An RGB-D based Augmented Reality 3D Reconstruction System for Robotic Environmental Inspection of Radioactive Areas

Preparing human intervention in hazardous, unknown and unstructured environments is a difficult task. The intervention should focus on the optimization of the operations in order to reduce the personnel exposure to hazards. Optimizing these operations is not always possible, due to a lack of information about the intervention environment: such information can be collected through a robotic inspection before the preparation of the intervention. The data collected during this inspection, such as radiation, temperature and oxygen level, must be accurate and precisely positioned in the environment in order to optimize the humans approaching path and their stay in the intervention area. In this paper we present a robotic system for collecting physical quantities, precisely positioned in the environment, which is easy to use by the robot operator and it is seamlessly integrated in the robot control. The operator is helped by the system in finding the most dangerous zones, which collects all the sensor readings while building a 3D model of the environment. Preliminary results are presented using CERN's accelerators facilities as testing area.