The Limits and Potentials of Deep Learning for Robotics
Robotics
2018-04-19 v1
Abstract
The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluation metrics, highlight the importance and unique challenges for deep robotic learning in simulation, and explore the spectrum between purely data-driven and model-driven approaches. We hope this paper provides a motivating overview of important research directions to overcome the current limitations, and help fulfill the promising potentials of deep learning in robotics.
Keywords
Cite
@article{arxiv.1804.06557,
title = {The Limits and Potentials of Deep Learning for Robotics},
author = {Niko Sünderhauf and Oliver Brock and Walter Scheirer and Raia Hadsell and Dieter Fox and Jürgen Leitner and Ben Upcroft and Pieter Abbeel and Wolfram Burgard and Michael Milford and Peter Corke},
journal= {arXiv preprint arXiv:1804.06557},
year = {2018}
}