The aim of this project is the development of an innovative monitoring technology, which can recognize and characterize plastic waste in an automated and large-scale process. The new system will be able to determine the current state of the plastic and couple the results with geo-referenced data. This way the scale of pollution as well as the changing properties of plastic waste can be determined over long periods and cleaning efforts planned accordingly. In order to apply this strategy in deeper waters the system should not only be diver based but integratable into underwater vehicles (ROV/AUV). The resulting data is interpretable without expert knowledge thanks to automatically generated color-coded maps which are a valuable asset in the ongoning battle against plastic pollution of the oceans. This way they can help political actors or NGOs in the development of strategies or legal initiatives as well as inform the general public about the scale of the plastic-waste problem.

Duration: 01.08.2020 till 31.10.2022
Donee: German Research Center for Artificial Intelligence GmbH
Sponsor: Federal Ministry for Economic Affairs and Climate Action
Grant number: Gefördert durch das BMWi aufgrund eines Beschlusses des Deutschen Bundestages, Förderkennzeichen 16KN091223

planblue GmbH (coordinator)
KSW - Kurt Synowzik Werkzeug u. Maschinenbau GmbH & Co. KG
University Stuttgart, Institute for bio-materials and bio-molekular systems -  Comparison/feedback/optimizations

Application Field: Underwater Robotics

Project details

Plastic waste in a coral-reef (Foto: Joost den Haan - planblue )
The developed components will be verified in a controlled laboratory environment by identifying  plastic-sendiment samples with known composition. These experiments will be conducted in DFKI's 20m³ basin, which can simulate sea-floor conditions by controlling illumination and turbidity. In the next step the new system will be evaluated in a lake environment. This way the developed technology can be transferred to all aquatic environments.
In addition the technology is relevant for monitoring of underwater structures such as offshore-wind, aquacultures or for harbor environments the software can be used to process hyperspectral images even in air.
For effective monitoring a coverage-planning strategy is required in order to map areas consistently. Typical pre-planned lawn-mower trajectories are not optimal for such tasks since they cannot integrate additional constraints due to limitations of divers (dive time, max-depth), ROVs (cable constraints) or AUVs (battery). DFKI will focus on development of a coverage-planning stategy which suits these needs.
The project is funded by the German Ministry of Economic Affairs and Energy (BMWi) inside the ZIM-cooperation network „Plastik-Monitoring in europäischen Gewässern – PlaMoWa Europa“ from 1. August 2020 until 31. October 2022.

Project partners: 

- planblue GmbH (coordinator) – Development of hyperspectral camera algorithms
- DFKI GmbH, Robotics Innovation Center – Development of planning algorithms, test environments
- KSW - Kurt Synowzik Werkzeug u. Maschinenbau GmbH & Co. KG – Development of underwater housing
- University Stuttgart, Institute for bio-materials and bio-molekular systems -  Comparison/feedback/optimizations
- GlobalGreen InnoTech GmbH - ZIM netzwork management for PlaMoWa Europa


MtecPla Project: Lab Tests for Marine Plastic Detection

Back to the list of projects
last updated 04.01.2024