Stocko 🦾

18K posts

Stocko 🦾 banner
Stocko 🦾

Stocko 🦾

@_Stocko_

✦ mastering ai﹠robots ✦ reluctant OpenSCAD+BOSL2 expert ✦ embodied ai ensures prosperity ✦

🇺🇸 Katılım Ocak 2021
1.2K Takip Edilen9.2K Takipçiler
Sabitlenmiş Tweet
Stocko 🦾
Stocko 🦾@_Stocko_·
Day 19: i'm printing the top again to adjust for the width of the bearings in the walls. it's crazy that a 0.4mm nozzle is 8x faster than a 0.2mm
Stocko 🦾 tweet media
English
2
0
12
1.9K
Stocko 🦾
Stocko 🦾@_Stocko_·
i've seen some attempts here on X to do this with a robot (one motor robot), but it ended up with crazy gearing and shafts and stuff. i can't find the account so here's the armatron's drive gears
Stocko 🦾 tweet media
English
2
0
7
664
Stocko 🦾
Stocko 🦾@_Stocko_·
i just had a great but maybe crazy idea
English
3
0
20
675
Stocko 🦾
Stocko 🦾@_Stocko_·
@patrickdoddboy true but i believe they had each selector drive a dof, like forward/back. so you could drive the arm going up and the wrist spinning at the same time
English
0
0
1
9
Patrick
Patrick@patrickdoddboy·
@_Stocko_ Per "selector" I guess is the better way to phrase it. Adds a lot more gearing too
English
1
0
1
8
Oahu Snackbar 🍣
Oahu Snackbar 🍣@Oahu5nackbar·
@_Stocko_ I like thinking about this stuff but I think electric motors are just so simple, cheap, and powerful that there will just be motors everywhere and it will be fine.
English
1
0
0
8
Stocko 🦾
Stocko 🦾@_Stocko_·
@hawkngradiation yeah, but it didn't have to be. i think it was slow because it was a toy. low torque motor, plastic gearing, alkaline batteries, etc.
English
0
0
1
13
Stocko 🦾
Stocko 🦾@_Stocko_·
@Oahu5nackbar yeah, that's the idea. it's like a hybrid between a fully mechanical thing like the armatron and fully electric one-motor-per-dof like most robots are these days
English
1
0
2
8
Stocko 🦾
Stocko 🦾@_Stocko_·
@patrickdoddboy the armatron actually does drive multiple dofs at once, but loses torque of course. which could be compensated for in the joint model i think..
English
1
0
0
13
Patrick
Patrick@patrickdoddboy·
@_Stocko_ Your big drawback is going to be the inability to simultaneously drive two DOF so it's going to have the classic jerky robot movement, and a hard time with dynamic tasks. You can get away with just one motor for the multiplexing tho.
English
1
0
2
14
Stocko 🦾
Stocko 🦾@_Stocko_·
@Oahu5nackbar someone has tried that and it was hard to pull off. i'm talking about keeping the mechanical wizardry in one area and make a 3dof joint out of 1 motor
English
1
0
2
17
Oahu Snackbar 🍣
Oahu Snackbar 🍣@Oahu5nackbar·
@_Stocko_ One central prime mover in the torso and a series of clutches and gear trains driving everything.
English
1
0
0
17
Stocko 🦾
Stocko 🦾@_Stocko_·
so the crazy idea is.. what if you made one 3dof joint out of one big motor plus three tiny servos that activate the drive path like an armatron does?
English
3
0
8
107
Marco Franzon
Marco Franzon@mfranz_on·
@_Stocko_ This is the result after 10mins training, for me it is impressive, immagine do it for real with a real training.
English
1
0
2
77
Marco Franzon
Marco Franzon@mfranz_on·
The future of agriculture lies in optimization. A system like this costs very little: a drone with a camera and a computer vision system accurate enough to count and identify plants or diseases. It's so easy that anyone can make it at home for their own crops.
English
34
73
805
62.5K
Victor M
Victor M@victormustar·
Question for robotics people: how far are we from a ~75cm toy robot that can walk and move around okay-ish (bonus points for claw hands) AND costs around $1 or 2k? Feels like we're technically close, but I haven't seen anything. What am I missing? hardware cost must be the bottleneck?
Victor M tweet media
English
18
4
31
3.4K
Stocko 🦾
Stocko 🦾@_Stocko_·
@Booleans_Things i'll keep building robots. my goal is a robot laborer probably working in my yard
English
1
0
1
7