RT Conference Proceedings
T1 Distributed deep reinforcement learning resource allocation scheme for industry 4.0 Device-To-Device scenarios
A1 Burgueño Romero, Jesús
A1 Adeogun, Ramoni
A1 Liborius Bruun, Rasmus
A1 Morejón García, C. Santiago
A1 De la Bandera Cascales, Isabel
A1 Barco-Moreno, Raquel
K1 Asignación de recursos
K1 Aprendizaje programado
K1 Robots autónomos
K1 Redes neuronales (Informática)
AB This paper proposes a distributed deep reinforcement learning (DRL) methodology for autonomous mobile robots (AMRs) to manage radio resources in an indoor factory with no network infrastructure. Hence, deep neural networks (DNN) are used to optimize the decision policy of the robots, which will make decisions in a distributed manner without signalling exchange. To speed up the learning phase, a centralized training is adopted in which a single DNN is trained using the experience from all robots. Once completed, the pre-trained DNN is deployed at all robots for distributed selection of resources. The performance of this approach is evaluated and compared to 5G NR sidelink mode 2 via simulations. The results show that the proposed method achieves up to 5% higher probability of successful reception when the density of robots in the scenario is high.
YR 2021
FD 2021
LK https://hdl.handle.net/10630/23013
UL https://hdl.handle.net/10630/23013
LA eng
NO This work has been partially funded by Junta de Andalucía (projects EDEL4.0:UMA18-FEDERJA-172 and PENTA:PY18-4647) and Universidad de Málaga (I Plan Propio de Investigación, Transferencia y Divulgación Científica). Ramoni Adeogun is supported by the Danish Council for Independent Research, grant no. DFF 9041-00146B. The authors would like to express their profound gratitude to Nokia Standardization Aalborg and Aalborg University for funding the first author’s research stay. The authors thank Assoc. Prof. Gilberto Beradinelli for his comments on the manuscript.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026