Abstract:This letter proposes a novel protocol that uses Q-learning-based geographic routing (QGeo) to improve the network performance of unmanned robotic networks. A rapid and reliable network is essential fo...This letter proposes a novel protocol that uses Q-learning-based geographic routing (QGeo) to improve the network performance of unmanned robotic networks. A rapid and reliable network is essential for the remote control and monitoring of mobile robotic devices. However, controlling the network overhead required for route selection and repair is still a notable challenge, owing to high mobility of the devices. To alleviate this problem, we propose a machine-learning-based geographic routing scheme to reduce network overhead in high-mobility scenarios. We evaluate the performance of QGeo in comparison with other methods using the NS-3 simulator. We find that QGeo has a higher packet delivery ratio and a lower network overhead than existing methods.Read More
Publication Year: 2017
Publication Date: 2017-01-23
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 92
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot