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, the AIDERS project will capitalize on:
- 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,
- design online machine learning algorithms to process and analyse the received data in real-time in order to build knowledge maps, and
- implement novel visualizations that higher-command can use to take intelligent decisions.
OUTPUTS:
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.
1. Needs assessment and value of AI algorithms in situational awareness
Firstly, through the knowledge gained, the first responders will be in a better position to assess the value and need of AI algorithms in situational awareness. In addition, through the interactions between the first responders in the project (as well as collaborators) and the technical partners of the consortium, application-specific needs will be identified and reported so as to engage the community even after the end of the project in considering and addressing these needs.
2. Design and development of a novel AI toolkit
Moreover, the aim is to address some of these needs of high priority during the project duration by developing the proposed AI toolkit. This toolkit will be implemented and tested in at least 4 real-life exercises to demonstrate its value and applicability in emergency response missions. The developed AI toolkit will be provided through the project’s website to any interested party to download and use on their own using off-the-shelf computing hardware. In this way, we ensure that its applicability is not restricted to the consortium members only but the international community can access and gain the benefits of the innovative solutions provided by the AIDERS project.
3. Testing and Evaluation in field exercises
Moreover, the testing and evaluation during the field exercises will allow for drafting processes and procedures in the use of AI techniques and algorithms in operational conditions. These draft guidelines will not only be part of the AIDERS project deliverables but also be used in the various dissemination and training activities conducted by the project partners.
4. Training activities
Overall the experience gained from all project outputs (i.e., knowledge, AI toolkit and field exercises) will be shared to the first responder community through a number of targeted training activities including the UCPM AMC training (conducted 4 times per year in Limassol, Cyprus). In addition to the AMC training, each of the participating consortium members will be hosting a national training event in conjunction with one of the project meetings where the national first responder agencies will be invited to attend.
Summarizing, all the project outcomes have an international outreach and are applicable to civil protection as well as other first responder agencies. As indicated above the project outputs will result to new knowledge and deliver on an innovative AI solution that will harness the increasingly vast amount of data RPAS units can provide to first responders. The field exercises and the expertise gained in deployment of the toolkit will provide the experience to develop processes and procedure for the introduction of this new technology to the operational workflow of emergency response missions.