Litcius/Paper detail

Aerial Edge Computing: Flying Attitude-Aware Collaboration for Multi-UAV

Jianwen Xu, Kaoru Ota, Mianxiong Dong

2022IEEE Transactions on Mobile Computing23 citationsDOIOpen Access PDF

Abstract

With the continuous innovation in manufacturing, Unmanned Aerial Vehicles (UAVs) have gradually become commodities from just professional equipment. As a universal type, quadrotor UAV allows us to see its potential for applications in multiple fields. Moreover, in the brand new field of aerial computing, UAVs have started to play a leading role in providing computing services to mobile users. However, limited by the performance of onboard equipment, we often cannot rely on one UAV to complete complex computing tasks. This paper first carries out a real-world case study and discovers the importance of flying attitude in applying quadcopter UAVs to achieve aerial edge computing. Then in designing the collaboration algorithms, we apply Monte Carlo Tree Search (MCTS) to realize the independent operations of UAVs while assisting each other in accomplishing the common goals. In performance evaluation, we compare the performance of our proposed solution with the existing methods. Finally, the results show that our MCTS-based algorithm can implement efficient collaboration among UAVs while reducing energy consumption and time cost in providing AEC services.

Topics & Concepts

Computer scienceQuadcopterMonte Carlo tree searchEnhanced Data Rates for GSM EvolutionField (mathematics)Edge computingDroneMobile edge computingDistributed computingEnergy consumptionReal-time computingMonte Carlo methodArtificial intelligenceEngineeringPure mathematicsElectrical engineeringStatisticsMathematicsGeneticsAerospace engineeringBiologyUAV Applications and OptimizationDistributed Control Multi-Agent SystemsRobotics and Sensor-Based Localization