Unsupervised Path Regression Networks
Michal Pándy,Daniel Lenton,Ronald Clark,Michal Pándy,Daniel Lenton,Ronald Clark
We demonstrate that challenging shortest path problems can be solved via direct spline regression from a neural network, trained in an unsupervised manner (i.e. without requiring ground truth optimal paths for training). To achieve this, we derive a geometry-dependent optimal cost function whose minima guarantees collision-free solutions. Our method beats state-of-the-art supervised learning basel...
