Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems

Luo, Ruyu; Ni, Wanli; Tian, Hui; Cheng, Julian

doi:10.1109/tvt.2022.3190557

Cited by 18 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [101], authors have provide a viable solution for multirobot communication using FL approach. Indoor multi-robot communications face challenges such as signal strength degradation (due to walls) and dynamic environments (due to movement of robots).…”

Section: Figure 12 Overview Of Federated Learning Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Shafique,

Alhassoun

2024

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

To have uninterrupted wireless connectivity, higher throughput, and latency rate down to nanoseconds; future networks will rely heavily on higher frequency bands, yet these signals suffer from attenuation and can be easily blocked by objects. Hence, those signals lose strength over longer distances significantly compared to their low-frequency counterparts. To overcome these constraints, reconfigurable intelligent surfaces (RIS) can increase the wireless network capacity and coverage by consciously altering the wireless propagation environment, which makes them one of the key enablers of the 6G communication networks. The potential benefits of RIS-assisted communication systems can be effectively increased using machine learning (ML) to pave the path towards Wireless 2.0, having a vision of digitization, programmability, and intelligence. This paper reviews recent developments in RIS technology with a special emphasis on tuning techniques, hardware concepts, RIS empowered by artificial intelligence techniques, and applications for next generation of networks. Finally, a viewpoint on the difficulties and potential directions of intelligent metasurfaces are also presented.

show abstract

Section: Figure 12 Overview Of Federated Learning Algorithmmentioning

confidence: 99%

“…1) [92] 2) [112] 3) [101] Security and Privacy 1) FL 2) DRL 3) FL 1) Improves user's privacy for mm-wave communication systems.…”

Section: ) [108]mentioning

confidence: 99%

Going Beyond a Simple RIS: Trends and Techniques Paving the Path of Future RIS

Shafique,

Alhassoun

2024

IEEE Open J. Antennas Propag.

View full text Add to dashboard Cite

show abstract

“…For example, each robot might have access to a portion of the environment, and they are not allowed to share the local images with each other, where the objective is still to train a high-quality global model. Luo et al [ 193 ] have employed such a federated deep RL technique for multi-robot communication. The authors, in this paper, avoid blockages in communication signals due to large obstacles while avoiding inter-robot collisions.…”

Section: Multi-robot System Applications Of Multi-agent Deep Reinforc...mentioning

confidence: 99%

Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey

Orr

Dutta

2023

Sensors

View full text Add to dashboard Cite

Deep reinforcement learning has produced many success stories in recent years. Some example fields in which these successes have taken place include mathematics, games, health care, and robotics. In this paper, we are especially interested in multi-agent deep reinforcement learning, where multiple agents present in the environment not only learn from their own experiences but also from each other and its applications in multi-robot systems. In many real-world scenarios, one robot might not be enough to complete the given task on its own, and, therefore, we might need to deploy multiple robots who work together towards a common global objective of finishing the task. Although multi-agent deep reinforcement learning and its applications in multi-robot systems are of tremendous significance from theoretical and applied standpoints, the latest survey in this domain dates to 2004 albeit for traditional learning applications as deep reinforcement learning was not invented. We classify the reviewed papers in our survey primarily based on their multi-robot applications. Our survey also discusses a few challenges that the current research in this domain faces and provides a potential list of future applications involving multi-robot systems that can benefit from advances in multi-agent deep reinforcement learning.

show abstract