Motion Policy Networks

Adam Fishman, Adithyavairavan Murali, Clemens Eppner, Bryan Peele, Byron Boots, Dieter FoxZenodo 2022 · DOI · OpenAlex

Abstract

This is the pretrained model, training data set, evaluation problem sets, and sample real robot data accompanying Motion Policy Networks, an end-to-end neural model that can be used to generate collision-free, smooth motion from just a single depth camera observation. The training data set consists of over 3 million motion planning problems for a Franka Panda arm in over 500,000 environments.
BibTeX
@inproceedings{fishman2022motion,
  author = {Adam Fishman and Adithyavairavan Murali and Clemens Eppner and Bryan Peele and Byron Boots and Dieter Fox},
  title = {{Motion Policy Networks}},
  booktitle = {Zenodo},
  year = {2022},
  doi = {10.5281/zenodo.7101781},
}

Loading related content...

Figure