Abstract
Orienteering problem (OP) is a routing problem, where the aim is to generate a path through set of nodes, which would maximize total score and would not exceed the budget. In this paper, we present an extension of classic OP—Orienteering Problem with Functional Profits (OPFP), where the score of a specific point depends on its characteristics, position in the route, and other points in the route. For solving OPFP, we developed an open-source framework for solving orienteering problems, which utilizes four core components of OP in its modular architecture. Fully-written in Go programming language our framework can be extended for solving different types of tasks with different algorithms; this was demonstrated by implementation of two popular algorithms for OP solving—Ant Colony Optimization and Recursive Greedy Algorithm. Computational efficiency of the framework was shown through solving four well-known OP types: classic Orienteering Problem (OP), Orienteering Problem with Compulsory Vertices (OPCV), Orienteering Problem with Time Windows (OPTW), and Time Dependent Orienteering Problem (TDOP) along with OPFP. Experiments were conducted on a large multi-source dataset for Saint Petersburg, Russia, containing data from Instagram, TripAdvisor, Foursquare and official touristic website. Our framework is able to construct touristic paths for different OP types within few seconds using dataset with thousands of points of interest.
Highlights
Orienteering problem (OP) is a class of routing problems, where the ultimate goal is to create a route through a given points of interest (PoIs), which would satisfy given conditions and constraints
In case of OP, Orienteering Problem with Compulsory Vertices (OPCV), Orienteering Problem with Time Windows (OPTW), and Time Dependent Orienteering Problem (TDOP), the route score was computed as the sum of Instagram visitors from all places and for Orienteering Problem with Functional Profits (OPFP), the final score was computed as the sum of scores described in previous section
We present an extension of classic OP—Orienteering Problem with Functional Profits (OPFP), where score of specific point depends on its characteristics, position in the route, and other points in the itinerary
Summary
Orienteering problem (OP) is a class of routing problems, where the ultimate goal is to create a route through a given points of interest (PoIs), which would satisfy given conditions and constraints. That is why scientists try to find the best solutions for this class of problems in terms of both solution quality and algorithm execution time When it comes to solving orienteering tasks on a large scale, like construction of itineraries through locations in a big city [12], the need for an efficient solver becomes crucial, because search space can include tens or hundreds of thousands points. To investigate computational efficiency of the developed framework for various problems in different conditions, we created a large multi-source dataset of locations for Saint Petersburg, Russia. It aggregates information from Instagram, TripAdvisor, Foursquare and official touristic guide. Experimental results that demonstrate FOPS applicability on examples of five problems (including OPFP) of walking itineraries generation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
