Dynamic ground risk assessment for safe UAV operations based on mass rapid transit (MRT) data

Abstract

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in recent years for various purposes. As UAVs become prevalent, there is increased Third-Party Risk associated with their operations, especially in urban areas with high population density. One of the solutions to improve safety is implementing integrated risk cost path planning. This study proposes a method to improve the accuracy of integrated risk cost path planning by implementing a dynamic ground risk assessment model based on dynamic population density. Singapore Mass Rapid Transit (MRT) using data from different subzone locations was collected and studied extensively to identify temporal trends. A temporal prediction model of MRT usage was developed using Random Forest Regression. Based on the prediction, the Gravity Model was used to diffuse the prediction volume output of different timings so dynamic risk index grid cells of 100m x 100m can be obtained and applied to integrated risk cost path planning for safer UAV operations.