Ad-hoc teams model for precision agriculture and pest monitoring in large plantations

• Grant number: 19/14791-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2019
• End date: September 30, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Jó Ueyama
• Grantee: Matheus Aparecido do Carmo Alves
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID

Abstract

Currently, the development of smart devices has gained importance in the most diverse scenarios, creating environments shared physically and logically by the physical systems and multiagents (devices) that compose them. The problem is that most of these systems and agents are not designed to communicate with each other, making it hard to implement these systems and to optimize the target task. To ensure the effectiveness of these systems, agents (physical systems) need to share information with each other, to process information and, to make services more flexible, even under limited conditions (such as restricting the knowledge about its teammates or the world around it).Brazil, as a predominantly agricultural economy country, has promoted researches and expressed an increasing interest in the development of frameworks that can optimize the agriculture and monitoring process of large plantations. Given this background, the FAPESP project proposal aims to carry out a study about the problem defined as "optimization of task planning and better partitioning of agent sets", designed as an online learning problem and coalition structure generation. Overall, we aim to develop a fully decentralized algorithm capable of generating real-time knowledge to optimize the precision agriculture process and pest monitoring for large plantations, also focusing on the optimization of the system and problems within the national level, in order to present a viable solution, socially and economically.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

YOURDSHAHI, ELNAZ SHAFIPOUR; ALVES, MATHEUS APARECIDO DO CARMO; VARMA, AMOKH; MARCOLINO, LEANDRO SORIANO; UEYAMA, JO; ANGELOV, PLAMEN. On-line estimators for ad-hoc task execution: learning types and parameters of teammates for effective teamwork. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, v. 36, n. 2, p. 49-pg., 2022-10-01. (19/14791-6, 13/07375-0)