50x speedups [1] to real-time [2] videos of watching robots fold clothes, student-style.
Off-topic, but even though it was 16 years ago, the robot looks so beautiful and well-designed. It looks so aesthetic!
bluebarbet 10 hours ago [-]
To me it does not seem like progress that, on a stressed and finite planet, humanity might "need" an energy- and resource-intensive machine to complete a task as physically undemanding (and even frivolous) as folding a sheet. But here we are.
nater5000 5 hours ago [-]
People are consuming useless plastic toys at an unfathomable rate. It's one example, but it likely contributes so much more to the stress on our planet than actual robots capable of providing actual utility by a huge margin. I'll question the use of humanity's resources once we reel in behaviors like that a bit.
dan-bailey 4 hours ago [-]
You leave my Lego collection out of this.
showerst 5 hours ago [-]
Have a couple of kids and then revisit this comment =). Laundry folding is probably family's most disliked trivial chore, and becomes a non-trivial chore if you have a large family with lots of activities that generate a constant stream of dirty uniforms and gym clothes.
embedding-shape 8 hours ago [-]
I see people taking cars for distances that would take 10-15 minutes to walk. If we're hunting to cut down on inefficiencies, there is a lot of stuff we could attack before a robot arm becomes impactful enough to care about.
brookst 4 hours ago [-]
I genuinely don’t understand this binary thinking. You could easily turn it around: if we’re cutting down on inefficiencies, laundry folding robots will give people more time to exercise.
Or, why bother going to the gym if you don’t eat healthily? Or, why bother eating healthy if you don’t go to the gym.
Not trying to give you a hard time specifically, it’s just a pattern that I feel left out of. If A and B are both improvements over status quo, why does one obviate the other?
King-Aaron 12 hours ago [-]
I just want my laundry folding robot to run slower than me, and not be able to do karate backflips etc in the event of some undesired scope creep happening one day.
nannal 11 hours ago [-]
House scale Faraday cages and an airlock for fiber optics. Should be sufficient until maybe 2032.
mxmilkiib 11 hours ago [-]
I've got a collection of socks needing darning!
brookst 4 hours ago [-]
Oh great now you’re outsourcing the “where the hell did the other sock go and why are there always odd numbers coming out of the dryer” existential crises to AI. Is there no aspect of the human experience you won’t cede to machines?
4 hours ago [-]
officialchicken 7 hours ago [-]
Seriously, Are we nunchaku yet? If so, I would like a Bruce Lee edition in classic yellow.
ethanwillis 11 hours ago [-]
A fully open-source humanoid arm for physical
AI research and deployment in contact-rich
environments.
When will someone release this but for deployment in target-rich environments?
hobofan 9 hours ago [-]
I think in target-rich environments, the humanoid form is pretty easy to beat.
MrPapz 9 hours ago [-]
This would be great to take advanced healthcare like surgery to remote communities!
- "Robots – Comprehensive catalog of 115 humanoid and quadruped robots" re: MJCF in mujoco_menagerie, awesomerobots, robot-descriptions/awesome-robot-descriptions:
https://news.ycombinator.com/item?id=45727432
- I can think of at least one museum that already has interactive demo robot arms that are in need of repair or replacement
NetOpWibby 12 hours ago [-]
One step closer to becoming Adam Jensen
King-Aaron 12 hours ago [-]
Or Smasher, there's a few Adams we're taking steps towards
tsumnia 4 hours ago [-]
You don't say... XD
nicman23 11 hours ago [-]
i asked for this
prometheus1992 5 hours ago [-]
i'm not really sure if people are being sarcastic about laundry folding being the real application of this because I have never felt in my life that i want a robot folding my laundry. i actually love folding my laundry.
slfnflctd 5 hours ago [-]
It's a huge milestone for robotic capabilities more generally. This particular problem has been discussed a ton in robotics communities. It requires a gentle-but-firm grip and extreme dexterity across a wide range of shapes, sizes, weights, densities and material types.
If a somewhat affordable robot can fold some of your laundry in a reasonable amount of time, all of a sudden there are a lot more new and useful things it can do as well. It's a metric.
Plus there are also people who don't like folding laundry. Like me.
prometheus1992 4 hours ago [-]
>>> If a somewhat affordable robot can fold some of your laundry in a reasonable amount of time, all of a sudden there are a lot more new and useful things it can do as well. It's a metric.
I see, is it like arc agi but for robots? wouldn't the companies just laundryfold-maxx their robots then?
throwup238 1 hours ago [-]
That would mean maximizing robotic dexterity, not just control, which means improved hardware. Roboticists would be ecstatic with a laundry-maxxed robot.
slfnflctd 3 hours ago [-]
My current opinion is that trying to 'maxx' in this area (as has been done with other benchmarks) would actually bring enough other use cases with it as a side effect that it would be worthwhile.
Intimacy between people in a long distance relationship: that's the killer app.
https://en.wikipedia.org/wiki/Teledildonics
Uh, the main site appears to be down (and most wouldn't click on the link, given it's name) - but you can read about a project here:
https://en.wikipedia.org/wiki/Brad_Haines
My intimacy with my partner in a short difference marriage would improved it we could eliminate folding washing from the weekly chores.
Lerobot banked on having full DL control of each joint so they wouldn't have to do that properly, but now VLAs just use inverse kinematics as a crutch and predict gripper offsets, so we're back to square one.
[1] https://youtube.com/watch?v=gy5g33S0Gzo
[2] https://www.pi.website/blog/pi0
Or, why bother going to the gym if you don’t eat healthily? Or, why bother eating healthy if you don’t go to the gym.
Not trying to give you a hard time specifically, it’s just a pattern that I feel left out of. If A and B are both improvements over status quo, why does one obviate the other?
- "Robots – Comprehensive catalog of 115 humanoid and quadruped robots" re: MJCF in mujoco_menagerie, awesomerobots, robot-descriptions/awesome-robot-descriptions: https://news.ycombinator.com/item?id=45727432
- I can think of at least one museum that already has interactive demo robot arms that are in need of repair or replacement
If a somewhat affordable robot can fold some of your laundry in a reasonable amount of time, all of a sudden there are a lot more new and useful things it can do as well. It's a metric.
Plus there are also people who don't like folding laundry. Like me.
I see, is it like arc agi but for robots? wouldn't the companies just laundryfold-maxx their robots then?