Abstract:In this paper we discuss the application of AI and ML to the exemplary industrial use case of the two-dimensional commissioning problem in a high-bay storage, which essentially can be phrased as an instance of Traveling Salesperson Problem (TSP). We investigate the mlrose library that provides an TSP optimizer based on various heuristic optimization techniques. Our focus is on two methods, namely Genetic Algorithm and Hill Climbing, which are provided by mlrose. We present modifications for both methods that improve the computed tour lengths, by moderately exploiting the problem structure of TSP. However, the proposed improvements have some generic character and are not limited to TSP only.