Deep reinforcement learning with successor features for navigation across similar environments

In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additiona...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingwei Zhang, Springenberg, Jost Tobias, Boedecker, Joschka, Burgard, Wolfram
Format: Conference Proceeding
Language:English
Subjects:
Learning (artificial intelligence)
Navigation
Neural networks
Simultaneous localization and mapping
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we consider the problem of robot navigation in simple maze-like environments where the robot has to rely on its onboard sensors to perform the navigation task. In particular, we are interested in solutions to this problem that do not require localization, mapping or planning. Additionally, we require that our solution can quickly adapt to new situations (e.g., changing navigation goals and environments). To meet these criteria we frame this problem as a sequence of related reinforcement learning tasks. We propose a successor-feature-based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances. Our algorithm substantially decreases the required learning time after the first task instance has been solved, which makes it easily adaptable to changing environments. We validate our method in both simulated and real robot experiments with a Robotino and compare it to a set of baseline methods including classical planning-based navigation.
ISSN:2153-0866
DOI:10.1109/IROS.2017.8206049