Context Analysis in Consolidated and Consolidating Urban Areas Using Segmentation and Classification of Characteristic Objects with a Semantic Simultaneous Localization and Mapping Approach on a Mobile Robot

This project addresses the limitations of traditional urban data collection methods, which are labor-intensive and lack three-dimensional precision. It proposes the development of an autonomous mobile robot (UGV) equipped with a 3D LiDAR sensor and semantic SLAM algorithms to automate the segmentation and classification of urban and natural elements. This technology will capture detailed environmental data, facilitating more efficient, data-driven urban planning. The development is divided into two phases: the mechanical and electronic construction of the mobile robot, and the implementation of artificial intelligence algorithms for point cloud processing. The system will be validated in various urban areas of Cuenca, Gualaceo, and Nabón, comparing its performance in terms of time and accuracy against conventional techniques. Expected results include the optimization of urban space management, the reduction of operational costs in surveying, and the generation of scientific knowledge through indexed publications. Furthermore, the project will strengthen the interdisciplinary training of engineering and architecture students, promoting the use of advanced technologies for the development of sustainable cities.<br/><br/><b>Goal</b>: <br/>To perform a contextual analysis of urban areas through the segmentation and classification of objects using semantic SLAM on a mobile robot equipped with a 3D LiDAR sensor. The goal is to automate the creation of enriched maps to improve the understanding and planning of complex urban environments.<br/><br/><b>Research lines</b>: <br/>Simulation and optimization of industrial processes