Marine biofouling has a tremendous economic and environmental impact; it can lead to >€1m in lost revenue per ship per year in fuel overconsumption alone. The International Maritime Organization estimates that gas emissions may increase between 38% and 72% by 2020, unless corrective measures are taken. The only way to mitigate biofouling is to detect it at an early stage (Level of Fouling – LoF 1), while it can still be cleaned with soft methods that do not damage hull paint or coating. With current approaches this is impossible, particularly within port waters as they are heavily turbid and inhibit visibility. Inspections outside port waters induce charter-off time that costs >€20k per day and are thus avoided by ship operators. SleekShip comprises a Semi-Autonomous Underwater Vehicle (SAUV) carrying a hyperspectral camera that captures light wavelength bands where light backscattering is less and the slime is easier to distinguish despite contamination. The inspection can take place in port waters while the ship is docked for other operations thus no additional charter-off time is incurred. An integrated cavitation-based cleaning tool allows for 100% paint-safe cleaning. By detecting biofouling early, ship owners will be able to achieve >€1.3m savings per vessel annually by reducing fuel overconsumption and paint/coating damage caused by hard-brush cleaning. Our consortium comprises SubseaTech, a dynamic manufacturer of underwater robots, QCELL, a high-tech SME specialising in hyperspectral imaging, M.Danchor a leading cleaning and inspection services company, TWI, the global leader in image-based underwater inspection technologies and Danaos, a NYSE-listed containership owner. Through SleekShip we aim to achieve sales of €41m, generating €17.9m profits and >110 jobs while helping the shipping industry save €3.4bn per year and reduce CO2 emissions by 115m tonnes over the 5 years after market launch. The Net Present Value ROI is 4:1 on EC funds with a grant.

X-ray imaging is a key component of applications ranging from medicine and food to security and industrial non-destructive testing (NDT). Current approaches to X-ray detection however are limited with respect to shape flexibility and material cost. Inherent inflexibility of the digital electronics and scintillating materials used both in charge integrating and particle counting detectors leads to inaccurate imaging of complex geometries due to geometric magnification. This is particularly problematic in industrial NDT where defects in complex shapes are easy to miss, and in medical applications where early detection of abnormalities can make the difference between life and death. In medical applications, the inability to resolve complex features within the human body is offset by higher radiation dosage, thereby increasing health risks. Moreover, current architectures require the hardware and electronic systems to be placed across the beam path. Thus, they need to be radiation-hardened sacrificing pixel density, greatly increasing the cost of manufacturing, limiting shelf life and making maintenance practically impossible. FleX-RAY completely redefines X-ray detectors by introducing an utterly novel design where the hardware and electronics for detection are placed outside of the beam path, greatly reducing material and manufacturing costs. Our architecture achieves unprecedented versatility as multiple grids of fibres can be stacked to enable finer resolutions as well as particle tracking capabilities. Finally, by leveraging fiber Bragg gratings, our detector’s shape can be interrogated in real-time removing the need to know the imaged geometry beforehand. Our project brings together cross-disciplinary expertise in materials, fibre optics, analogue and digital electronics and particle physics to produce the world’s first ultra-flexible, low-cost, self-shape reporting X-ray detector that will enable 10x higher resolution at half the price of current approaches.

The WEEE (waste from electrical and electronic equipment) management chain has realised an explosion of fire incidences, caused by carelessly discarded batteries into either recycling bins or black rubbish bags, where they are easily damaged by sorting equipment and start to burn, endangering human lives, disrupting waste services and causing millions of Euros of damage (from €190,000 up to €1.3m per fire incident). The Grinner project aims at commercialising an autonomous AI-enabled robotic sorting system capable of detecting and removing waste containing batteries from current waste streams before they enter inhospitable-to-battery machines that crush and consolidate waste. The system will comprise (i) the fastest Energy-resolved X-Ray detectors in the market, (ii) an ML-enabled software module that will analyse X-Ray data and effectively detect waste containing batteries while passing through the waste flow and vision-based pick-and-place robot(s) that will remove the flagged WEEE. Project objectives: • Build an X-Ray data set of WEEE scrap. • Customisation of the X-Ray system • Develop the AI software module for detection of batteries within WEEE using X-Ray data. • Deploy a vision-based robotic solution capable of Picking-and-Placing WEEE • Develop, integrate and install a prototype system in a WEEE facility environment to conduct live trials and validate Grinner. • Explore the potential exploitation of Grinner as an economically viable, stand-alone product for recycling facilities.

The fresh food industry is highly labour-intensive, with labour costs often contributing up to 50% of overall production costs. Pressure is growing to reduce production costs while facing major labour shortages. So far robotic automation for picking of delicate fresh produce has been impossible mainly due to the complex, contact-rich interactions involved in such tasks. SoftGrip will deliver an innovative soft gripper solution for the autonomous picking of delicate white button mushrooms cultivated on Dutch shelves. The versatility of the proposed solution will enable the adoption of the technology by other fresh-food industries experiencing similar stringent handling requirements such kiwifruit, grapes, etc. Towards this goal, our consortium will develop: (a) low-cost, soft robotic grippers having built-in actuation, sensing and embodied intelligence that enable reliable and efficient picking of mushrooms; (b) material synthesis and fabrication techniques that offer precise tuning of mechanical properties, comply with food-safe standards, allow for chemical recycling and offer self-repair properties; (c) a set of accelerated continuum mechanics modelling algorithms that facilitate real-time model-based control schemes, capable of being executed by limited computational resources. (d) advanced learning capabilities of the soft gripper through a learning by imitation framework comprising multi-task and meta-learning techniques, so that SoftGrip can be deployed with minimal programming effort. SoftGrip will enable a step change in efficiency, helping mushroom growers cut down on costs by >30% and increase their yields by >20% while also improving job quality in the industry. In the long-term, it will lower the barriers of robotics deployment open up new opportunities for adoption of robotic solutions in the agri-food sector.

The European water network distribution is plagued by leaks that cause a staggering 20% of drinking water to go wasted. This is an environmental disaster given that water and sanitation sector is currently estimated to contribute up to 5% of global GHG emissions. Water utilities are struggling with this problem however the deadalic nature of water networks make manual inspections and repairs completely non-viable. Technology-based solutions have significant limitations in terms of measurement accuracy and leak localisation. Most importantly they do not encompass repair. TUBERS sets forth a new paradigm by creating the worlds first combination robotic platforms allowing for 24/7 inspection and targeted in-situ repairs, greatly reducing the costs of regular inspection and maintenance. The system will comprise: (a) A snake-like resident robot which can operate over long distances and negotiate pipeline-junctions to navigate large parts of the water network, (2) A modular soft-robotic platform capable of moving using an inchworm movement technique, for inspections and repairs of pipe segments featuring a novel repair deployment mechanism (3) A High-accuracy inspection system that can detect leaks and, most importantly, measure corrosion based on coded excitation, an advanced technique that greatly improves Signal-to-Noise ratio, (4) A Decision Support System powered by Explainable Machine Learning algorithms incorporating a Multi-Criteria Decision Analysis framework for holistic planning of inspection and maintenance. The TUBERS solution will be validated in real water network pipelines operated by 3 of the most prominent water utility companies in the Netherlands. Once it reaches the market, our solution is poised to revolutionise inspection and repair of drinking water networks, providing the operators with powerful tools to eliminate waste, facilitating savings of an estimated 158GWh of energy and reduction of 79.000 tonnes of CO2 emissions within a 5-year period.