Customizable and Jointly Optimized Route Planning: A Deep Architecture Enabling Differentiable Shortest-Path Search

The paper introduces a deep architecture that jointly optimizes cost functions and a route-ranking model to accommodate diverse user preferences in route planning. It first generates a complete set of Pareto‑optimal routes using a multi‑objective Dijkstra algorithm, then employs a neural network that emulates shortest‑path search and ranking in an end‑to‑end differentiable framework. A novel loss function treats route preference as a constrained optimization problem, allowing a single objective to be optimized while other attributes remain constrained, and experiments on real‑world data show significant improvements over existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• benchmarks