Name
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 helps to fulfill the promising potentials of deep learning in robotics. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1177/0278364918770733 | INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH |
Keywords | DocType | Volume |
Robotics, deep learning, machine learning, robotic vision | Journal | 37 |
Issue | ISSN | Citations |
4-5 | 0278-3649 | 21 |
PageRank | References | Authors |
1.37 | 57 | 11 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Niko Sünderhauf | 1 | 449 | 32.94 |
| Oliver Brock | 2 | 879 | 58.84 |
| Walter J. Scheirer | 3 | 773 | 52.81 |
| R. Hadsell | 4 | 1678 | 100.80 |
| Dieter Fox | 5 | 12306 | 1289.74 |
| Jürgen Leitner | 6 | 104 | 14.05 |
| Ben Upcroft | 7 | 357 | 34.85 |
| Pieter Abbeel | 8 | 6363 | 376.48 |
| W Burgard | 9 | 14438 | 1393.44 |
| Michael Milford | 10 | 1221 | 84.09 |
| Peter I. Corke | 11 | 2495 | 234.29 |