EDI in Riga, Latvia is a non-profit public research institute founded in 1960. Currently, EDI is specializing in the development of Smart Embedded Cooperative Systems in fields of health, mobility, space, production, social challenges, safety, and security. EDI has more than 80 researchers working on innovative technologies in electronics and computer science. At the moment, main fields of competence include signal and image processing (incl. AI), development of cyber-physical and embedded systems, intelligent transport systems (incl. connected and automated driving), hardware and software prototyping, system integration, wireless sensor networks (incl. IoT), intelligent devices, development of sensors, radars, biometrics, wearables, precise timing, robotics, etc.
EDI has a unique state-of-the-art infrastructure to support local and international SMEs. For example, EDI has a 100+ node heterogeneous sensor network and wireless network testbed distributed around a 7-floor building for validation and research in sensor network protocols & wireless network protocols. Additionally, 50 mobile nodes are available on site for on-site deployments (e.g. in customers’ factories). Besides, EDI has WSN hardware prototyping test bench EDImote developed with flexibility of prototyping, performance monitoring, and hardware and software debug assistance in mind (enabling fast prototyping for virtually any hardware). Also, high-performance workstations for computation, signal processing, visualization, and design (Matlab, Simulink, Labview, Quartus, Tanner Tools Pro, etc.) are available for use. PCB designing and simulation tools Altium Designer and fast prototyping systems (LPKF ProtoMat-S62, LPKF MiniContac-RS, Xytronic-IR620 Preheater, Unox thermal equipment) for multilayer PCB design. Laboratory equipment: Spectrum analyzers up to 20GHz (e.g. ROHDE&SCHWARZ-FSU8), Arbitrary waveform signal generators (e.g. Agilent-N6031A), Digital oscilloscopes up to 50GHz (e.g. 25GSPS Tektronix DPO70604). Mixed signal oscilloscopes (e.g. Tektronix MSO4104, Tektronix MSO4032). Portable spectrum analyzers and oscilloscopes, etc. Last but not least, EDI has High-Performance Computer (HPC) with dozens of Nvidia GPUs; Vibration and shock test platform, climate test chamber, Professional IR/Thermal camera, Professional 3D printer, automated-driving car platform, etc.
EDI has implemented several national projects with local industries (incl. SMEs) thus supporting companies (e.g. KEPP EU, HansaMatrix, Square Audio, Squalio, Lattelecom, etc.) to digitalize their industry.
On January 1st, 2019 EDI started the H2020 IA project called TRINITY which aims to create a network of multidisciplinary and synergistic local digital innovation hubs (DIHs) composed of research centers, companies, and university groups that cover a wide range of topics that can contribute to agile production: advanced robotics as the driving force and digital tools, data privacy and cybersecurity technologies to support the introduction of advanced robotic systems in the production processes.
While on July 1st, 2020 EDI started the H2020 IA project called DIH-world which aims to accelerate the uptake of advanced digital technologies by European manufacturing SMEs in all sectors and support them in building sustainable competitive advantages and reaching global markets strengthening the capacities of regional DIHs, particularly in underrepresented regions across Europe.
Link to national or regional initiatives for digitizing industry
EDI has implemented in past and is currently implementing several projects related to industry digitalization, for example,
- ERDF project: “Deep neural network method for improving the accuracy of tracking and classification of vehicle registration plates.”
- ERDF project: “Research on computer vision approaches for industry automatization.”
- “Transformation of the DICOM standard image data for the 3D spatial image display”
- H2020 IA project “DIH-World – Accelerating deployment and matureness of DIHs for the benefit of Digitisation of European SMEs” (DIH-World)
- H2020 ECSEL project: “Artificial Intelligence for Digitizing Industry” (AI4DI).
- H2020 ECSEL project: “Framework of key enabling technologies for safe and autonomous drones’ applications” (COMP4DRONES).
- H2020 ECSEL project: “Advanced packaging for the photonics, optics, and electronics for low-cost manufacturing in Europe” (APPLAUSE).
- H2020 ECSEL project: “Arrowhead Tools for Engineering of Digitalisation Solutions” (ARROWHEAD TOOLS).
- H2020 ECSEL project: “VIZTA sounds for Vision and Identification Z-sensing Technology and Applications” (VIZTA).
- H2020 IA project: “Digital Technologies, Advanced Robotics and increased Cyber-security for Agile Production in Future European Manufacturing Ecosystems” (TRINITY).
- H2020 ECSEL project: “Programmable Systems for Intelligence in Automobiles (PRYSTINE)”.
- H2020 ECSEL project: “Intelligent Motion Control Platform for Smart Mechatronic Systems” (I-MECH).
- H2020 IA project: “Trustworthy and Smart Actuation in IoT systems” (ENACT).
- H2020 ECSEL project: “Advancing fail-aware, fail-safe, and fail-operational electronic components, systems, and architectures for highly and fully automated driving to make future mobility safer, more efficient, affordable, and end-user acceptable” (Autodrive).
- FLAG-ERA project: “Frictionless Energy Efficient Convergent Wearables For Healthcare and Lifestyle Applications” (CONVERGENCE).
- Besides, EDI research activities are in line with the smart specialization strategy (RIS3) as our research activities ar related to information and communication technologies; biomedicine, medical technologies, and smart materials, technologies and engineering systems; smart energetics
Market and Services
- Agriculture, hunting and forestry
- Transport, storage and communication
- Health and social work
- Other markets
- TRL2 – Technology concept and/or application formulated
- TRL3 – Analytical and experimental critical function and/or characteristic proof of concept
- TRL4 – Component and/or breadboard validation in laboratory environment
- TRL5 – Component and/or breadboard validation in relevant environment
- TRL6 – System/subsystem model or prototype demonstration in a relevant environment
- TRL7 – System prototype demonstration in an operational environment
- Awareness creation
- Ecosystem building, scouting, brokerage, networking
- Visioning and Strategy Development for Businesses
- Collaborative Research
- Concept validation and prototyping
- Testing and validation
- Education and skills development
AI/ML/NN tools for rapid development of vision based robotic systems
Goal: Automation of industrial processes involving large number of objects with unpredictable positions/locations.
Description: A lot of industrial processes involve operation with large number of different objects. It is hard to automate these kinds of processes because sometimes it is impossible to predetermine the positions for these objects (For example when objects are distributed chaotically in some container). To overcome this issue, we integrate 3D and 2D computer vision solutions with robotic systems for object detection, localisation and classification. In experiments we are using Microsoft Kinect V2 depth sensor for 2D and 3D information acquisition. For object detection and classification, we are developing algorithms based on artificial neural networks. One of the challenges for artificial neural network-based methods is the need for large amount of labelled data. We are exploring methods how to generate this kind of data procedurally, to allow generation of such data for various objects a lot faster with reduced amount of manual work allowing faster adaption of this method for different scenarios.Contribution to increased agility in production: Provided algorithms and methods, which are based on artificial neural networks, will allow to generate labelled data for various objects a lot faster with reduced amount of manual work allowing faster adaption of system which is capable of randomly dropped object detection, recognition, classification and pick-up by a robotic arm for different scenarios. More details: https://projects.tuni.fi/trinity/
Large scale (100 node) EDI WSN TestBed
EDI Wireless Sensor Network TestBed is a 100+ node heterogeneous sensor network and wireless sensor network testbed (distributed around 7 floor building (inside & outside)) for validation and research in sensor network & wireless network protocols. Additionally, 50 mobile nodes are available on site.They can be used for example in-vehicle placement. Capabilities: testing of IEEE 802.11a/b/g/n/p, IEEE 802.15.4 and other protocols (depends on WSN node); Fully reconfigurable routers; Remote reprogramming of the whole network; Energy measuring and remote debugging capabilities for the sensor nodes through a custom adapter; Control and management through either OMF or, alternatively, a simple webbased interface.
Super-stable impulse generator producing extremely low jitter
Impulse generator with extremely high stability and wide frequency range. It is implemented in two modifications: supporting NIM signal output and supporting LVTTL signal output (therefore it is possible to use them together with Event timers). Generator period stability in range up to 25000 ns is smaller than 1 ps (RMS). For wider ranges the reference signal is needed. Generator applications include measurement system testing (e.g. Event timers), calibration etc.
Universal Event timer producing extremely high measurement resolution
Together with Eventech Ltd the Event timer is developed capable to measure single pulse within 3 ps resolution (RMS) and maximum measuring rate up to 20 MHz. The various modifications of the timer are available (with increased measuring rate but lowered resolution). Event timers are used in SLR (Sattelite Laser Ranging) systems and have potential in LIDAR, 3-D scan, Laser Link communication systems.
SIKA – Research on development of mathematical model for silicon crystal growing technological process by using image processing methods
Client: KEPP EU (Silicon Metallurgy)
Client needs: To explore importance of the silicon crystal growing process mathematical model modifiable parameters and stability of the crystal diameter, using an image processing technique by measuring the diameter of the silicon crystal and the electron beam gun power.
Provided solution: Designed silicon crystal growing process mathematical model, based on the established image processing algorithm performing silicon crystal ingot diameter measurement. More details: https://www.youtube.com/watch?v=-HOTtb6l3J8
Operating system MansOS and configuration tool Seals for embedded systems
EDI has expertise in development of operating systems and software for embedded systems. MansOS & Seals have been developed specially for low-power and computationally weak devices. The operating system can be modified depending on specific requirements and needs (including adaptation for Wireless Sensor Networks). Potential applications are data acquisition and gathering from environment, industrial process monitoring etc. More details: http://mansos.edi.lv
UWB receiver producing high sensitivity
UWB (Ultra Wide Band) receiver producing sensitivity 15mkV (RMS). In comparison the Geozondas UWB receivers provide sensitivity about 75mkV (RMS) under the same conditions. It can be used for weak signal measurements in many industrial and science applications. As well it can be used for UWB radar applications (object localization, search of underground communications etc).