Documents

  • AAM

    Accepted author manuscript, 3.62 MB, PDF document

DOI

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.

Original languageEnglish
Title of host publicationProceedings of the European Conference on Mobile Robots (ECMR 2019)
EditorsLibor Preucil, Sven Behnke, Miroslav Kulich
Place of PublicationPiscataway, NJ, USA
PublisherIEEE
Number of pages8
ISBN (Electronic)978-1-7281-3605-9
DOIs
Publication statusPublished - 2019
EventECMR 2019: European Conference on Mobile Robots - Prague, Czech Republic
Duration: 4 Sep 20196 Sep 2019

Conference

ConferenceECMR 2019: European Conference on Mobile Robots
CountryCzech Republic
CityPrague
Period4/09/196/09/19

    Research areas

  • Actor-critic, Auxiliary tasks, Deep reinforcement learning, Robot navigation

ID: 66572585