Home/Projects

Projects

The directions, scientific interests, and technologies of the AI Center — from machine learning and computer vision to robotics and industrial digitalization. Work at various stages: from ideas and directions to applied research and prototypes.

6
directions
AI·ML
technologies & methods
UA·EN
materials in two languages
Open
open to collaboration

Directions & topics

Research · development · ideas
Prototype Industry

AEGIS-CAD

A computer-aided design system for pipework layouts in which generative AI proposes layout options and finite-element analysis, embedded inside the generation loop, decides which of them are admissible.

LangGraph / LangChainMultimodal LLMs (vLLM)Finite Element MethodCadQuery / OCCTPydantic
Learn more →
Development Cloud

SmartBalance

An edge-AI platform that combines solar generation, biogas, storage, and EV charging into a single controllable flexibility resource for distribution grids with a high share of renewables.

Edge AILSTM / XGBoostDeep RLNVIDIA Jetson OrinNGSI-LD / OCPP 2.0.1
Learn more →
Development NLP

AI Grant Researcher

A multi-agent AI system built on Claude for automated preparation of grant applications to European programmes — from parsing the call to a ready submission package.

Multi-agent AIAnthropic ClaudeTypeScript / Node.jsPrisma / PostgreSQLReact-PDF
Learn more →
In progress NLP

AI-Based Software Development

A lecture course on the modern AI-assisted software-development workflow with the Claude assistant — from problem statement to finished code.

Anthropic ClaudeClaude CodeAgentic workflowSpec-driven development
Learn more →
In progress ML

UNESRALE

Developing machine-learning methods within a UNESCO and CBPF (Brazil) programme that gives researchers remote access to AI infrastructure, mentorship, and participation in joint scientific tasks. The lab is preparing three individual research applications.

Anomaly detectionFoundation modelsPhysics-informed MLSynthetic dataHPC
Learn more →

Technologies & methods

All materials →
Overview

Computer Vision: approaches and applications

Image classification, detection, and segmentation — an overview of typical architectures and use cases.

Method

Transformers in Natural Language Processing

Attention, context, and language models — how they work and where they are applied in modern NLP.

Technology

Edge AI: on-device inference

Running neural networks outside the cloud — trade-offs between accuracy, speed, and compute resources.

Direction

Robotics and intelligent control

Sensors, navigation, and decision-making in autonomous and smart systems.

Tools

A stack for ML experiments

A typical set of technologies and practices for machine-learning research — from data to model.

Have an idea for a joint direction?

Propose research or an applied problem — we'll consider collaboration with students and the Center's laboratory.

Propose → About the Center