Binh
@pham_blnh
1.4K Following 4K Followers
it took a lot of prep, but i managed to reproduce this
instead of just having astra figure out everything (since i’m token poor), i told it to first do a real2sim of the environment, then move the robot around to check for alignment, then draw
the trajectories will be validated first in sim, then transferred to real
this saves tokens spent and makes astra draw faster
it’s also a proof of how crazy the new model at both few-shot real2sim and robot control
below is an attempt to draw a flower meadow using this method
Show more
just had a quick look at microduck_rl
the codebase is very elegant, i’d recommend reading the agent.md since it contains quite a few fun quirks for reward modeling like
head tracking too tight impairs walking cause the head is 38% of the duck’s weight, so it naturally oscillates -> to solve this, smooth the head tracking error using ema, essentially penalizing only the dc bias
also a few other quirks as you dig deeper into the codebase like how they model the backlash of the motor by adding an unactuated hinge (with very small range) in series with the motor
gg @antoinepirrone
Show more
you don’t need a robot to see physical ai in action, you just need a browser.
this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser.
the result is the first ever demo of ACT that runs locally on the web.
try it yourself now at
Show more
