ICS Laboratory excels in high-performance and real-time signal processing, digital circuit design, development of new sensors, heterogeneous single-chip systems, computer vision embedded systems, development of machine learning algorithms, on-chip architectures, development of operating systems, etc.
Our vision is to create a world where the core value is unlocking the potential of each individual. To provide every individual the opportunity to comprehend the latest technologies, fostering the development of a safer and more sustainable society.
We believe that by advancing research and investing in integrated circuits and systems, we will be able to create new approaches to computation, thereby ensuring sustainable societal development and simultaneously strengthening the institute’s and Latvia’s competitiveness in the global market.
Long-term goals of the laboratory:
-
invest in human capital, attracting new talents and developing research excellence, to promote world-class competence in the field of semiconductor devices and to transform Latvia’s high-tech sector;
-
create innovations that exceed existing standards in microchip technologies, thereby contributing to the growth of the European innovation and research ecosystem and indicating new directions in scientific progress..
Research directions:
-
Development of the next generation sensors
ICS Laboratory has experience in developing and adapting digital logic for signal processing needs, with a particular focus on imaging, quantum and other high-data-rate sensors. In this regard, the laboratory provides high efficiency and performance using programmable logic array devices (FPGAs). The requirements of next-generation technologies require a special approach to data processing, which can be achieved by developing specialized silicon hardware (chip) solutions. The laboratory addresses this challenge by using FPGA System-on-Chip (SoC) circuits, that enable parallel processing and high adaptability. This approach facilitates the implementation of optimized algorithms that meet the requirements of specific sensors, achieving highdata transmission speed and efficiency. With high-performance digital logic, the laboratory promotes innovation in image and data processing technologies, while enabling new applications and industrial sectors to benefit from next-generation sensor solutions.
-
Artificial Intelligence in Heterogeneous Single-Chip Systems
ICS active involvement in machine vision research, combined with expertise in the design of microchip digital circuits, provides the necessary foundation for the development of artificial intelligence accelerators. The interpretation of large volumes of structured and unstructured data has become integral to information technology.However, the machine learning algorithms required for interpretation cause significant challenges for traditional von Neumann architecture devices. Heterogeneous single-chip systems enable the implementation of specialized hardware using AI-adapted computing on silicon hardware. Following the latest trends in machine vision, the laboratory develops digital computing circuits in single-chip systems, aimed at achieving very low-power real-time machine learning computations. This low-power, high-volume data interpretation has significant applications in independent power-supply devices such as drones and electric cars.
-
Computing accelerators and their integration
The ability to implement algorithms in digital logic gives a unique opportunity to improve any modern technology. However, the development of silicon hardware solutions is relatively more expensive than conventional software development, as it requires more extensive training of specialists, longer technology development and testing cycles, as well as the need to integrate the technology with the rest of the system. The laboratory has experience in managing a wide range of technological abstractions, including electronics design, digital circuit design, operating system engineering, driver development, software development, algorithm creation and even complete system design. This range of expertise gives the ability to successfully transfer accelerator technologies to industry, therefore ICS laboratory maintains a solution for integrating accelerators into technologies based on conventional hardware (more information: https://www.edi.lv/solutions/silhouse-paatriniet-savu-masinredzes-risinajumu/).
Key words
– development of new sensors
– signal processing
– smart sensors
– embedded intelligent systems
– development of digital circuits
– high-speed interfaces
– acceleration of parallel data processing
– real-time data processing
– HSoC, SoC, FPGA
Laboratory Team
(from left side) E.Lielāmurs, S.Umnovs, M.Meļņiks, A.Bizuns, R.Novickis (in the middle), M.Celitāns, I.Rubika, A.Cvetkovs and Ibrahim Sayed
Recent projects
- Silicon IP Design House (SilHouse) part 2
- Go IT! #Horizon Europe
- Intelligent, Safe and Secure Connected Electrical Mobility Solutions: Towards European Green Deal and Seamless Mobility (EcoMobility) #ChipsJU
- Artificial Intelligence using Quantum measured Information for realtime distributed systems at the edge (A-IQ Ready) #ChipsJU
- Trusted lifetime in operation for a circular economy (ARCHIMEDES) #ChipsJU
Publications
- Novickis, R., Levinskis, A., Kadiķis, R., Feščenko. V., Ozols, K. (2020). Functional architecture for autonomous driving and its implementation. 17th Biennial Baltic Electronics Conference (BEC2020), Tallinn, Estonia.
- Justs, D., Novickis, R., Ozols, K., Greitāns M. (2020). Bird's-eye view image acquisition from simulated scenes using geometric inverse perspective mapping. 17th Biennial Baltic Electronics Conference (BEC2020), Tallinn, Estonia.
- R.Novickis, D.J. Justs, K.Ozols and M.Greitāns "An Approach of Feed-Forward Neural Network Throughput-Optimized Implementation in FPGA", Electronics journal: Special Issue Advanced AI Hardware Designs Based on FPGAs, 2020
- Edgars Lielāmurs, Andrejs Cvetkovs, Rihards Novickis, Kaspars Ozols, 2023. Infrared Image Pre-Processing and IR/RGB Registration with FPGA Implementation. Electronics, 12(4), 4, MDPI.