Protoclone: Bipedal, musculoskeletal Android

"closed-loop means open-loop repeatability is not critical"

Hobby servos have limited repeatability especially as they wear, and when swinging an arm with shifting center of mass the errors will be quite obvious.

One may want to look at the UR5 platform design before wasting time and money. Best of luck =3

First I'd like to reproduce the Push-T task of the policy diffusion paper (video here: https://diffusion-policy.cs.columbia.edu/)

Afterwards I'd like to tackle useful tasks related to gardening/botanical experiments: uprooting weeds, handling pests, harvesting small fruits. What's interesting is that you can develop new approaches to these problems. Uprooting stuff is difficult to do for a machine I guess. Maybe just cut the weeds with scissors every day, that'll teach them a lesson. Or remove aphids "by hand".

Another interesting thing is to do more scientific tasks such as handling a lot of tedious tasks on many, many plants. Example: creating polyploid plants is a lot of manual labor, what I'm talking about here is basically lab automation (doing flow cytometry on dozen or even hundred of samples).

Another aspect to explore in this space is continuous measurements (measuring photosynthesis efficiency for instance). I'm not a botanist but it seems that measuring devices either come in the form of a box you put the plant in, and you can get quasi-continuous measurements, or they are hand-held and you can only do punctual measurements (typical example: chlorophyll fluorometry). Also plants grow and change shape so putting a measuring device on a plant is in fact rather difficult. I think something like Aloha (even without the "Mobile" extension) could help tackle these situations.

It's between 20k and 30k dollars. Maybe your profession is suffering from "industrial bias": it focuses only on high-end robotics because it's the only thing that makes sense economically for now and anything super-cheap is seen as laughable ? Wasn't it the case for FDM 3D printer too before they went mainstream in the 2010s ?

I just want to build a toy and explore what's possible with this technology for non-serious applications. The servos may wear too quickly ? I'm fine with that. However I have trouble figuring out how cheap I can go. If I can carry out a task using the "control arm" and the "working arm" performs ok, does that mean Aloha will be able to learn it ? What are the limits then ? What if my arms are really flexible (as flexible as a 10 cm section of a PLA filament for instance), but I manage to carry out the task, can something based on policy diffusion learn to handle the task with "bones" that flex and oscillate ?

Yeah I think of it this way. I have an expensive vacuum and an expensive lawnmower. I paid a lot because they have a pretty dumb level of auto (eg roomba). If I could have bought a commodity push vac and push mower this humanoid could operate it. But they could also serve dozens of other valuable services with cheap existing tools for which no roomba equivalent even exists. At some point being surrounded by purpose built robots is not the best strategy even though when you are only focusing on a single purpose a specialized robot seems best.

Someone made a comment about energy efficiency and Bitcoin and AI should tell you everything about how much “we” actually care about energy efficiency, if this robot had infinite learning potential and the physical ability of a human it’s totally going to win out in the race to mechanize the world.

Just think for a moment on all the unique interfaces we humans encounter with our tools on a daily basis*. No interior in our cars look the same, coffee machines have varying functionalities, every vacuum has its buttons placed differently, all our digital interfaces (smartphones, smart home control panels, digital oscilloscopes, synthesizers etc.), even simple remote controls etc. Some of these interfaces are just some designers choice on top of an already standardized digital protocol (CAN bus, Bluetooth) - so this thing takes the hard way and needs to adapt to all those interfaces in order to be more useful than "can follow you around"?

Honestly, I think that would be quite an achievement and could be great for something like elderly care. Although this thing needs to be able to do useful tactile tasks first, like putting a thread through a pinhole, or cutting your vegetables in cubes of equal size. I'd look forward to seeing a demo!

*: How many things do you personally encounter with the exact same interface? iPhones yes-ish (apps can be renamed and shuffled around, the control center can be customized etc.), but not even QWERTY keyboards. I think we humans constantly strive for some form of individuality.

> If you want a robot to pour you coffee from a coffee maker humans also use, how do you imagine that working?

Two standardised grabbers for round and flat things. Simple three-finger device should cover almost all of the dishes. Same for water/beans refills. Zigbee/wifi/ir/whatever local comms to trigger the coffee machine.