Real-time Artificial Intelligence for DEcision support via RPAS data analyticS

ended

Currently, the majority of first responders seeking to introduce remotely piloted aircraft system (RPAS) units into their operations are quickly stumbled upon the deluge of collected data and reside merely on snapshots to inform incident commanders of the situation in the field. The AIDERS project aims at developing application-specific algorithms and novel mapping platform that will harness the large volume of data that first responders are now able to collect through heterogeneous sensors (including visual, thermal and multispectral cameras, LIDAR, CBRN sensors, etc.) on-board RPAS units, and converting that data into actionable decisions for improved emergency response. To address this challenge, this project will capitalize on: 1) the long-lasting collaboration of the first responder and technical partners in the consortium to identify which information needs to be extracted from the collected data, 2) design online machine learning algorithms to process and analyse the received data in real-time in order to build situational maps, and 3) implement novel visualizations that higher-command can use to take intelligent decisions. The AIDERS project activities will result in 4 main outputs, namely: 1) knowledge on potential use of AI techniques and algorithms for acquiring valuable information of the incident, 2) a novel AI toolkit will be developed to provide relevant, reliable, and timely information from the available aerial sensor data, 3) field exercises will be conducted to evaluate the integration and performance of the AI toolkit, and 4) conduct a number of training activities to first responder experts. These outputs will be the drivers of the project to achieve its objects. All the project outputs have an international outreach and are applicable to civil protection as well as other first responder agencies which will have the chance to access and integrate in their own mission cycle.