Real-time object navigation with deep neural networks and hierarchical reinforcement learning

Aleksey Staroverov, Dmitry A. Yudin, Ilya Belkin, Vasily Adeshkin, Yaroslav K. Solomentsev, Aleksandr I. Panov

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number3034524
Pages (from-to)195608-195621
Number of pages14
JournalIEEE Access
Volume8
DOIs
Publication statusPublished - 2020
Externally publishedYes

Keywords

  • Cognitive robotics
  • Indoor navigation
  • Intelligent agents
  • Neural networks
  • Object segmentation
  • Real-time systems
  • Robot learning

Fingerprint

Dive into the research topics of 'Real-time object navigation with deep neural networks and hierarchical reinforcement learning'. Together they form a unique fingerprint.

Cite this