NOTES:

  • This paper is the first to introduce the motion taxonomy, a collection of robot-relevant features that can be used to describe actions in a binary-encoded format known as motion codes.
  • We show that motion codes better capture similarity between actions, which is corroborated by similarities based on force and trajectory data.

Citation:

D. Paulius, Y. Huang, J. Meloncon, and Y. Sun (2019). “Manipulation Motion Taxonomy and Coding for Robots”. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE. Macau, China, pp. 5596–5601.