doi: 10.7763/IJMO.2024.V14.854
Reinforcement Learning Based Communication Relay for Small Indoor Robots
Hyojun Ahn
1,*
,
Sejin Kim
1
,
Eunseo Baek
1
,
Mingyu Shin
1
,
Sungjun Shim
2
,
Jooyoung Kim
2
,
Yongjin Kwon
1,*
- 1 1Department of Industrial Engineering, College of Engineering, Ajou University, Suwon, South Korea
- 2 Intelligent/Autonomous Control SW Team, LIG Nex1, Sungnam, South Korea
- Manuscript received July 31, 2023
- revised September 11, 2023
- accepted January 12, 2024
- published June 19, 2024
Abstract
Communication relay among small indoor robots performing surveillance tasks within complex indoor environments is a vital element. In situations where communication is impeded, such as GPS blockage or disaster situations, robots moving within buildings must install repeaters or relay robots in appropriate locations to maintain the link. However, research on optimized methodologies for when and where to install relay robots is lacking. This is due to the complexity and diversity of indoor environments, making it difficult to present standardized solutions. To address these challenges, this paper proposes an algorithm for optimized communication relays by combining reinforcement learning and traditional shortest path algorithms. As a result of applying this algorithm, the distance traveled was reduced by 30%, and the sustained communication time increased by 36%. In addition, this approach demonstrated potential for future applications in dynamic mission planning for small indoor robots.
Keywords
- reinforcement learning
- small indoor robots
- communication relay
- A* algorithm
- dynamic mission planning
- simulation
How to Cite
Hyojun Ahn, Sejin Kim, Eunseo Baek, Mingyu Shin, Sungjun Shim, Jooyoung Kim, and Yongjin Kwon, "Reinforcement Learning Based Communication Relay for Small Indoor Robots," International Journal of Modeling and Optimization, vol. 14, no. 2, pp. 88-93, 2024. https://doi.org/ 10.7763/IJMO.2024.V14.854
Copyright & License
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).