Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots

Tanmay Shankar, Yixin Lin, Aravind Rajeswaran, Vikash Kumar, Stuart Anderson, Jean Oh

Keywords: Robot Skills, Unsupervised Correspondences, Unsupervised Learning, Alignment, Density Matching, Skill Learning, Robot Learning, Transfer Learning, Skill Transfer

Abstract:

In this paper, we explore how we can endow robots with the ability to learn correspondences between their own skills, and those of morphologically different robots in different domains, in an entirely unsupervised manner. We make the insight that different morphological robots use similar task strategies to solve similar tasks. Based on this insight, we frame learning skill correspondences as a problem of matching distributions of sequences of skills across robots. We then present an unsupervised objective that encourages a learnt skill translation model to match these distributions across domains, inspired by recent advances in unsupervised machine translation. Our approach is able to learn semantically meaningful correspondences between skills across 3 robot domain pairs despite being completely unsupervised. Further, the learnt correspondences enable the transfer of task strategies across robots and domains.
We present dynamic visualizations of our results at https://sites.google.com/view/translatingrobotskills/home.

One-sentence Summary: We learn unsupervised correspondences between skills across different morphological robots by matching explicit densities of skill sequences.