iMarEx - Intelligente Maritime Exploration

In the iMarEx project, the use of both classical AI and machine and deep learning in different areas of maritime exploration is being researched and tested. In this context, AI concepts are developed, tested and finally implemented on robotic watercraft using the example of surface vehicles (wave glider, catamaran). The concrete task is for a surface vehicle to autonomously locate the source of a liquid outflow, e.g., a water body with high turbidity or pollutants, and drive to the location of the outflow to enable further actions such as sampling or investigation.

The content implementation includes robust state estimation, generation of a time-varying, dynamic environment and dispersion model e.g. for pollutants, and information-driven adaptive exploration and search strategies. In addition, optimal path planning, control, and regulation will be implemented by the project partners. Another challenge is the application of the developed methods on embedded systems, which requires special hardware solutions. For this purpose, the project partners will develop a powerful and fault-tolerant RISC-V processor system with FPGA-based, integrated AI acceleration, which will be specifically adapted and optimized to the requirements of maritime exploration missions.

Publications: