Vision-Based Machine Learning in Robot Soccer

被引：0

作者：

Olthuis, J. J. ^{[1
]}

van der Meer, N. B. ^{[2
]}

Kempers, S. T. ^{[1
]}

van Hoof, C. A. ^{[2
]}

Beumer, R. M. ^{[1
]}

Kuijpers, W. J. P. ^{[1
]}

Kokkelmans, A. A. ^{[1
]}

Houtman, W. ^{[1
]}

van Eijck, J. J. F. J. ^{[2
]}

Kon, J. J. ^{[1
]}

Peijnenburg, A. T. A. ^{[2
]}

van de Molengraft, M. J. G. ^{[1
]}

机构：

[1] Tech United Eindhoven, De Random 70,POB 513, NL-5600 MB Eindhoven, Netherlands

[2] RobotSports, De Schakel 22, NL-5651 GH Eindhoven, Netherlands

来源：

ROBOT WORLD CUP XXIV, ROBOCUP 2021 | 2022年 / 13132卷

关键词：

RoboCup soccer; Middle size league; Machine learning; Object detection; People detection; Real-time;

D O I：

10.1007/978-3-030-98682-7_27

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Robots need to perceive their environment in order to properly interact with it. In the RoboCup Soccer Middle Size League (MSL) this happens primarily through cameras mounted on the robots. Machine Learning can be used to extract relevant features from camera imagery. The real-time analysis of camera data is a challenge for both traditional and Machine Learning algorithms, since all computations in the MSL have to be performed on the robot itself. This contribution shows that it is possible to process camera imagery in real-time using Machine Learning. It does this by presenting the current state of Machine Learning in MSL and providing two examples that won the Scientific and Technical Challenges at RoboCup 2021. Both examples focus on semantic detection of objects and humans in imagery. The Scientific Challenge winner presents how YOLOv5 can be used for object detection in the MSL. The Technical Challenge winner demonstrates how to improve interaction between robots and humans in soccer using OpenPose. This contributes towards the goal of RoboCup to arrive at robots that can beat the human soccer world champion by 2050.

引用

页码：325 / 337

页数：13

共 50 条

[1] Design of vision-based soccer robot using DSP
胡广
陈鑫
曹卫华
吴敏
[J]. Journal of Harbin Institute of Technology(New series), 2001, (03) : 239 - 243
[2] Probabilistic vision-based opponent tracking in robot soccer
Schmitt, T
Hanek, R
Buck, S
Beetz, M
[J]. ROBOCUP 2002: ROBOT SOCCER WORLD CUP VI, 2003, 2752 : 426 - 434
[3] Vision-based reinforcement learning for robot navigation
Zhu, WY
Levinson, S
[J]. IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 1025 - 1030
[4] Active learning for vision-based robot grasping
Salganicoff, M
Ungar, LH
Bajcsy, R
[J]. MACHINE LEARNING, 1996, 23 (2-3) : 251 - 278
[5] Vision-based mobile robot learning and navigation
Gopalakrishnan, A
Greene, S
Sekmen, A
[J]. 2005 IEEE INTERNATIONAL WORKSHOP ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION (RO-MAN), 2005, : 48 - 53
[6] Machine Vision-Based Intelligent Fire Fighting Robot
Ho, Chao-Ching
Chen, Ming-Chen
Lien, Chih-Hao
[J]. ADVANCED DESIGN AND MANUFACTURE III, 2011, 450 : 312 - +
[7] A SURVEY OF VISION-BASED ARCHITECTURES FOR ROBOT LEARNING BY IMITATION
Bandera, J. P.
Rodriguez, J. A.
Molina-Tanco, L.
Bandera, A.
[J]. INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS, 2012, 9 (01)
[8] Vision-Based Robot Path Planning with Deep Learning
Wu, Ping
Cao, Yang
He, Yuqing
Li, Decai
[J]. COMPUTER VISION SYSTEMS, ICVS 2017, 2017, 10528 : 101 - 111
[9] A vision-based virtual fixture with robot learning for teleoperation
Luo, Jing
Liu, Weibin
Qi, Wen
Hu, Jianwen
Chen, Junming
Yang, Chenguang
[J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2023, 164
[10] Omni-directional vision-based control strategy for humanoid soccer robot
Su, Yu-Te
Li, Tzuu-Hseng S.
Hsu, Chia-Ling
Lu, Ming-Feng
Hu, Chun-Yang
Liu, Shao-Hsien
[J]. IECON 2007: 33RD ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-3, CONFERENCE PROCEEDINGS, 2007, : 2950 - 2955

← 1 2 3 4 5 →