12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      MetaMorph: Learning Universal Controllers with Transformers

      Preprint
      , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Multiple domains like vision, natural language, and audio are witnessing tremendous progress by leveraging Transformers for large scale pre-training followed by task specific fine tuning. In contrast, in robotics we primarily train a single robot for a single task. However, modular robot systems now allow for the flexible combination of general-purpose building blocks into task optimized morphologies. However, given the exponentially large number of possible robot morphologies, training a controller for each new design is impractical. In this work, we propose MetaMorph, a Transformer based approach to learn a universal controller over a modular robot design space. MetaMorph is based on the insight that robot morphology is just another modality on which we can condition the output of a Transformer. Through extensive experiments we demonstrate that large scale pre-training on a variety of robot morphologies results in policies with combinatorial generalization capabilities, including zero shot generalization to unseen robot morphologies. We further demonstrate that our pre-trained policy can be used for sample-efficient transfer to completely new robot morphologies and tasks.

          Related collections

          Author and article information

          Journal
          22 March 2022
          Article
          2203.11931
          fc68dbce-f962-48a1-a723-7fcf783016c3

          http://creativecommons.org/licenses/by/4.0/

          History
          Custom metadata
          ICLR 2022
          cs.LG cs.NE cs.RO

          Robotics,Neural & Evolutionary computing,Artificial intelligence
          Robotics, Neural & Evolutionary computing, Artificial intelligence

          Comments

          Comment on this article