HI version is available. Content is displayed in original English for accuracy.
I started working on Nori while doing robotics research at Columbia. I was teaching robots through human demonstrations, but getting my hands on affordable hardware was difficult. Most labs have one or two expensive robots, which makes it hard to collect large datasets, run long experiments, or test across several robots.
So I built my own. After seven iterations the latest Nori has:
* 19 degrees of freedom
* Two 7+1 DOF arms with a 1.5 kg payload per arm
* A 55 kg telescoping lift
* A differential wheeled base
* Four 720p, 30 fps RGB cameras
* 2D lidar
* A dual microphone array with full-duplex voice communication
* A 432 Wh battery
* A Raspberry Pi 5 with 4 GB RAM (SLAM and safeties are run on board, heavier ACT and VLAs must be run from a computer via LAN or a server via WAN)
Getting this under $2,000 was the main engineering challenge. Nori has more than 100 moving and structural parts, so costs add up quickly across actuators, bearings, wiring, power delivery, and assembly. Some main choices we made to get the cost low was using high-ratio servos instead of QDD motors, and using a wheel base instead of legs.
We assemble each robot in San Francisco and have designed it to be easy to manufacture and repair (we offer 3D files to print repairs).
Our open SDK includes teleoperation and demonstration tools: https://github.com/Nori-Robotics/nori-sdk-py
We also built a browser-based simulator so you can try it out: https://lab.norirobotics.com/nori/model
We’ve shipped our first robot and are building the next batch. Eventually, we want people without robotics experience to teach Nori tasks and share them with other owners.
Currently the hardware is already capable of basic cleaning tasks, opening drawers, restocking shelves and pouring beers. Here is a video of Nori doing things: https://youtube.com/shorts/VRfVXHfQvD8
We make money by selling the hardware for $1,688, with optional paid software on top. Parts of hardware are open source. More details are in our hardware paper: https://doi.org/10.48550/arXiv.2605.16537
If you work in robotics, what would you build with a robot at this price? What would you change about the hardware?
Discussion (43 Comments)Read Original on HackerNews
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 are at 320 x 240 resolution. For rough work or finding some sort of oddity your good, but anything precise you need to spend real money. It's a pretty cool toy, but don't go buying this expecting that much.
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 success / fail rate is.
I'd want to bolt it with a mount to the wall when not in use because it needs to be climb-resistant for children during the daytime when I don't need it functional but there is a solid 8 hour 2200->0700 window when no one will be in the living room and speed is not an issue.
I was talking to my wife about this device and actually the wheeled form factor and (probably) no control software for balance is a feature for our use-case because when the Unitree G1 or whatever falls over the result is catastrophic. The balance control software attempts pure insanity and will likely kill a child nearby.
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.
- nori.ai (ai health coach)
- heynori.com (ai family hub)
- nori inc (soil based carbon sequestration)
- noriagentic.com (that's us, ai cloud infrastructure)
and my personal favorite
- nori.co (makers of 'The Nori Cloud' a clothes steamer, as seen on Oprah's Favorite Things)
I could see myself printing all sorts of costumes for it and using it as an ad hoc characters for tabletop games or as a spare bandmate if I ever finish my synth.
"We make money by selling the hardware for $1,688, with optional paid software on top."
The software would have to be quite good and also affordable for me to consider it, as all subscriptions are liabilities. I might one day want my robot to go with me to a show or to do something meaningful. Whenever that happens I will NOT be held hostage by software and will either source my own software or replace parts of the hardware till something works before I keep throwing money at a bad service. I would prefer to just have a good vendor supported software that I don't have to think about but I have trust issues. Privacy would be a huge concern, I can't have this in my garage lab with all my stuff being sent back to your servers for computer vision tasks etc.
I don't mean to be negative, but making a sustainable business on a hardware race to the bottom sounds challenging.
I'd be curious to to know from others here, what in-home tasks do people think they'll really be able to automate with any of the various bimanual or humanoid robot platforms that seem to be going around?
How is teleoperation anything more than a glorified puppet master pulling the strings or a radio controlled toy car?
At this point, I think with the speed of AI development, the AI will be designing it's own body. It'll be ready to do that before humans figure out how to produce useful bodies.
I can see me doing so many things with this.
Could it put small to medium sized packages in a package room of a condo?
Hopefully upto 24" in any dimension and 5-10 lbs(and ignore the others it can't handle)?
The set up of the small room: three stacked total height 5' rack shelves on both sides and a 2' wide passage in the middle.
Not saying off the shelf but how hard would it be to teach it how to do that?
2. Is the app distributed as an APK outside of the Play Store? Does it have any hard requirements on GMS that would prevent users of degoogled devices from using it?
3. Is every function available through the app possible to perform or recreate with the open SDK? Is this robot (now, and in the future) going to be accessible to technically competent folks who don't own a smartphone at all?
4. Is there a privacy policy on your website for the robot itself? Is there any telemetry? What kind? Will it be recording me without me asking it to? Is the software that ships on it totally open source?
Cool project! I might be quite interested, depending on how much it respects user freedoms and privacy.
The reality: "Good morning sir. Would you care for some assistance getting out of bed?" "Please let me know if I can give you any help with your morning routine." "Your low salt, heart healthy high fiber breakfast is ready now, and I have all your pill bottles lined up on the table for your approval."
The form factor is good which is why multiple companies are building in that form factor. The arm motion will be like a 90 year old with mild Parkinsons. Watch the videos closely and you will notice the issue.
Not sure who the market is here apart from SF tech bros with money to burn.
You know: like the first word in this forum's name.
Got it, sooo.. SF tech bros. I think that humanoid robots are interesting but the real innovation and product-market fit will come figuring out how to do menial household chores (folding clothes is still very much unsolved, for example) as opposed to an ultra-generalized robot that can "do anything."