- Underwater docking
- Classification of sonar data with deep learning
- Vehicle system performance optimisation
- Hydrobatics simulator
- Autonomous underwater perception
- Underwater navigation
- Robust, flexible and transparent mission planning and execution
- Multi-agent mission planning and execution
- Air-independent energy storage
- Autonomous situation awareness and world modeling
- Underwater communication
- Demonstrator program
The aim of this project is to develop algorithms for robust, flexible and transparent mission planning and execution, within the focus areas of Safeguarding Society, Ocean Production and Environmental Monitoring.
Robustness is a key property in Maritime Underwater Robots. If a vehicle malfunction, it might be lost and prove very difficult to recover. On the other hand, flexibility and transparency are key properties, since the vehicles should be able to handle a wide range of missions without costly reprogramming by experts.
In this study we will address the challenge of providing a system that is both flexible and user-friendly for non-experts, while at the same time robust in the sense that the risk of losing the vehicle is minimized. We will also strive to make the system transparent, in the sense that the user can understand the planning being made and the decisions taken, and therefor trust the autonomous system to execute the given missions. Finally, we try to achieve the objectives above while using a combination of model based and data driven design methods.
Petter Ögren, assoc. Professor Robotics, Perception and Learning KTH – Project leader
Mart Kartasev, PhD student