Neuro-Dominating Set Scheme for a Fast and Efficient Robot Deployment in Internet of Robotic Things

Abstract : Internet of Robotic Things (IoRT) is a new concept introduced for the first time by ABI Research. Unlike the Internet of Things (IoT), IoRT provides an active sensorization and is considered as the new evolution of IoT. In this context, we propose a Neuro-Dominating Set algorithm (NDS) to efficiently deploy a team of mobile wireless robots in an IoRT scenario, in order to reach a desired inter-robot distance, while maintaining global connectivity in the whole network. We use the term Neuro-Dominating Set to describe our approach, since it is inspired by both neural network and dominating set principles. With NDS algorithm, a robot adopts different behaviors according whether it is a dominating or a dominated robot. Our main goal is to show and demonstrate the beneficial effect of using different behaviors in the IoRT concept. The obtained results show that the proposed method outperforms an existing related technique (i.e., the Virtual Angular Force approach) and the neural network based approach presented in our previous work. As an objective, we aim to decrease the overall traveled distance and keep a low energy consumption level, while maintaining network connectivity and an acceptable convergence time.
Document type :
Journal articles
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01864325
Contributor : Valeria Loscri <>
Submitted on : Wednesday, August 29, 2018 - 4:35:40 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Friday, November 30, 2018 - 3:38:17 PM

File

nds_v5.0.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01864325, version 1

Collections

Citation

Cristanel Razafimandimby, Valeria Loscri, Anna Vegni, Abderrahim Benslimane. Neuro-Dominating Set Scheme for a Fast and Efficient Robot Deployment in Internet of Robotic Things. Ad Hoc Networks, Elsevier, 2018. ⟨hal-01864325⟩

Share

Metrics

Record views

380

Files downloads

145