All Colors Shortest Path Problem

Abstract: All Colors Shortest Path problem defined on an undirected graph aims at finding a shortest, possibly non-simple, path where every color occurs at least once, assuming that each vertex in the graph is associated with a color known in advance. To the best of our knowledge, this paper is the first to define and investigate this problem. Even though the problem is computationally similar to generalized minimum spanning tree, and the generalized traveling salesman problems, allowing for non-simple paths where a node may be visited multiple times makes All Colors Shortest Path problem novel and computationally unique. In this paper we prove that All Colors Shortest Path problem is NP-hard, and does not lend itself to a constant factor approximation. We also propose several heuristic solutions for this problem based on LP-relaxation, simulated annealing, ant colony optimization, and genetic algorithm, and provide extensive simulations for a comparative analysis of them. The heuristics presented are not the standard implementations of the well known heuristic algorithms, but rather sophisticated models tailored for the problem in hand. This fact is acknowledged by the very promising results reported.