DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context

Alan Lahoud, Erik Schaffernicht, Johannes A. Stork

Keywords: neural networks, inverse optimization, path planning, structured predictions, shortest path

TL;DR: Framework to learn underlying cost transitions from context an suboptimal trajectories with different start and end nodes

Abstract: Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning. Yet, existing methods either oversimplify cost assumptions or scale poorly with the number of observed trajectories. This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. It allows to learn from a large number of trajectories in each learning step without additional computation. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We further propose a method to sample paths from DataSP in order to reconstruct/mimic observed paths' distributions. We prove that the inferred distribution follows the maximum entropy principle. We show that DataSP outperforms state-of-the-art differentiable combinatorial solver and classical machine learning approaches in predicting paths on graphs.

List Of Authors: Lahoud, Alan and Schaffernicht, Erik and Stork, Johannes

Code Url: https://github.com/AlanLahoud/dataSP

Submission Number: 465