Immersive4Learning
Company info:
Name: ARVRtech
Partners:
Cadix
Company info:
Name: Wegoto
Date founded: 2015
Number of employees: 3
Location: Montbonnot St-Martin (France)
Wegoto develops solutions to capture geographic data in the field & connect geographic information systems (GIS) to a multimodal mobility platform, for real time data update and dissemination.
Partners:
Real-Time 3D scanning system for Accessibility diagnosis
in urban environments
Challenge
Digital 3D city maps are useful for many applications, for instance, urban planning, emergency response simulation, virtual tourism and illustration of historical buildings, route planning, accessibility analysis for different types of mobility and profiles. Basically, different types of maps can be created, depending on the application requirements. The main acquisition techniques that can be found in the literature are either highly time consuming (with many manual post-treatment to build the 3D map) or they are highly computational demanding (with off-line treatment of the raw data and large memory storage) while the spatial resolution might be not sufficient for the targeted application.
The objective of CADIX is to develop an integrated system that complements today WEGOTO LabTrack, a trolley designed to collect data in pathways to later perform accessibility analysis and route planning for people with different profiles and (dis)abilities in the context of soft mobility.
Solution
CADIX captures at low cost 3D data from different range sensors. These data are fused in real-time, leading to a compact source of 3D information. The LabTrack-CADIX solution is a hybrid measurement system with cameras, telemeters, Time-of-Flight sensors, LiDAR together with GPS localisation of the obstacles present in the pathway. This LabTrack-CADIX solution extends the current database with “safety cocoon” information, i.e. information regarding a safe volume defined around the LabTrack.
FED4SAE Support
Wegoto business model is based on collecting and disseminating urban geographic data. FED4SAE allows Wegoto to access CEA support to revisit the architecture (hardware and software) of the LabTrack, taking into account sensor characteristics, computing and memory needs and ease the integration of an encoded wheel that triggers data acquisition every time the LabTrack travels 1m. Thanks to CEA expertise, CADIX firmware was developed using ROS (Robot Operating System) and integrating SigmaFusion™ to fuse data in 3D from the different range sensing technologies, i.e. LiDAR, stereo camera and Time-of-Flight sensors (from STM) acquired through a STM32 platform, provided to the project by STM. Tests have been conducted with the prototype in laboratory environment. Then, the LabTrack-CADIX system will be validated tests in real-life environments.
Impact
Wegoto is currently accelerating its development and in search for financing to sustain its business roadmap. Wegoto will continue to invest in R&D activities to accelerate and increase its data collection speed. The CADIX project is fully part of Wegoto corporate strategy and complementary to future envisaged projects, in particular in the field of imaging.
Videos
SureWash
Company info:
Name: Surewash-Glanta
Date founded: 2010
Number of employees: 7
Location: Dublin, Ireland
SureWash uses its patented gesture recognition application to teach staff, patients on the proper hand hygiene protocol to WHO handwashing standard.
Partners:
SureWash Hand Hygiene guidance and measurement system over the sink
Challenge
According to the European Centre for Disease Control (ECDC), almost 9 million infections occur each year in European hospitals and long-term care facilities Hospital Acquired Infections kills 100,000 US Hospital Patients each year and cost $45 B PA. The World Health Org (WHO) estimate that 50% of infections could be prevented with better hand hygiene using systems like SureWash™. Seven percent (7%) of all Hospital patients in developed countries acquire infections (HAI).
In response to the challenge, the WHO have developed a seven step handwashing protocol that mitigates the risk of bacteria remaining on washed hands. Glanta have developed a Augmented Reality system called surewash™ that trains Hospital & Nursing home staff on this WHO Protocol developing their muscle memory.
Solution
Glanta now wish to develop an Over The Sink hand wash monitoring system (Surewash OTS) that will provide real-time feedback to the users as they are washing their hands as to their compliance to the WHO handwashing protocol. The goal is to increase staff compliance thus reduce infections and avoiding the need for antibiotics, improve patient experience and shorten hospital stay, overall resulting in lives saved and significant cost avoidance.
FED4SAE Support
The goal of SureWash™ in partnership with Intel, CEA and IRT-Nanoelec is to develop an Over The Sink system that improves hand hygiene in healthcare and food preparation markets The SureWash™ OTS will gather real-time data on hand hygiene quality that can be used to manage the risk of cross contamination in hospitals and kitchens.
The SureWash OTS solution will leverage Intel’s MyriadX™ hardware which accelerates the execution of convolutional neural networks used in Artificial Intelligence based Computer Vision along with Intel Realsense™ depth sensing camera.
The final system will be evaluated in the IRT-Nanoelec testbed facility. Functional testing will include privacy and cybersecurity compliancy assessment as well as usage analysis and user acceptance with potential customers. As part of the FED4SAE suite of services, SureWash is receiving support in business modelling, market insights and design to cost from Blumorpho and CEA-Open Innovation team.
Impact
A working prototype was developed and deployed at Korian Nursing Homes in France and while the feedback was very positive, Korian identified the need to prioritise training and hand hygiene awareness to their staff and it is monitoring product development.
The final product is expected to go to market in 1H 2020. As this has the potential to be a life saving solution, that can deliver huge benefits in a completely new market, the potential is huge and Intel will use its global presence to assist Surewash in exploring market opportunities.
Video
Protolab
Company info:
Name: Protolab srl
Date founded: 2010
Number of employees: 5
Location: Padua, Italy
High-tech SME developing innovative complete solutions tailored to customer needs and providing integrated systems & services.
Partners:
Development of a smart sensor kit for monitoring of scoliosis treatment braces
Challenge
Each year about 2% of European teenagers must be treated with braces (spinal orthosis) to counteract the evolution of scoliotic curve by applying a mechanical stress against the body and favouring the correct posture of rachis. Despite the need of recording the exerted pressure expressed by orthopaedic specialists, there is currently no device available, in the market, able to quantitatively measure acting forces inside the braces and to monitor the wearing time. Market analysis outlines big potential in the scoliosis management market, stressing increasing year to year demand still not satisfied by products on the market. It also identifies among main drivers the advancement of technology with tracking devices that can monitor the patient health evolution.
Solution
Protolab aims at: i) developing an innovative plug & play wearable sensor kit for monitoring the pressure inside scoliosis braces, ii) improving the compliance with medical prescriptions and iii) boosting the patient active participation in order to reach satisfying results from the care treatment. Digitization will boost the development of automated analysis to frequently check treatment progresses, while the availability of gathered data will allow the use of predictive algorithms to favour rapid intervention in case of wrong trends, thus favouring the active participation of the patient to the care treatment.
FED4SAE Support
Thanks to FED4SAE project that leverages the collaboration with STM, CEA-Leti and IRT Nanoelec, Protolab will first develop a prototype system based on a novel STM32 microcontroller referred as STM32WB that integrates all the hardware means to support Bluetooth™ 5.0 and IEEE 802.15.4 wireless standards such as ZigBee 3.0 and Openthread. The STM32WB will be used to collect data from sensors, to process them and then transferred via BLE to a dedicated smartphone app for representation and further analysis.
Then tests of the new prototype data communication in realistic conditions will be performed in the Products & Technologies Living-Lab (PTL) of IRT Nanoelec at CEA-Leti in Grenoble. The evaluation of regulatory constraints related to patient’s data management will be assessed as well, including evaluation of the cybersecurity and privacy risk analysis. Then the miniaturized and integrated solution will be developed and tested in the same realistic environment.
Innovation management & business expertise provided by Blumorpho will support Protolab in the identification of the strategy and the statutory constraints in order to secure the go-to-market strategy.
Impact
Protolab targets to enter the market by end of 2020, its customers being the braces manufacturers, fragmented in 1 or 2 major players geographically distributed in every region. The overall EU market is estimated at 100 000 braces per year, e.g. more than 60 M€/year. The niche market represents a great opportunity for Protolab where two strategies can be addressed with two different growth perspectives: 1) in-house growth, 2) direct investment from a top player in the market of Orthopaedics.
Video
HSENS
Company info:
Name: Encore Lab SL
Date founded: 2010
Number of employees: 1500
Location: Logrono, Spain
Encore Lab is a technology-based company whose main objective is the development of innovative solutions in three technical areas: development of electronic devices, advanced software and data analysis via data mining.
Partners:
New low consumption and autonomous soil humidity sensor with fast deployment
Challenge
Water is a key resource for agriculture both for the economic and environmental sustainability. The volume of water used for irrigation per year in EU-28 is 39.8 billion m3. However, effective irrigation is only 35% of this amount.
Irrigation of crops is usually applied based on a fixed schedule or even on the farmers intuition. Despite technologies such as soil moisture sensors are available in the market to help farmers make better decisions on water management, there is a poor market penetration for these technologies.
Solution
ENCORE aims to design a low cost Cyber-Physical-System that will integrate sensing, logging and remote communication functionalities. Using the latest low consumption IoT technologies such as Ultranarrow Band protocols and the new generation of low power microprocessors STM32-L0.
Additionally, the envisaged system will be designed to make the deployment process very easy so no specialized staff will need to be involved (DIY concept) and only a simple app will guide the user during the process.
Impact
Soil moisture monitoring is the more direct method to assess the real need for irrigation in agriculture. With the world’s population set to increase by 65% (3.7 billion) by ∼2050, the additional food required to feed future generations will put further enormous pressure on freshwater resources. Agriculture is the largest single user of fresh water, accounting for ∼75% of current human water use.
Globally, in both irrigated and rain fed agriculture only about 10–30% of the available water (as rainfall, surface or groundwater) is used by plants as transpiration, being even a lower figure (5%) in arid areas.
In this context, improving water use efficiency in agriculture could not only make a better use of this scarce resource but also reduce the energy consumption derived of the use of pumps and other devices involved in irrigation.
HSENS proposes a new technology that will significantly contribute to these goals, allowing to reduce the consumption both of water and energy by more than 30% in agriculture. Thus, only in Europe the new system would allow to save almost 12 billion m3 of water per year.
Video
Artomatrix
Company info:
Name: Artomatix
Date founded: 2012
Number of employees: 26
Location: Dublin Ireland
Artomatix is an award winning software company that uses Artificial Intelligence to transform 3D artistic workflows in top creative arts studios worldwide.
Partners:
Artificial Intelligence based algorithm for image quality enhancement
Challenge
Steaming Video Content accounts for 63% of Internet Traffic today and future traffic volumes forecast significant increase as a result of more internet users, more smart devices along with the demand for higher resolution content from HD to 4K or 8K UHD. The challenge of the project is to deliver high quality video experience to the user by increasing the compression and decreasing the resolution of the source stream. This will have the potential to massively reduce global internet traffic, improving the user experience and benefitting the World at large.
Solution
Artomatix goal is to develop a more efficient method to deliver high-resolution content to the user while minimising the network traffic and associated infrastructure costs. So the challenge is to enable data to be transmitted / broadcast at a low resolution and then upscaled and enhanced in real-time on the user’s device by applying “AI at the edge” to deliver that compelling user experience.
By exploiting the capabilities offered by new AI approaches and applying CNNs to image upscaling, Artomatix are developing an efficient high-quality hardware independent upscaling engine which can be licenced to and exploited by multiple platforms such as the TheoPlayer™ multi-platform player.
FED4SAE Support
FED4SAE has enabled Artomatix to further a collaboration with Intel; receive support from CEA-Leti and receive advice on the management of innovation and the got-to-market strategy from Blumorpho.
Artomatix have built a stripped-down version of its image-enhancement NN making it compatible with resource-limited hardware such as the Intel ® Movidius™ Myriad VPU in the Intel Neural Compute Stick hardware with almost unperceivable quality loss. Thanks to the collaboration with CEA, Artomatix is now operating an industry-standard-based image and video compression testbench for enhanced-images quality assessment and NN training.
Impact
Artomatix aim to be the “Adobe of Creative AI” and they plan to double their workforce from 20 to over 40 by the end of 2020. There are multiple markets that can benefit from this technology from Creative AI, e-Sports and streaming media and one option is to licence their commercial solution on a “pay per use” model and address multiple markets using Software as a Service API approach.
Video
IDRD
Company info:
Name: Ubotica Technologies Ltd.
Date founded: 2016
Number of employees: 12
Location: Dublin, Ireland; Ciudad Real, Spain
Irish SME focused on delivering computer vision and AI based solutions on-the-edge.
Partners:
IDRD: In-Line Diabetic Retinopathy Detection
Challenge
Diabetic Retinopathy (DR) is the leading cause of vision loss in adults aged between 25 and 60, with a recent study estimating that the number of people worldwide with DR will grow to 191 million by 2030. Elsewhere, it has been estimated that the cost of DR to the UK economy will reach £97,000,000 by 2036. When DR is caught early, treatment is effective at reducing or preventing vision loss and while a very small number of countries have national screening programmes for DR detection in place, they are not commonplace and are costly to run.
Solution
In-line Diabetic Retinopathy (IDRD) is a light weight Computer Vision and Artificial Intelligence solution for detecting the presence of DR indicators in retinal images on-the-edge, in the specialist fundus cameras that take these images. The solution has been developed around the Intel Movidius Myriad2 Vision Processing Unit (VPU), which pre-processes the retinal images using its on-board image filtering capabilities and then applies an Artificial Intelligence Convolutional Neural Network (CNN) to assess the retinal image for DR indicators. The solution has been designed to assist ophthalmologists to accurately and consistently evaluate and diagnose DR. Ubotica are working with fundus camera manufacturers to introduce IDRD to the marketplace by 2021.
FED4SAE Support
A significant challenge in the deployment of AI based solutions is in the supervising of decisions of the CNNs which are at the core of these systems. Through the FED4SAE program we are working with fortiss to integrate their Neural Network Dependability Kit (NNDK) into IDRD. Among other features, it supports neural network (NN) verification to ensure the results do not lead to undesired behaviours, test-case generation and quality metrics computation to increase model robustness, and runtime monitoring to check if a decision of a deployed model is supported by the training data. In this way we are introducing a level of confidence to IDRD that heretofore was not possible, giving us a credible Verifiable AI element to our offering. In addition, working with our FED4SAE partners fortiss, Intel and Blumorpho has had a very positive impact on both our technical and business capabilities.
Impact
Deploying our IDRD solution in fundus cameras will significantly enhance the role of both the cameras and the ophthalmologists who use the cameras in the eye care paradigm, with further advances anticipated with the introduction of detectors for other pathologies, such as Glaucoma and Hypertension, all based on the same underlying hardware. With the integration of the NNDK the product offering has been significantly enhanced, with its supervisory role on the decisions being made by the CNNs delivering a significant benefit to the integrators of IDRD.
Video
https://www.youtube.com/watch?v=SlCkOZ8aK_Y
RobRad
Company info:
Name: ASINCO GmbH
Date founded: 2012
Number of employees: 25
Location: Duisburg, Germany
www.asinco.de
www.radarmesstechnik.de
Partners:
Robustification of radar sensors for application in harsh industrial environments
Challenge
Due to the adverse environmental conditions in metal production, essential measurement technologies, e.g. optical and laser-based, reach their physical limits in various fields of application. Thus, observation of relevant process parameters stays fragmented over the whole process-chain.
Radar-based measurement is insensitive to the adverse conditions (e.g. high temperature, dust, air humidity, mist from rolling emulsion or oil) and recording necessary measurement variables with sufficient precision. Due to advancement in innovative signal processing algorithms this is achieved without any discernible disadvantages compared to existing measurement technologies.
Solution
For improving the technological readiness level, well-structured and competently performed experiments and functionality tests are of core importance. Within the metal industry environmental conditions as high temperatures, dust, varying humidity and corrosive gases typically occur within the areas where sensors are located. This hinders many common sensors (optical, laser-based) from reaching their specified functionality.
The objectives within the application experiments in this project can be summarized as follows:
- Testing and improving sensor performance in terms of real-time capabilities for digital signal processing (sampling time: up to 1 kHz)
- Testing and improving sensor protection (housing) against harsh environment conditions with long-term continuous load tests against corrosive gases
- Testing and improving sensor protection (electronic) against harsh environment conditions with long-term continuous load tests with temperatures up to 100°C and variable humidity
FED4SAE Support
The increasing use of sensor intelligence and data preprocessing capabilities will be tackled as well with the use of the industrialized STM. By transferring main raw data processing onto a decentral embedded system included in the sensor, core requirements are provided for effectively implementing the sensing units as self-aware CPS in industrial environments. The simulation of real process environments by exploiting the functionalities of the advanced platforms of the corrosive gases testbed perfectly rounds of the improvement of the technological readiness level of the radar sensors. ASINCO is already closely interconnected within the pan-European community of radar sensors and additionally within the steel producing community. These cross-border collaborations can be further enhanced.
Impact
In close compliance with the targeted objectives of the call, this project tackles the development of further enhancing an already novel and smart solution of a technologically specialized SME. Thereby, it becomes possible to expand ASINCO’s leading position in the target market of providing robust measurement solutions for the metal producing industry.
The initiation and further pursuit of the robustification and market readiness development of radar-based sensors is the main interest for ASINCO. Numerous preliminary talks and discussions with various stakeholders from universities over research institutes to clients, clearly shows that the systems currently available on the market obviously do not meet industrial requirements. There is currently great interest in testing radar measurement technology for applications such as product tracking, geometry and speed measurement and control on hot wide strip mills. The radar-based system technology to be further developed and especially robustified for the industrial application also has the potential to be used in almost every process stage of metal processing, from continuous casting (slabs) and hot rolling (hot strip, heavy plate) to cold rolling and finishing, as well as in long product plants. In a comparison of today’s optically- or laser-based measuring systems, a previously unattained field of application, namely much closer to the process, can be opened up. With the entry of this new measuring technology, possibilities for process improvement with associated energy savings are attained at many points in the metal production process. There is also potential in the use of other materials such as plastics, glass, wood and paper.
INCOMING
Company info:
Name: Zannini S.p.A.
Date founded: 1963
Number of employees: 150
Location: Castelfidardo (AN), Italy
Zannini is specialized in the production of high precision machined components for automotive applications
Partners:
INCOMING: smart Interface for COnnected MachinING operation
Challenge
In Industry 4.0, the manufacturing world is embracing information and communication technology (ICT) more and more. Applications range from production management to smart material handling, from autonomous vehicles to sensor networks for machine monitoring. To gain the maximum benefit from adopting these systems, production machines must be directly interconnected with the factory ICT.
Making a network connection is only the start: making all machines, sensors and systems interact and play together like a well-tuned orchestra is the actual challenge. Efficient ways must be found to specify these interactions, since conventional programming would be too time consuming. Another significant aspect of this challenge is the need to bridge the technology gap and integrate legacy machines with no or only rudimentary digital networking capabilities.
Solution
INCOMING will develop a new integrated and interoperable solution to connect different types of machines through an open system that can be easily scaled and modified. This will be composed by an open source infrastructure for distributed industrial process measurement and control systems based on the 4DIAC platform, with a STM32 based solution as production machine add-on hardware.
To demonstrate the system functionality, this solution will be installed in three turning machines, with three different generations of machine control technologies. Machine operators and production managers will be able to monitor and control status and parameter data from these machines, enabling them to increase the overall equipment efficiency (OEE) by discovering problems and process inefficiencies faster.
FED4SAE Support
INCOMING will be carried out thanks to support by fortiss for the 4DIAC implementation and to support by ST Microelectronics for the chosen prototype STM32MP1 boards with X-NUCLEO expansion. Business innovation coaching is supported by Blumorpho.
Impact
INCOMING will generate impact in several ways. The first one is to establish a digital infrastructure that allows Zannini to gather operational status data from tool machines, which in turn can be used to improve production management processes, with the goal of increasing the Overall Equipment Efficiency (OEE) of these machines by an amount between 5% and 10%. The second reason is to permit Zannini to gain knowledge about the advantages of open software and hardware platforms for machine connectivity over commercial ones, so as to gain a competitive advantage in a fast changing market. Furthermore, the know-how that will be generated during INCOMING will also introduce the possibility for Zannini to create new services or even products for other companies.
Sentinal
Company info:
Name: Sentinum UG
Date founded: 2018
Number of employees: 3
Location: Nuremberg, Germany
Sentinum specializes in the implementation of large-scale wireless sensor networks for municipal use. Starting with the hardware, over the wireless communication up to data storage, evaluation and visualization.
Partners:
An energy-self-sufficient drainage monitoring system for critical event detection
Challenge
Rapid flooding of drainage systems is a well-known but hard to predict consequence of heavy rain that occurs in many climates around the world. The resulting high flow rate and pressure in the duct system can lead to considerable damage to the substance or even worse to detached manhole covers which pose a danger to pedestrians and traffic participants.
Solution
Only with a holistic sensor system an accurate picture of the events in the canal is generated and damage to infrastructure and people can be prevented. By recording the water level, flow rate and pressure, conclusions can be drawn in real time about events in the drainage system. We also record the position of the manhole cover and the presence of harmful gases such as H2S to protect people in the vicinity. The sensor is completely energy self-sufficient and wireless. The communication uses the latest LPWAN technologies. All data is stored by our cloud services and visualized for the customer.
FED4SAE Support
In the implementation of our product, we benefit especially from the partners provided to us via FED4SAE. Our energy self-sufficient sensors require low-power microcontrollers which nevertheless possess a certain performance. For this we use the STM32L4. With its extremely low power consumption in sleep modes it is predestined for our application. Via FED4SAE we have direct contact to ST-Microelectronics and can access this resource and expertise first hand. With the Fraunhofer IISB as test bed, we can simulate the harsh environmental conditions prevailing in a sewer system and analyze its effects in a unique way. Being able to fall back on such practical tests during product development accelerates time-to-market extremely and increases the quality of our final product.
Impact
Our system will affect two different areas. On the one hand, there are hardly any possibilities for planning offices and municipal civil engineering departments to evaluate how their sewer system works. With our system, data is continuously recorded over many years and processed to provide information about changes and anomalies. This opens up a completely new perspective on the planning phase, implementation and, above all, maintenance of the sewer systems.
The second point is increased safety for pedestrians and traffic participants. Injuries and even fatal accidents due to missing manhole covers occur more frequently than they should. Accidents or even drowning due to the tremendous suction of the backflowing water during heavy rain events. With our sensor system, depositioned manhole covers are instantly detected and warnings are transmitted to the relevant authorities. By voice call, sms or email. With this information, communities can act quickly and avoid resulting threats to people and the environment.
