Vision-based navigation using deep reinforcement learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00334856" target="_blank" >RIV/68407700:21230/19:00334856 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/19:00334856

Výsledek na webu

<a href="https://doi.org/10.1109/ECMR.2019.8870964" target="_blank" >https://doi.org/10.1109/ECMR.2019.8870964</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ECMR.2019.8870964" target="_blank" >10.1109/ECMR.2019.8870964</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Vision-based navigation using deep reinforcement learning

Popis výsledku v původním jazyce

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a major part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator surpasses the performance of state-of-the-art goal-oriented visual navigation methods from the literature.

Název v anglickém jazyce

Vision-based navigation using deep reinforcement learning

Popis výsledku anglicky

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target given by an image. To achieve this, we have extended the batched A2C algorithm with auxiliary tasks designed to improve visual navigation performance. We propose three additional auxiliary tasks: predicting the segmentation of the observation image and of the target image and predicting the depth-map. These tasks enable the use of supervised learning to pre-train a major part of the network and to reduce the number of training steps substantially. The training performance has been further improved by increasing the environment complexity gradually over time. An efficient neural network structure is proposed, which is capable of learning for multiple targets in multiple environments. Our method navigates in continuous state spaces and on the AI2-THOR environment simulator surpasses the performance of state-of-the-art goal-oriented visual navigation methods from the literature.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of European Conference on Mobile Robots

ISBN

978-1-7281-3605-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

Czech Technical University

Místo vydání

Prague

Místo konání akce

Prague

Datum konání akce

4. 8. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000558081900059