Synthetic Data-Based Semantic Mapping: Application to Object Recognition in Industry 5.0

Description

As Industry 5.0 becomes an increasingly tangible reality, the imperative for humans and robots to collaborate fully within the workplace has become more crucial than ever before. To address this challenge, robots need to recognize their surroundings. This involves a need for a semantic mapping of the robot’s environment. Semantic mapping entails the process of creating a digital representation of a physical environment that captures not only its geometric properties but also its semantic features. In the context of industrial environments; this involves identifying and labeling objects, surfaces, and other features, and associating them with semantic information, such as their function, category, or behavior. This manuscript outlines the techniques used for creating semantic mapping, utilizing Simultaneous Localization and Mapping (SLAM) techniques, including the integration of artificial intelligence techniques. Additionally, this manuscript also explores the previous work conducted in training deep learning models using synthetically generated data.