Roberto

TUM dropout. Building machines that build anything.

[Roberto @robertorobotics]

Anyone who is looking for Assembly as a service done by Robotic cells?

Let me know. DMs are open.

(currently based in germany. Nextis offers Aaas worldwide)

[Roberto @robertorobotics]

@eigenron The 🐐🐐

[Roberto @robertorobotics]

@archiexzzz @pbshgthm @_Stocko_ Their gripper was inspiration.

[Roberto @robertorobotics]

iterating…

[Roberto @robertorobotics]

@wagecattle i already know 👀

[Roberto @robertorobotics]

@DominiqueCAPaul @JannikGrothusen Yeah i am building small manufacturing cells. The side glasses should arrive tomorrow! Good idea to standardise the env.

[Roberto @robertorobotics]

new top lights arrived. as soon as the side and top frosted glass plates arrive they will be installed for bright diffuse light! (should be tomorrow)

[Roberto @robertorobotics]

@KuphDev 100% excited for this upgrade

[Roberto @robertorobotics]

@perryadong This is what I was looking for. Awesome work!

[Roberto @robertorobotics]

@DominiqueCAPaul @aurel_arnold super cool! This is awesome

[Roberto @robertorobotics]

@DominiqueCAPaul No will need to load the env into isaac sim or mujoco to do that. This is just a movement player.

[Roberto @robertorobotics]

from now on I can replay my recorded datasets in simulation or simulate the policy outputs.

Major key for safety and validation!

will post a video soon 👀

[Roberto @robertorobotics]

@wagecattle @christianhdkwls 👀👀

[Roberto @robertorobotics]

@techietaro Thanks for the advice. Will do some A/B soon. :)

[Roberto @robertorobotics]

With my custom architecture I now achieve on average 60% progress on my gearbox assembly task.

The original average progress of pi0.5 base (after 10k fine tuning) was 14% .

Trajectory of progress is looking good. Now have to reduce the cycle time of iterating on a base policy.

[Roberto @robertorobotics]

@jaikr_x Cool! Yeah i designed them

[Roberto @robertorobotics]

@BrangstrupL @vai_viswanathan no so far only supervised BC, with some smarter conditioning and sampling.

[Roberto @robertorobotics]

@wagecattle @karpathy Also do Elon

[Roberto @robertorobotics]

@DominiqueCAPaul lol

[Roberto @robertorobotics]

everyone benchmarks success rate. the metric that actually determines economic usefulness is TTLNT

-> time to learn new task. and the real unlock is when the policy is substrate-independent: doesn't care which cell it runs on.

[Roberto @robertorobotics]

@DominiqueCAPaul My custom build. They are on my github if you are interested:

https://t.co/k8B2xlWbnF

[Roberto @robertorobotics]

@RohanSeelan Thanks :) 100 episodes!