Fog-Based Federated Learning for Drone Delivery Services

• Grant number: 23/16328-7
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Effective date (Start): February 01, 2024
• Effective date (End): June 30, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Luiz Fernando Bittencourt
• Grantee: Fabíola Martins Campos de Oliveira Genari
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Host Company: Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação (FEEC)
• Associated research grant: 21/00199-8 - SMART NEtworks and ServiceS for 2030 (SMARTNESS), AP.PCPE

Abstract

A smart aerial delivery service uses drones to deliver packages in urban areas, replacing or supplementing terrestrial vehicles. Intelligent drone delivery is vital in reducing the environmental impact, delivery time, and costs, calling the attention of delivery companies that started to perform small-scale tests with drones and providers offering this service, such as Alphabet's Wing. In big cities, a drone delivery service will employ many drones, increasing drone density and bringing the fundamental challenge of avoiding collisions with other drones or typical obstacles of urban spaces. This project aims to advance the state of the art by proposing approaches to achieve a safe collision level for drone delivery services, similar to aviation, using edge or fog computing and federated learning techniques. For this purpose, we will improve our modified Unity-based UTSim drone simulator to include fog computing infrastructure and machine learning methods.