The semantic orientation in space system is a concept of combining spatial data processing technology and semantic analysis. Its main purpose is not only orientation in space but also understanding the meaning of objects in a given environment. Semantic spatial orientation could be used, for example, to create more advanced navigation systems that understand the context of natural language (e.g. ‘drive up to the blue chair on the right’, ‘how many whiteboards are there in the rooms’). The realisation of the objective should be a multi-stage process combining the aspect of mapping with semantic analysis and aspects of navigation (carried out by a separate team), ultimately creating a complementary whole. Stage 1 will allow for the verification of the basic concept of semantic analysis of space and the introduction of semantic representation of objects. This stage consists of the following tasks:
- adaptation of the 3D space in the simulation environment and integration of the virtual robot model with the control system,
- creation of a spatial map of the environment based on data provided by the simulation system and robot sensors,
- preparation of data structures to represent the space (POI) and the system that records the full set of information (RBG image, depth image, robot position) while following the route determined by the optimal visual mapping system
- preparation of tools for data extraction (RBG image, depth image, robot position) collected by the robot while following the route
- preparation of a navigation system that will enable the robot to effectively reach a designated point in the environment
- development of a base algorithm supporting camera data acquisition for optimal visual coverage of space mapping
- development of an API enabling integration of the solution with a semantic analysis module