English

Evaluation of state representation methods in robot hand-eye coordination learning from demonstration

Robotics 2019-03-05 v1

Abstract

We evaluate different state representation methods in robot hand-eye coordination learning on different aspects. Regarding state dimension reduction: we evaluates how these state representation methods capture relevant task information and how much compactness should a state representation be. Regarding controllability: experiments are designed to use different state representation methods in a traditional visual servoing controller and a REINFORCE controller. We analyze the challenges arisen from the representation itself other than from control algorithms. Regarding embodiment problem in LfD: we evaluate different method's capability in transferring learned representation from human to robot. Results are visualized for better understanding and comparison.

Keywords

Cite

@article{arxiv.1903.00634,
  title  = {Evaluation of state representation methods in robot hand-eye coordination learning from demonstration},
  author = {Jun Jin and Masood Dehghan and Laura Petrich and Steven Weikai Lu and Martin Jagersand},
  journal= {arXiv preprint arXiv:1903.00634},
  year   = {2019}
}

Comments

submitted to IROS 2019

R2 v1 2026-06-23T07:56:07.429Z