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

arXiv:2405.04923v1 Announce Type: new
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 …

abstract algorithm arxiv assumptions context cost costs cs.ai cs.lg differential features graphs paper path planning scale transitions type