Advanced search
Start date
Betweenand


An Embedded System Architecture based on Genetic Algorithms for Mission and Safety Planning with UAV

Full text
Author(s):
Arantes, Jesimar da Silva ; Arantes, Marcio da Silva ; Motta Toledo, Claudio Fabian ; Trindade Junior, Onofre ; Williams, Brian C. ; ACM
Total Authors: 6
Document type: Journal article
Source: PROCEEDINGS OF THE 2017 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'17); v. N/A, p. 8-pg., 2017-01-01.
Abstract

The present paper describes an embedded system architecture, based on genetic algorithms, aiming safety mission execution by Unmanned Aerial Vehicles (UAVs). A two-dimensional non-convex environment is considered since obstacle avoidance happens. The embedded system integrates the Mission Oriented Sensor Array (MOSA) and In-Flight Awareness (IFA) systems, where MOSA is responsible for mission accomplishment and IFA stands for flight safety. The features of MOSA and IFA are combined under a platform that applies promising genetic algorithm approaches from literature to reach their goals. First, the genetic algorithms performance running from the embedded system is compared against their performance on a personal computer architecture. Next, the proposed system is evaluated in a real-world scenario using Software In-The-Loop (SITL) technique. The computational results showed that the embedded system provides reliable results. (AU)

FAPESP's process: 13/26091-2 - The study and proposition of methods for the general Chance-Constrained qualitative state planning problem
Grantee:Claudio Fabiano Motta Toledo
Support Opportunities: Scholarships abroad - Research
FAPESP's process: 14/11331-0 - Hybrid qualitative state plan and mission planning problem with UAVs
Grantee:Márcio da Silva Arantes
Support Opportunities: Scholarships in Brazil - Doctorate
FAPESP's process: 15/23182-2 - Autonomous system for mission control and flight safety in UAVs
Grantee:Jesimar da Silva Arantes
Support Opportunities: Scholarships in Brazil - Doctorate