π0.5: A VLA with open-world generalization
1–10 of 47 posts
Re: π0.5: A VLA with open-world generalization
#2By the way, they’ve open-sourced their π0 model (code and model weights). More information can be found here: https://github.com/Physical-Intelligence/openpi
Re: π0.5: A VLA with open-world generalization
#3Re: π0.5: A VLA with open-world generalization
#4Is the robot platform they're using something they've developed themselves? The paper doesn't seem to mention any details outside of sensors and actuators.
Re: π0.5: A VLA with open-world generalization
#5Is the robot platform they're using something they've developed themselves? The paper doesn't seem to mention any details outside of sensors and actuators.
Off the shelf robots -- we've got our models running on dozen+ different robot types (and have this specific generalization demo working on multiple platforms too.)
Re: π0.5: A VLA with open-world generalization
#6This is amazing! As someone working with industrial robots, normally under strict environmental constraints and control, witnessing such real-world robotics progress truly excites me about the future! By the way, they’ve open-sourced their π0 model (code and model weights). More information can be found here: https://github.com/Physical-Intelligence/openpi
Re: π0.5: A VLA with open-world generalization
#7Earlier quoted context omitted.
Off the shelf robots -- we've got our models running on dozen+ different robot types (and have this specific generalization demo working on multiple platforms too.)
Great, would you happen to know what's used in this video?
Re: π0.5: A VLA with open-world generalization
#8Re: π0.5: A VLA with open-world generalization
#9Is it a throughput constraint given too much data from the environment sensors?
Is it processing the data?
I'm curious about where the bottleneck is.
Re: π0.5: A VLA with open-world generalization
#10These variable-length arrays are getting quite advanced