Sim2real, reality gap #275
ndolphin-github
started this conversation in
Debate - Technical topics
Replies: 1 comment
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi,
I am currently using SOFA to transition my custom-built soft robot model into a simulation environment. I have a question regarding the sim2real process.
How can I adjust the scripts in SOFA's Python environment to minimize the reality gap between the simulation model and the actual measured data from the robot? Are there any well-documented methods for setting up SOFA simulations for this purpose?
I am using the latest version of SOFA, v23.06, along with Python 3 libraries. To my knowledge, there are several parameters I can edit, such as the Young's modulus or the Poisson ratio of the material. However, I am uncertain if the reality gap can be significantly reduced by merely adjusting some parameters. Are there any recommended publications that detail the process of sim2real using SOFA?
Beta Was this translation helpful? Give feedback.
All reactions