Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00350230" target="_blank" >RIV/68407700:21230/21:00350230 - isvavai.cz</a>

Alternative codes found

RIV/68407700:21730/21:00350230

Result on the web

<a href="https://doi.org/10.1109/LRA.2021.3068106" target="_blank" >https://doi.org/10.1109/LRA.2021.3068106</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/LRA.2021.3068106" target="_blank" >10.1109/LRA.2021.3068106</a>

Result language

angličtina

Original language name

Visual Navigation in Real-World Indoor Environments Using End-to-End Deep Reinforcement Learning

Original language description

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing, localization, and planning in one module, which can be trained and therefore optimized for a given environment. However, to date, DRL-based visual navigation was validated exclusively in simulation, where the simulator provides information that is not available in the real world, e.g., the robot's position or segmentation masks. This precludes the use of the learned policy on a real robot. Therefore, we present a novel approach that enables a direct deployment of the trained policy on real robots. We have designed a new powerful simulator capable of domain randomization. To facilitate the training, we propose visual auxiliary tasks and a tailored reward scheme. The policy is fine-tuned on images collected from real-world environments. We have evaluated the method on a mobile robot in a real office environment. The training took approximately 30 hours on a single GPU. In 30 navigation experiments, the robot reached a 0.3-meter neighbourhood of the goal in more than 86.7% of cases. This result makes the proposed method directly applicable to tasks like mobile manipulation.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/EF15_003%2F0000470" target="_blank" >EF15_003/0000470: Robotics 4 Industry 4.0</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE Robotics and Automation Letters

ISSN

2377-3766

e-ISSN

2377-3766

Volume of the periodical

6

Issue of the periodical within the volume

3

Country of publishing house

US - UNITED STATES

Number of pages

8

Pages from-to

4345-4352

UT code for WoS article

000639767800013

EID of the result in the Scopus database

2-s2.0-85103234640