Live data from Hacker News

Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

norirobotics.com

61–70 of 71 posts

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#61
post #56

The biggest problem is they are using RC style servos. This is why all the arm motions are jerky and lack precision. What this means: No force feedback on positioning. Jerky motion due to actuator steps. Limited precision. Terrible slow motion control performance. Fast movements will look better. Inability to solve problems with software. Basically think of all the joints like those cheap thermal camera screens that…

Well, if it can fold my laundry and do the dishes, then jerky movements don't matter to me. I suppose precision can be fixed with camera feedback. And those force feedback actuators use significantly more power.

For the love of god. You're going to hurt yourself. You don't need to be a robotics expert but, you want your motors to not jitter? Use a robotics library! PLAN the trajectory. The jerk will disappear and lots of other things will disappear. Your trajectory generator will say "sorry, Dave" (throw an exception, they're mostly C++), rather than the robot crashing or hurting you or the battery catching fire (which these servos can easily cause). Basic blind servo control is cool for RC cars but for something this size it definitely isn't.

Don't send raw step changes to the servo positions. Use a trajectory generator that enforces position/velocity/acceleration/jerk limits, ideally use measured joint state (but not available on hobby servos) rather than assuming commanded position was reached, and add hardware-level current/torque/fault limits and a real emergency-stop strategy. Torque/current limiting, if necessary in software, is the minimum here.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#62
post #49

Right, a $1,688 robot that can: - Cook food - Clean up - Bring me stuff from the fridge - Load a dishwasher - Fold clothes So I guess my main question is: What do you hope to accomplish by shamelessly lying? I mean, beyond the lack of shame, you're selling a product here, so are you not at least afraid of the lawsuits? You do know that false advertising is a crime, right? Or I suppose you're just very optimistic and…

> What do you hope to accomplish by shamelessly lying?

YC funding.

> so are you not at least afraid of the lawsuits?

That will happen after the founders "successfully exited" so why would they care.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#63
post #7

Looks cool. Can you be up front about its real capabilities. Are these videos of it eg tidying up real or just staged / cherry picked? If you let it loose in a messy room or stirring something in a kitchen, what are the genuine results you would expect in the wild? We’re all used to seeing things like Atlas back flipping but then can’t do anything in a real environment. Just curious how this fits in and what the succ…

That video of it folding clothes would seem to hint at that. It's only able to awkwardly throw it into a pile, but they still included it. It's clearly a very cool project, but it suggests the claimed capabilities are more show than substance.

I mean, none of the videos show it completing a task successfully as I see it!

1. Doesn't look like it's stirring well enough to prevent burning

2. Seems to just be picking up vertical cans and grabs the napkin unintentially, never see it pick up any of the more interesting shapes/orientations.

3. Doesn't shut the fridge door

4. Teleports to things in it's hand, never see it actually place something in the rack.

5. Not a fold in site, vague wafting of a shirt around

6. Poured a few grains of cereal, not sure it can tell if it's poured the right amount of anything. Doesn't look like a useful result there.

Honestly, it could probably close the fridge. Why they can't show it completing a task in any of their examples is probably not a good sign for the skills situation. It's clear the goal is crowdsourcing the software and providing a platform with no idea whether it can actually do any of these tasks reliably to be useful.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#64
post #61
post #56

Earlier quoted context omitted.

Well, if it can fold my laundry and do the dishes, then jerky movements don't matter to me. I suppose precision can be fixed with camera feedback. And those force feedback actuators use significantly more power.

For the love of god. You're going to hurt yourself. You don't need to be a robotics expert but, you want your motors to not jitter? Use a robotics library! PLAN the trajectory. The jerk will disappear and lots of other things will disappear. Your trajectory generator will say "sorry, Dave" (throw an exception, they're mostly C++), rather than the robot crashing or hurting you or the battery catching fire (which these…

If you're worried about safety: compliance can be implemented outside of the motor, e.g. with springs.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#65
post #63
post #7

Earlier quoted context omitted.

That video of it folding clothes would seem to hint at that. It's only able to awkwardly throw it into a pile, but they still included it. It's clearly a very cool project, but it suggests the claimed capabilities are more show than substance.

I mean, none of the videos show it completing a task successfully as I see it! 1. Doesn't look like it's stirring well enough to prevent burning 2. Seems to just be picking up vertical cans and grabs the napkin unintentially, never see it pick up any of the more interesting shapes/orientations. 3. Doesn't shut the fridge door 4. Teleports to things in it's hand, never see it actually place something in the rack. 5. N…

This was exactly as I was thinking tbh. And the radio silence from them on any reply I think makes this more likely. I don’t want to be a dick if someone’s making something cool, but just be honest about it.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#66
post #64
post #61

Earlier quoted context omitted.

For the love of god. You're going to hurt yourself. You don't need to be a robotics expert but, you want your motors to not jitter? Use a robotics library! PLAN the trajectory. The jerk will disappear and lots of other things will disappear. Your trajectory generator will say "sorry, Dave" (throw an exception, they're mostly C++), rather than the robot crashing or hurting you or the battery catching fire (which these…

If you're worried about safety: compliance can be implemented outside of the motor, e.g. with springs.

Yes, at 100x the cost, so anybody taking the route of using servos is not going to do that either. Plus it's 2026, not 1960, use software.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#67
post #32

Earlier quoted context omitted.

Wow, I have the exact same use case. Just move stuff off the floor so my vacuum robot can run and my life will improve 3-4x. Easy $2000 buy. The matic is being sold as one with better obstacle avoidance and I have no doubt it does but the point is I want the obstacle out away and the floor cleaned underneath.

Having stuff moved off the floor for your robot vacuum will make your life 4 times better?

100%.

Caveat: I have kids.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#68
It looks nice but it also saddens me a bit. You did all the easy and nice work to design a nice form factor and make a nice website, but you left all the hard work for the customer ... Not sure what to think. Maybe if the marketing was more honest (not cherry picked) I would be more positive.

Re: Launch HN: Nori Robotics (YC S26) – A low-cost humanoid robot for development

#69

The biggest problem is they are using RC style servos. This is why all the arm motions are jerky and lack precision. What this means: No force feedback on positioning. Jerky motion due to actuator steps. Limited precision. Terrible slow motion control performance. Fast movements will look better. Inability to solve problems with software. Basically think of all the joints like those cheap thermal camera screens that…

Is it possible to use the PWM signal from some RC servos to measure feedback at the motor?
Post reply on HN