Use Models with Fewer Points
Update learning algorithm, sensor module, and policy to learn sparser models.
This task relates to the on-going implementation of hierarchically arranged LMs. As these become available, it should become possible to decompose objects into simpler sub-object components, which in turn will enable LMs to model objects with significantly fewer points than the ~2,000 per object currently used.
Help Us Make This Page Better
All our docs are open-source. If something is wrong or unclear, submit a PR to fix it!
Updated 8 days ago