Unsupervised Learning for Subterranean Junction Recognition Based on 2D Point Cloud
This provides a solution for mission planners in robotics to navigate aerial platforms in unknown subterranean areas, but it is incremental as it applies existing spectral clustering to a new domain.
The paper tackles the problem of detecting tunnel junctions in subterranean environments using 2D point clouds, proposing an unsupervised learning framework based on spectral clustering, and validates it with simulations and real flight data.
This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for high level mission planners to navigate an aerial platform in unknown areas or robot homing missions. The framework utilizes spectral clustering, which is capable of uncovering hidden structures from connected data points lying on non-linear manifolds. The spectral clustering algorithm computes a spectral embedding of the original 2D point cloud by utilizing the eigen decomposition of a matrix that is derived from the pairwise similarities of these points. We validate the developed framework using multiple data-sets, collected from multiple realistic simulations, as well as from real flights in underground environments, demonstrating the performance and merits of the proposed methodology.