Comparative Analysis of Visual-Inertial SLAM Algorithms in Simulated Environments

• Grant number: 25/12556-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2025
• End date: July 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Carlos Henrique Costa Ribeiro
• Grantee: Daniel da Silveira Sahadi
• Host Institution: Divisão de Ciência da Computação (IEC). Instituto Tecnológico de Aeronáutica (ITA). Ministério da Defesa (Brasil). São José dos Campos , SP, Brazil
• Company: Ministério da Defesa (Brasil). Instituto Tecnológico de Aeronáutica (ITA). Divisão de Engenharia Mecânica (IEM)
• Associated research grant: 21/11258-5 - Engineering Research Center for the Aerial Mobility of the Future (ERC-AMF), AP.PCPE

Abstract

Simultaneous Localization and Mapping (SLAM) plays a crucial role in autonomous navigation systems, enabling devices to build a map of an unknown environment while tracking their position within it. Among the various SLAM approaches, Visual-Inertial SLAM (VI-SLAM) combines camera and inertial data to improve robustness and accuracy. This research aims to compare the performance of three widely used open-source VI-SLAM frameworks - ORB-SLAM3, Kimera, and VINS-Fusion - in simulated environments. The study will assess these systems in terms of accuracy, robustness, computational efficiency, and ease of integration. Experiments will be conducted using two different hardware setups, that is, all VI-SLAM frameworks will be tested on different environments to compare their efficiency, one of the hardware setups that is going to be used is the drone from eVTOL ITA which uses a Jetson Orin Nano, the results obtained will be compared to verify the compatibility of the softwares. The project involves system setup, simulation configuration, real-world data acquisition, algorithm integration, and comparative analysis.