Nowadays, the major part of offshore operations is done by divers in dangerous missions. Since their number is limited, the dependency on their work represents a real threat to the offshore industry. The extended use of unmanned underwater vehicles (AUVs/ROVs) could solve this problem but since they are usually tailormade for a specific task and difficult to operate their deployment is very expensive. The overall goal of the SWARMs project is to expand the use of AUVs/ROVs and facilitate the creation, planning and execution of maritime and offshore operations. This will reduce the operational cost and increase the safety of tasks assigned to divers. The SWARMs project aims to make AUVs/ROVs accessible to more users by:
- Enabling AUVs/ROVs to work in a cooperative mesh thus opening up new applications and
ensuring re-usability as no specialized vehicles are needed but heterogeneous standard vehicles can
combine their capabilities,
- Increasing the autonomy of AUVs and improving the usability of ROVs The approach is to design and develop an integrated platform (a set of Software/Hardware components),incorporated into the current generation of underwater vehicles in order to improve autonomy, cooperation, robustness, cost-effectiveness, and reliability of the offshore operations. SWARMs’ achievements will be demonstrated in two field tests in different scenarios:
*Inspection, maintenance and repair of offshore infrastructure
*Pollution monitoring
*Offshore construction operations
SWARMs is an industry-led project: big technology companies will collaborate with SMEs specialized inthe subsea, robotics and communication sectors and universities and research institutions to ensure that the newest innovations in subsea robotics
The genetic algorithm census transform: evaluation of census windows of different size and level of sparseness through hardware in-the-loop training (Jul 2020) Carl Ahlberg, Miguel Leon Ortiz, Fredrik Ekstrand, Mikael Ekström Open Access Journal of Real-Time Image Processing (J RT Image Proc)
Extended Colored Traveling Salesperson for Modeling Multi-Agent Mission Planning Problems (Feb 2019) Branko Miloradovic, Baran Çürüklü, Mikael Ekström, Alessandro Papadopoulos 8th International Conference on Operations Research and Enterprise Systems (ICORES 2019)
Unbounded Sparse Census Transform using Genetic Algorithm (Jan 2019) Carl Ahlberg, Miguel Leon Ortiz, Fredrik Ekstrand, Mikael Ekström WACV 2019 - IEEE Winter Conference on Applications of Computer Vision (WACV'19)
A genetic mission planner for solving temporal multi-agent problems with concurrent tasks (Aug 2017) Branko Miloradovic, Baran Çürüklü, Mikael Ekström International Conference on Swarms Intelligence (ICSI'17)
An Optimized, Data Distribution Service-Based Solution for Reliable Data Exchange Among Autonomous Underwater Vehicles (Aug 2017) Jesus Rodríguez-Molina , Sonia Bilbao Arechabala , Belen Martinez Rodriguez , Mirgita Frasheri , Baran Çürüklü Sensors (SENSC9)
Algorithms for the Detection of First Bottom Returns and Objects in the Water Column in Side-Scan Sonar Images (Jun 2017) Mohammed Al-Rawi , Fredrik Elmgren , Mirgita Frasheri , Baran Çürüklü, Xin Yuan , José-Fernán Martínez-Ortega, Joaquim Bastos , Jonathan Rodriguez , Marc Pinto OCEANS '17 A Vision for our Marine Future (OCEANS '17)