A game for robot operation training in Search and Rescue missions

Abstract

Search and rescue (SAR) teams often face several complex and dangerous tasks, which could be aided by unmanned robotic vehicles (UV). UV agents can potentially be used to decrease the risk in the loss of lives both of the rescuers and victims and aid in the search and transportation of survivors and in the removal of debris in a catastrophe scenario. Depending on the nature of a catastrophe and its geographical location, there are potentially three types of UVs that can be deployed: aerial, surface and ground. Due to the control and manipulation particularities each type of UV contemplates, their operators need prior training and certification. To train and certify the operators a tool (serious game) is under development. In this paper we will make an overview about our approach in its development. This game uses a typical client-server architecture where all client agents (virtual UVs and operator client interfaces) share the same immersive virtual environment which is generated through the merging of GIS data and a semantic model extracted from 3D laser data. There will be several types of scenarios suitable to several types of catastrophe situations. Each of these scenarios has its own mission plan for the trainees to follow. The game will also provide an interface for mission planning so that each mission plan will be carefully designed to accurately correspond to a matrix of skills. This matrix lists a set of common skills in various different UV operational case studies which will allow the certification of operators.