MRL Champion Team Paper in Humanoid TeenSize League of RoboCup 2019

Mahmudi, Hamed; Gholami, Amir Hossein; Delavaran, Mohammad Hossein; Khatibi, Soheil; Bazargan, Saeid; Moradi, Milad; Alaee, Bita; Rahmani, Arash; Bandpey, Kazem Firouzmandi; Fallahzadeh, Peyman; Teimouri, Meisam

doi:10.1007/978-3-030-35699-6_45

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, the overall performance of the proposed ball detection method is investigated in a real-world test. All experiments are performed in a kid-size humanoid robot [22] equipped with a Logitech c920 camera capturing 640×480 images at a rate of 30 frames per second and an Intel NUC with a Core i3 U6100 processor. The training is carried out on a Nvidia GTX 1080 GPU.…”

Section: Methodsmentioning

confidence: 99%

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

Teimouri

Delavaran

Rezaei

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Ball detection is one of the most important tasks in the context of soccer-playing robots. The ball is a small moving object which can be blurred and occluded in many situations. Several neural network based methods with different architectures are proposed to deal with the ball detection. However, they are either neglecting to consider the computationally low resources of humanoid robots or highly depend on manually-tuned heuristic methods to extract the ball candidates. In this paper, we propose a new ball detection method for low-cost humanoid robots that can detect most soccer balls with a high accuracy rate of up to 97.17%. The proposed method is divided into two steps. First, some coarse regions that may contain a full ball are extracted using an iterative method employing an efficient integral image based feature. Then they are fed to a lightweight convolutional neural network to finalize the bounding box of a ball. We have evaluated the proposed approach using a comprehensive dataset and the experimental results show the efficiency of our method.

show abstract

Section: Methodsmentioning

confidence: 99%

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

Teimouri

Delavaran

Rezaei

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Teams must build the mechanical and electronic parts of the robot and develop its software. While playing soccer, robots must walk steadily, visually perceive the ball, the players, and the field limits, kick the ball, and self-locate in a spatial environment [163]. In the HL, there are 3 different size categories: KidSize, TeenSize and AdultSize [164].…”

Section: A International Competitionsmentioning

confidence: 99%

Educational Robotics: Platforms, Competitions and Expected Learning Outcomes

et al. 2020

View full text Add to dashboard Cite

“…We tested the proposed method on the MRL-HSL humanoid robot (Mahmoudi et al, 2019) episodes are bound to 20 time steps but may terminate prematurely in the case of missing the ball from the field of view (as failure) or reaching the best viewpoint (as success).…”

Section: Experiments Environmentmentioning

confidence: 99%

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

Khatibi¹,

Teimouri²,

Rezaei³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

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.

show abstract

MRL Champion Team Paper in Humanoid TeenSize League of RoboCup 2019

Cited by 6 publications

References 8 publications

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

A Real-Time Ball Detection Approach Using Convolutional Neural Networks

Educational Robotics: Platforms, Competitions and Expected Learning Outcomes

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

Contact Info

Product

Resources

About