First roadside drive for MOSS, the 3D printed open source litter picking robot. Tarmac, slopes, dry grass, fresh grass, the tracks go through all of it like a small bulldozer, nothing jams. Driven from the pad, straight from the battery switch, no laptop in the loop. Numbers from the... onboard log: over 8 min of driving, over 70 m on each track by the encoders. Pack at 11.68 V at the start, 11.34 V at the stop, roughly 9% of the pack by the resting voltage afterwards. And only about half of the pack is usable before the tracks start stalling in pivots. The motors and the hardware in general held very well. Zero stall guard trips, zero dead pivots. The battery is the weak part, a $20 3S4P pack, 12 cells, sold as 40 Ah and clearly not. Charger and pack get replaced next. Rough estimate with proper high capacity cells: about 50 min and 430 m per charge.show more

Build guide Download CAD & STL files Bill of materials GitHub repository Join the kit waitlist

ngl it's a lot smaller than I thought it was! lol but it's still one of the coolest projects I'm seeing here on X so great job!!

Yep it’s small but you can build it at home and experiment with autonomous navigation and manipulation, cost is exponential in 3D 5 x 5 x 5 = 125 but 10 x 10 x 10 =1’000

this is the kind of open source project that makes people stop scrolling. a robot that actually survives grass is a much better demo than another render.

Need one

🦾

Looking to give this a go Question Any considerations using regular wheels instead of tracks. Thinking it would be quieter indoors, and have more endurance ?

It’s not the tracks that are loud, it’s the gearboxes on the motors. The project is open source: if you want wheels instead of tracks, ask your agent to modify it. Think about the steering first, skid steer doesn’t work well with plain wheels, so the easy path is mecanum wheels. They are a bit expensive, and they don’t fix the gearbox noise. Brushless motors or hub motors with mecanum should be the way to go. On endurance, wheels roll easier than tracks, so you should gain some range. I have no numbers to give you.

@OpenAIDevs So dope

This is so true

lol

I live in Louisiana. Sadly, his bin is not big enough to handle our trash.

It's a first step, the goal is to have a platform for the community to experiment, when robotic trash collection becomes reliable, fast and inexpensive, we will scale it.

were going to need a bigger boat

😀

Are you still running teleop or is it autonomous?

First run outside, teleop only

Looking good. Amazing progress. I'll hit you up in Discord

Awesome, looking forward to it!

Nice work! You mind showing us the view from its own camera. I'd like to know from how far away it can see a piece of trash Are you going to need to put the camera on a pole?

I have no plan to put anything on a pole, the camera is already on the arm

Really cool outdoor demo!

Merci, je vois que vous avez travaillé chez Aldebaran et Parrot, le Disco est le meilleur drone que j’aie possédé, infatigable je l’ai envoyé faire des missions de zinzin. Et je l’ai usé jusqu’au bout. 🦾

En effet, magnifique aile-volante ! Vous devez avoir de belles images embarquées en souvenir.

De la folie, j’ai beaucoup volé sur le lac de la Gruyère, mais c’était surtout cette sensation d’un oiseau majestueux quand il arrivait d’une mission à 15km et fesait son apparition devant ma maison. Rien de technologique ne m’a jamais autant impressionné, dommage que le marché n’ait pas mieux reçu ce produit à l’histoire incroyable, avec son grand frère qui l’a précédé.

Premier vol du @Parrot Disco aux USA, janvier 2016 : quel bel oiseau !

@Parrot Photogrammétrie avec le Disco en 2018

Getting it out onto the roadside with just the pad is a satisfying milestone. Is the next run still focused on driving, or will it include litter pickup too? I’m curious how the stop–grab–carry rhythm changes that endurance estimate compared with continuous driving.

not to be snarky, but maybe don't add title it a "litter picking up robot" when it shows NO interest in dealing with litter ;>

🤡

Achieving robust locomotion across diverse terrain without complex control suggests a strong mechanical design. How scalable is this design for more delicate or uneven environmental debris?

Roadside is its favorite territory

Pivot stalls make peak current delivery important alongside capacity. Comparing pack-terminal voltage with motor-driver input voltage during the same pivot can help separate pack sag from cable and connector losses.

Tell it to stop being lazy! 😂

40 Ah from 4 cells in parallel is 10 Ah a cell, even good 21700s top out around 5

3s4p is 3x4, so it's 12 cells. It's possible to pack 40Ah at 3.6v 0r 13Ah at 12v, it's just these cheap batteries are not 3600mAh or 5000mAh, they most likely use 1200mAh, very light stuff you can feel haha, almost a scam.

A 3D-printed, open-source robot picking up litter on real roads — this is the kind of robotics progress I can get behind.

he’s very cute but when will he pick up anything