The project aims to automate the detection and recovery of floating waste (bottles, floating debris, oil slicks, etc.) by the Mass Cleaner maritime drone, in partnership with Efinor Sea Cleaner. Based in Paimpol, this French company designs multipurpose vessels dedicated to cleaning seas, rivers and ports, and has delivered more than 170 units. The
Mass Cleaner is its surface drone, capable of operating either remotely or autonomously.
Reducing the need for manual supervision is a key lever for scaling up, but it must not come at the expense of safety or reliability. To enable the algorithm to accurately perceive its environment, detect obstacles and plan its movements autonomously, our team developed several technology building blocks: sensor data fusion, construction of a consistent tactical picture, mission planning and adaptation to local contingencies, and management of interactions with a human operator, who supervises operations and can approve the collection of detected waste when there is uncertainty.
Before any deployment on the Mass Cleaner, we needed to be able to test, simulate and replay all of these behaviours in a controlled environment that faithfully reproduces navigation conditions (waves, currents, sensor noise) as well as the other entities around the boat.