Multi-sensor information fusion for Internet of Things assisted automated guided vehicles in smart city

Smart transportation is one of the important factor in the smart city environment because it enhance the citizen lives style and improving the sustainability. Driverless Automatically guided vehicles rely on environmental information for performing target-oriented movements and navigation. Handling multiple information from the environment is a complex task though, these information are necessary for improving the realization of these vehicles. Therefore, considering the significance of sensor data in this guided vehicle environment, this article introduces Responder-dependent Additive Information Fusion (RAIF) scheme. This scheme observes the responding sensor information for determining the achievement level of the target endorsed for the guided vehicle. The multi-instance sensor information is gathered from the Internet of Things (IoT) based connected devise. The timely responding sensors and its data are correlated with the previous history for improving the precision of navigation of the guided vehicles. This scheme relies on classification machine learning for identifying remitting and un-remitting instances based on correlation for information fusion. This helps to identify the error causing sensor information and to mitigate them from fusion to improve the precision of achieving the target.

Automated summary

Smart transportation plays a crucial role in smart cities by enhancing citizen lifestyles and sustainability. The RAIF scheme introduced in the article utilizes classification machine learning to improve navigation precision by observing responsive sensor information and eliminating error-causing data.