The Limits and Potentials of Deep Learning for Robotics

TL;DR

This paper discusses the unique challenges and opportunities of applying deep learning to robotics, emphasizing the need for better evaluation, simulation, and hybrid approaches to realize its full potential.

Contribution

It provides an overview of robotics-specific issues in deep learning, highlighting evaluation metrics, simulation challenges, and the spectrum of data-driven versus model-driven methods.

Findings

Identifies robotics-specific challenges for deep learning

Highlights the importance of evaluation metrics in robotics

Explores hybrid approaches between data-driven and model-driven methods

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.