Semantic simulation for mobile robot operator training

The paper concerns the research related to the semantic mapping application for automatic virtual scene generation. Data is acquired by a mobile robot equipped with 3D measurement system. The virtual scene composed by several entities and relations between them is the core of the proposed semantic simulation engine. Semantic mapping is still an open problem because of its complexity. There are several robotic applications that use semantic information to build complex environment maps with labeled entities, therefore advanced robot behavior based on ontological information can be processed in high conceptual level. We are presenting a new approach that uses semantic mapping to generate physical model of an environment that is later integrated with mobile robot simulator. Semantic map is generated based on raw data acquired by a mobile robot in INDOOR environment. This raw data is transformed into a semantic map and then consequently NVIDIA PhysX model is constructed. The PhysX model is used to perform an inspection intervention mobile robot simulation in which collision detection and rigid body simulation is available.