Defesa de Mestrado do discente Rodrigo Lucas, dia 13/06/2025, às 14:00.

Defesa de Mestrado do discente Rodrigo Lucas, dia 13/06/2025, às 14:00.

Título: Avanços em SLAM Multimodal: Aprimorando a Navegação de Robôs Autônomos em Aplicações Logísticas e Industriais

Resumo : Autonomous mobile robots offer promising solutions for logistics, inspection, and other tasks in industrial environments and confined spaces, increasing efficiency and safety. Accurate navigation of these complex environments, however, is a central challenge for robotics, requiring precise mapping and real-time localization. The Simultaneous Localization and Mapping (SLAM) technique allows robots to build maps while moving, but its accuracy can be compromised in audible or feature-poor environments. The specific challenge of this study is to improve SLAM solutions and robustness in challenging industrial environments. Here, we show that fusion of data from LiDAR, RGB camera, IMU, and encoders, integrated in an Arduino-based control architecture, significantly improves the mapping accuracy and autonomous navigation capability of a mobile robot. Previously, SLAM often relied on a single sensor (such as LiDAR or camera), making it vulnerable to sensor failure or resource-limited environments. The multisensory approach of the Scramble robot, presented in this work, demonstrates a significant reduction in localization errors and a greater ability to adapt to changes in the environment. This represents a breakthrough, as it allows robots to operate more reliably in real industrial scenarios, where accuracy and robustness are critical. In a broader context, this research contributes to the development of more independent and adaptable robotic systems, capable of dealing with real-world complexity. In addition, a modular and low-cost architecture used can facilitate the adoption of the technology in diverse applications, from warehouse logistics to the inspection of critical infrastructures. The integration of advanced SLAM algorithms with affordable hardware and robust data fusion strategies paves the way for a new generation of autonomous mobile robot.

Data : 13/06/25  Hora : 14 horas

Link : Defesa de Mestrado- Rodrigo Lucas Santos
sexta-feira, 13 de jun. · 14:00 – 17:00
Como participar do Google Meet
Link da videochamada: https://meet.google.com/ozu-abvc-eom

Banca: Prof. Dr. Rafael Alves Bonfim - UFOP; Prof. Dr. Sandro Renato Dias - Cefet-MG; Prof. Dr. Ricardo Augusto Rabelo - UFOP; Prof. Dr. Mateus Coelho Silva - UFABC