Can this algorithm be adapted to new UR5?

andyzeng / visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

http://vpg.cs.princeton.edu/

BSD 2-Clause "Simplified" License

883 stars 314 forks source link

Can this algorithm be adapted to new UR5? #82

Open gsbandy24 opened 3 years ago

gsbandy24 commented 3 years ago

I am attempting to replicate the results here for my studies while applying the algorithm to more unique/novel objects in real world testing.

However, it was just explained to me that the code used by A. Zeng was for a very old UR5 firmware and the communication message format is radically different from any UR robot with recent firmware.

Does anyone know how difficult/how possible it is to make VPG for a ur bot with newly updated firmware