GNG-based Clustering of Risk-aware Trajectories into Safe Corridors

Abstract

Personal air transportation on short distances is a promising trend in modern aviation, raising new challenges as flying in low altitudes in highly populated environments induces additional risk to people and properties on the ground. Risk-aware planning can mitigate the risk by preferring flying above low-risk areas such as rivers or brownfields. Finding such trajectories is computationally demanding, but they can be precomputed for areas that are not changing rapidly and form a planning roadmap. The roadmap can be utilized for multi-query trajectory planning using graph-based search. However, a quality roadmap is required to provide a low-risk trajectory for an arbitrary query on a risk-aware trajectory from one location to another. Even though a dense roadmap can achieve the quality, it would be computationally demanding. Therefore, we propose to cluster the found trajectories and create a sparse roadmap of safe corridors that provide similar quality of risk-aware trajectories. In this paper, we report on applying Growing Neural Gas (GNG) in estimating the suitable number of clusters. Based on the empirical evaluation using a realistic urban scenario, the results suggest a significant reduction of the computational burden on risk-aware trajectory planning using the roadmap with the clustered safe corridors.