Open Access
Open access

Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning

Staroverov A., Yudin D.A., Belkin I., Adeshkin V., Solomentsev Y.K., Panov A.I.
Тип документаJournal Article
Дата публикации2020-12-02
Название журналаIEEE Access
ИздательIEEE
КвартильQ1
ISSN21693536
  • General Materials Science
  • General Engineering
  • General Computer Science
Краткое описание
In the last years, deep learning and reinforcement learning methods have significantly improved mobile robots in such fields as perception, navigation, and planning. But there are still gaps in applying these methods to real robots due to the low computational efficiency of recent neural network architectures and their poor adaptability to robotic experiments’ realities. In this article, we consider an important task in mobile robotics - navigation to an object using an RGB-D camera. We develop a new neural network framework for robot control that is fast and resistant to possible noise in sensors and actuators. We propose an original integration of semantic segmentation, mapping, localization, and reinforcement learning methods to improve the effectiveness of exploring the environment, finding the desired object, and quickly navigating to it. We created a new HISNav dataset based on the Habitat virtual environment, which allowed us to use simulation experiments to pre-train the model and then upload it to a real robot. Our architecture is adapted to work in a real-time environment and fully implements modern trends in this area.
Цитируется в публикациях: 11
Метрики
Поделиться
Цитировать
ГОСТ |
Цитировать
1. Staroverov A. и др. Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning // IEEE Access. 2020. Т. 8. С. 195608–195621.
RIS |
Цитировать

TY - JOUR

DO - 10.1109/access.2020.3034524

UR - http://dx.doi.org/10.1109/ACCESS.2020.3034524

TI - Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning

T2 - IEEE Access

AU - Staroverov, Aleksey

AU - Yudin, Dmitry A.

AU - Belkin, Ilya

AU - Adeshkin, Vasily

AU - Solomentsev, Yaroslav K.

AU - Panov, Aleksandr I.

PY - 2020

PB - Institute of Electrical and Electronics Engineers (IEEE)

SP - 195608-195621

VL - 8

SN - 2169-3536

ER -

BibTex |
Цитировать

@article{Staroverov_2020,

doi = {10.1109/access.2020.3034524},

url = {https://doi.org/10.1109%2Faccess.2020.3034524},

year = 2020,

publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},

volume = {8},

pages = {195608--195621},

author = {Aleksey Staroverov and Dmitry A. Yudin and Ilya Belkin and Vasily Adeshkin and Yaroslav K. Solomentsev and Aleksandr I. Panov},

title = {Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning},

journal = {{IEEE} Access}

}

MLA
Цитировать
Staroverov, Aleksey et al. “Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning.” IEEE Access 8 (2020): 195608–195621. Crossref. Web.