Production of the Future: AI Research Centre Presents Its Developments in Manual Operations Control Systems
Researchers from the HSE AI Research Centre have built a system for the automated control of manual operations, which finds application in industrial production. The system facilitates the process of monitoring objects and actions, as well as controlling the quality of their execution.
Artificial intelligence technologies help automate human actions, simplifying their work, or completely replacing personnel. The automation of manual operations control in production goes even further: from selective quality control of products by the Quality Control Department to continuous monitoring of the entire assembly process.
Based on AI technologies, HSE scientists have developed a demonstration stand—one of the key components for testing developments before their implementation in production. Using computer vision, the automated system analyses the sequence of actions of the assembler, whether it is a robot or a human. This allows it to be determined if an important step was missed, or if an assembly action was incorrect. The system also evaluates compliance with safety techniques: the usage of personal protective equipment and absence of third persons or unrelated objects in the assembly area. With all actions logged in the system, individual performance indicators for each employee can be obtained. For the assembler, the system is useful because it alerts them if they forgot to perform a step or did it incorrectly. Ultimately, it significantly reduces the output percentage of defective products.
Viktor Minchenkov, project leader, Deputy Head of the Unit for Software Systems Development at HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)
‘At the moment, we can track the sequences of semi knocked down and screw driving assembly. We can track the quantity and quality of an item placement on the workbench. We can track safety violations related to the use of personal protective equipment. In the final implementation, we can adapt the stand for controlling any technological process if it can be implemented through means of visual control.’
The project ‘Intelligent Automation of Manual Operations in Production’ of the AI Research Centre is being carried out by specialists from HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE) within the framework of the federal project ‘Artificial Intelligence.’
The main advantage of this developed system is that AI allows many actions to be performed equally well and even better than humans. One particular difference is that computer vision does not suffer from ‘fatigue’ as does human vision.
Sergey Slastnikov, Associate Professor at HSE School of Applied Mathematics of HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)
‘Analogues of the developed system undoubtedly exist—there are quite a few local solutions for highly specialised tasks. In turn, we are developing our own approach, which potentially can be applied to a wider range of problems. As part of its testing, we are in collaboration with various domestic companies, both industrial and technological, for example, in the field of video analytics and IT services development. Several pilot projects have already been launched.’
The range of applications for this development is very wide. For example, the technology can be used as simulators for training with automatic assessment of the level of training or in video surveillance and video analytics systems, where malicious actions of humans can also be controlled.
Anton Sergeev, Director of the Centre for Software Development and Digital Services at HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)
‘Our professional engineering and mathematical school and a project-based training model at MIEM allowed us to quickly put together a young but qualified team and implement computer vision technology for production. The created system is like an experienced digital mentor: it watches, advises, teaches, points out mistakes, and impartially and fairly evaluates efficiency. Data on process efficiency is automatically sent to the enterprise's ERP system.’
An important parameter of these systems is the speed of data collection (video or photos) for training embedded AI algorithms. This stage is also automated in the system and reduces the time and cost of implementation. The details of the approach were presented by the project team in the paper ‘Method of Automatic Images Datasets Sampling for the Manual Operations Control Systems’ in 2023.
See also:
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.
HSE Scientists Train Neural Network to 'Hear' Faults in Electric Motors
Researchers at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a new method—the Signature-Guided Data Augmentation (SGDA) framework—that achieves 99% accuracy in motor fault detection and 86% accuracy in fault classification. The application of this approach can reduce industrial equipment repair costs, minimise downtime, and improve production safety. The study results have been published in Engineering Applications of Artificial Intelligence.
HSE Graduate’s AI Project Wins at TECH & AI Awards
Daria Davydova, graduate of the HSE Graduate School of Business and Head of the AI Implementation Unit at the Artificial Intelligence Department of Alfa-Bank, received a prize at the TECH & AI Awards. She was awarded for the best AI solution for optimising business processes. The winners were determined as part of the VII Russian Summit and Awards on Digital Transformation (CDO/CDTO Summit & Awards).
New Neural Network for Science and Innovation Being Developed at HSE University
HSE researchers are training large language models (LLMs) to understand Russian-language scientific terminology while improving their energy efficiency. The adapted model runs 2.7 times faster and requires 73% less memory than the original open model, allowing it to operate on more affordable hardware. The programme has passed state registration.
HSE FCS Researchers Showcase AI and Bioinformatics Breakthroughs at ICLR 2026
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science, along with students from the AI360: Artificial Intelligence Engineering track of the Applied Mathematics and Information Science bachelor’s programme, took part in ICLR, one of the world’s most prestigious international conferences on machine learning and representation learning. This year’s event was held in Rio de Janeiro, Brazil.
The Future of Cardiogenetics Lies in Artificial Intelligence
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a program capable of analysing regions of the human genome that were previously inaccessible for accurate interpretation in genetic testing. The program adapts large generative AI (GenAI) models for cardiogenetics to predict how specific mutations affect the function of individual genes.
HSE and Yandex Propose Method to Speed Up Neural Networks for Image Generation
A team of scientists at HSE FCS and Yandex Research has proposed a method that reduces computational costs and accelerates text-to-image generation in diffusion models without compromising quality. These models currently set the standard for text-to-image generation, but their use is limited by high computational loads, the company said in a statement.
A Trap for the Advanced Student: How to Break the Habit of Blindly Trusting Neural Networks
Andrei Ternikov, Associate Professor at the St Petersburg School of Economics and Management at HSE University–St Petersburg, has developed a method for conducting online exams that significantly limits students’ ability to use ChatGPT and other AI models to obtain correct answers. Andrei Ternikov spoke to the HSE News Service about his approach—which won the HSE University Autumn Educational Innovation Competition, received an Alfa Future grant, and was presented at an international conference in Japan.
HSE Researchers Train Neural Network to Predict Protein–Protein Interactions More Accurately
Scientists at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a model capable of predicting protein–protein interactions with 95% accuracy. GSMFormer-PPI integrates three types of protein data (including information about protein surface properties) to analyse relationships between proteins, rather than simply combining datasets as in previous models. The solution could accelerate the discovery of disease molecular mechanisms, biomarkers, and potential therapeutic targets. The paper has been published in Scientific Reports.
Human Intuition Proves Stronger than Algorithms: Game Theory Tournament Held at HSE University in Perm
Researchers from the International Laboratory of Intangible-driven Economy (Perm) and the HSE Laboratory of Sports Studies, together with mathematician and science populariser Alexey Savvateev, organised a game theory tournament entitled ‘The Election Race.’ Participants competed both against one another and against artificial intelligence. For now, humans have managed to gain the upper hand and propose more effective strategies.