Solving Routing Problems for Multiple Cooperative Unmanned Aerial Vehicles using Transformer Networks

 

Research  

 

  • GTI
  • data
  • Solving Routing Problems for Multiple Cooperative Unmanned Aerial Vehicles using Transformer Networks

Solving Routing Problems for Multiple Cooperative Unmanned Aerial Vehicles using Transformer Networks

 

 

Description

Missions involving Unmanned Aerial Vehicle usually consist of reaching a set of regions, performing some actions in each region, and returning to a determined depot after all the regions have been successfully visited or before the fuel/battery is totally consumed. Hence, planning a route becomes an important task for many applications, especially if a team of Unmanned Aerial Vehicles is considered. From this team, coordination and cooperation are expected to optimize results of the mission. In this paper, a system for managing multiple cooperative Unmanned Aerial Vehicles is presented. This system divides the routing problem into two stages: initial planning and routing solving. Initial planning is a first step where the regions to be visited are grouped in multiple clusters according to a distance criterion, with each cluster being assigned to each of the Unmanned Aerial Vehicles. Routing solving computes the best route for every agent considering the clusters of the initial planning and a variant of the Orienteering Problem. This variant introduces the concept of shared regions, allowing an
Unmanned Aerial Vehicle to visit regions from other clusters and compensating for the suboptimal region clustering of the previous stage. The Orienteering Problem with shared regions is solved using the deep learning architecture Transformer along with a deep reinforcement learning framework. This architecture is able to obtain high-quality solutions much faster than conventional optimization approaches. Extensive results and comparison with other Combinatorial Optimization algorithms, including cooperative and non-cooperative scenarios, have been performed to show the benefits of the proposed solution.

SolvingRouting

For questions about this multi-agent system, please contact Daniel Fuertes at This email address is being protected from spambots. You need JavaScript enabled to view it..

Download

Click here to download the code.

 

Citation

D. Fuertes, C. R. del Blanco, F. Jaureguizar, J. J. Navarro, N. García, Solving routing problems for multiple cooperative unmanned aerial vehicles using transformer networks, Engineering Applications of Artificial Intelligence 122 (2023) 106085. doi:10.1016/j.engappai.2023.106085.