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

TL;DR

This paper introduces a deep reinforcement learning approach for active vision in humanoid soccer robots, enabling adaptive viewpoint selection to improve self-localisation and ball tracking, outperforming traditional entropy-based methods especially with localization errors.

Contribution

The paper presents a novel deep Q-learning based active vision method that only requires raw camera images, improving viewpoint selection for humanoid robots in soccer scenarios.

Findings

Achieves 80% success rate in selecting optimal viewpoints.

Outperforms entropy-based methods in high self-localisation error scenarios.

Effective in simulated RoboCup environment.

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 an 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 results show that the proposed method outperforms the entropy-based methods in the RoboCup context, in cases with high self-localisation errors.