Real-time Active Vision for a Humanoid Soccer Robot using Deep Reinforcement Learning

Soheil Khatibi, Meisam Teimouri, Mahdi Rezaei

2021

Abstract

In this paper, we present an active vision method using a deep reinforcement learning approach for a humanoid soccer-playing robot. The proposed method adaptively optimises the viewpoint of the robot to acquire the most useful landmarks for self-localisation while keeping the ball into its viewpoint. Active vision is critical for humanoid decision-maker robots with a limited field of view. To deal with active vision problem, several probabilistic entropy-based approaches have previously been proposed which are highly dependent on the accuracy of the self-localisation model. However, in this research, we formulate the problem as an episodic reinforcement learning problem and employ a Deep Q-learning method to solve it. The proposed network only requires the raw images of the camera to move the robot’s head toward the best viewpoint. The model shows a very competitive rate of 80% success rate in achieving the best viewpoint. We implemented the proposed method on a humanoid robot simulated in Webots simulator. Our evaluations and experimental show that the proposed method outperforms the entropy-based methods in the RoboCup context, in cases with high self-localisation errors.

Paper Citation

in Harvard Style

Khatibi S., Teimouri M. and Rezaei M. (2021). Real-time Active Vision for a Humanoid Soccer Robot using Deep Reinforcement Learning.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 742-751. DOI: 10.5220/0010237307420751

in Bibtex Style

@conference{icaart21,
author={Soheil Khatibi and Meisam Teimouri and Mahdi Rezaei},
title={Real-time Active Vision for a Humanoid Soccer Robot using Deep Reinforcement Learning},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={742-751},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010237307420751},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Real-time Active Vision for a Humanoid Soccer Robot using Deep Reinforcement Learning
SN - 978-989-758-484-8
AU - Khatibi S.
AU - Teimouri M.
AU - Rezaei M.
PY - 2021
SP - 742
EP - 751
DO - 10.5220/0010237307420751