Drone Search and Rescue – Project ICARUS
Project ICARUS was born out of a disaster, seeing that drone search and rescue was still far better theoretically than in practice.
ICARUS, a drone search and rescue project in the EU, notes this on its website:
“After the earthquakes in l’Aquila, Haiti and Japan, the European Commission confirmed that there exists a large discrepancy between (robotic) technology which is developed in laboratory and the use of such technology on the terrain for Search and Rescue (SAR) operations and crisis management.
Thus, the European Commission’s Directorate-General for Enterprise and Industry decided to fund ICARUS, a Research project (global budget: 17.5M€) which aims to develop robotic tools which can assist “human” crisis intervention teams.”
We reached out to this project team to learn more.
Q. We are intrigued by your efforts with Project ICARUS, could you tell our readers a bit more about this drone search and rescue project?
A. It all started about 4 years ago when there were some major natural and man-made disasters like the earthquakes in Haiti and L’Aquila (Italy). Later came the Costa Concordia shipping incident in Italy and the Tohoku earthquake and tsunami in Japan. Especially this last incident made it very clear that – while there was a lot of interesting robotic technology developed in research labs – these systems were not really ready be used in real crisis management operations. As a result, the European Commission decided to fund a research project called ICARUS, which aims to bridge the gap between the robotic research community and end-users.
Q. This research project, which has a global budget of 17.5M€, aims to develop robotic tools which can assist “human” crisis intervention teams. What types of tools are you developing?
The objective of the ICARUS project is to develop robots which have the primary task of gathering data. The unmanned search and rescue devices are foreseen to be the first explorers of the area, as well as in situ supporters to act as safeguards to human personnel. In order not to increase the cognitive load of the human crisis managers, the unmanned search and rescue devices are designed to navigate individually or cooperatively and to follow high-level instructions from the base station. The robots connect wirelessly to the base station and to each other, using a wireless self-organising cognitive network of mobile communication nodes which adapts to the terrain. The unmanned search and rescue devices are equipped with sensors that detect the presence of humans and are also equipped with a wide array of other types of sensors. At the base station, the data is processed and combined with geographical information, thus enhancing the situational awareness of the personnel leading the operation with in-situ processed data that can improve decision-making. All this information is integrated in the existing command and control systems used by the forces involved in the operations. Moreover, e-training tools are put at the disposal of the end users in order to allow them to train the use of the different ICARUS tools.
Q. Are you working on any UAV (air-based) solutions and, if so, what are the biggest technical and regulatory challenges?
Every crisis and operation is different, so it is not possible to develop one UAV system which would be good for all operations. Therefore, three different aerial platforms were developed within the scope of this project. The first UAV is a light (6kg) solar aeroplane which can stay in the air for days at lower altitude (typical cruising altitude around 200 meters) and is ideally suited for fast mapping operations or for improving the situational awareness of the rescue workers. The second aerial platform is an octocopter which is ideally suited for targeted victim search operations using its infrared and visual cameras. This outdoor rotorcraft is also able to deliver rescue kits (floatation devices, water, …) to any victims found. The third aerial platform is a small indoor rotorcraft with advanced autonomous navigation capabilities, enabling it to enter semi-demonished buildings, searching for survivors, even when the communication link to the operator fails.
If drone search and rescue robots are to become a success, then an essential point is the introduction of these robotic systems in the standard operating procedures of the search and rescue workers and in the regulatory framework. In the event of a crisis, it is crucial to be able to deploy quickly, but also in line with the regulatory framework of the host country. Therefore, regulatory challenges have been addressed from the design phase. As regulation varies widely across the world, it is at present impossible to build a UAV which will automatically get a flight permit everywhere. However, in most countries it is the case that flight permits are more difficult to obtain for heavier systems and if you want to fly higher. As a result, we deliberately restricted ourselves to low-weight aircraft being able to operate at low altitudes.
Q. Are you working on any AUV (water-based) solutions and, if so, what are the biggest technical and regulatory challenges?
ICARUS mostly concentrates on finding live survivors, so the efforts on water-based robots concentrate on unmanned surface vehicles. Also here, a multi-scale approach was followed and three different types of assets were developed for conducting different kinds of operations. First, a slower USV with extensive autonomous sensing capabilities was developed for operations close to the seashore. Secondly, a very fast and larger intervention USV was developed for operations further away where speed is a crucial issue. At last, novel unmanned rescue capsules were developed which can be deployed from any of the aforementioned USV. These unmanned rescue capsules can propel themselves towards victims in the water and carry a floatation device (life raft), enabling multiple people to save themselves.
Q. What are the biggest drone search and rescue successes you have had to date with this project?
The project has already demonstrated sound results in realistic operating conditions during 2 main trials. At the training centre of the Belgian First Aid and Support Team, integrated operations between ICARUS land and aerial robots were demonstrated. The same was done at the NATO Centre for Maritime Research and Experimentation, for the ICARUS marine and aerial robots. These tests were great successes. However, the proof of the pudding is in the eating. As one of few research projects, ICARUS deployed a robotic system in a real crisis. In the period between end of May and beginning of June 2014, Bosnia and Herzegovina and Serbia were hit hard by catastrophic massive flooding after abundant rainfall over a few weeks causing floods and landslides. An Unmanned Aerial System was deployed on-site in collaboration with traditional relief workers, to support them with damage assessment, area mapping, visual inspection and re-localizing the many explosive remnants of war which have been moved due to the flooding and landslides. Novel robotic technologies and data processing methodologies were brought from the research labs and directly applied onto the terrain in order to support the relief workers and minimize human suffering. The response from the response teams brought into contact with the unmanned tools was very positive, as they see the clear advantages of the system. One of the end-users noted that the aerial assessment done by the UAS in 2 hours saved the team 3 days. Such important time-savings can be a matter of life and death in crisis response scenarios.
Q. This is a European effort but are there any plans to coordinate efforts and partner with countries on other continents?
We are in touch with similar efforts in the United States and Japan. Cross-continental, coordination of more technical research aspects is more difficult, but there are an important coordination actions going on in the domains of standardisation and validation. These are important aspects, as it is not easy to define quantifiable metrics to benchmark the performance of the different systems in realistic operating conditions, while this is really needed to drive the innovation. Another area of cross-continental collaboration is the user acceptance and the integration of robotic technology in the standard operating procedures of the search and rescue community, as this is a global challenge.
Q. What should we have asked you about this project and/or drone search and rescue more broadly?
We also developed two unmanned ground vehicles. The first one is a large vehicle which is more intended for “national” kind of operations. This vehicle is capable of driving over very rough terrain and carries a powerful manipulator arm, enabling it to apply structural changes to the environment (clear debris, breach through walls, do shoring operations, …) The second ground vehicle is much smaller and is intended to search for human survivors in semi-demolished buildings.
