Real-time driver state detection A vision system for controlling an industrial robot with hand movements Integration of a camera and virtual reality with a robotic arm Application of computer vision in the recognition and interpretation of sign letters Mapping of characteristic points of the human face using machine learning and Blender software Six-legged robotic insect Two-way communication based on the MQTT protocol within the virtual and real environment

Scientific projects

The LAPIS Laboratory is actively involved in national and international research projects that advance the fields of artificial intelligence, robotics, cyber-physical systems, smart education and intelligent environments. The projects conducted within LAPIS combine fundamental research with applied innovation, contributing to both scientific progress and real-world impact.

Research Impact

Through these projects, LAPIS addresses key challenges in:

AI-driven intelligent systems and cognitive robotics
IoT, smart environments, and distributed sensing
immersive technologies and digital education
human-centered and adaptive interaction systems.

By combining scientific rigor with technological innovation, LAPIS contributes to the development of next-generation intelligent, connected, and human-aware systems aligned with Industry 4.0 and beyond.

ExQuMe – Explaining Quantum Mechanics (Erasmus+)

Duration: 2025–2028 Programme: Erasmus+ (KA220-HED)

Coordinator: University of Turku (Finland), https://exqume.eu

ExQuMe explores innovative approaches to teaching quantum mechanics through immersive Virtual Reality (VR) storytelling. By integrating historical scientific narratives with interactive VR environments, the project addresses the abstract and challenging nature of quantum physics in higher education.

The project focuses on enhancing student engagement and conceptual understanding, with particular attention to inclusivity and increasing female participation in STEM. Key outcomes include the development of VR-based learning modules, educational frameworks, and evaluation methodologies, supporting the long-term integration of immersive technologies into higher education curricula.

------------------

SAFER – Smart AI- and IoT-based Fire Extinguisher

Duration: 2026–2029 Programme: Competitiveness and Cohesion Programme (IRI S3)

Coordinator: Pastor TVA d.d. (Croatia), https://pastor.hr

SAFER is an applied research and innovation project focused on the development of a next-generation smart fire extinguisher integrating Artificial Intelligence and Internet of Things (IoT) technologies.

The system enables continuous monitoring of device status and environmental conditions, including pressure, temperature, smoke, hazardous gases, and air quality. Through connectivity with mobile applications and smart home systems, SAFER introduces a distributed early warning and fire prevention model.

The project delivers a functional prototype, digital platform, and validated solution for real-world deployment, contributing to improved safety and new IoT-driven services in residential environments.

------------------

SPARTA – Smart Predictive Analytics for Reliable Turbine Assets

Duration: 2026–2029

Programme: Competitiveness and Cohesion Programme (IRI S3)

Coordinator: SolidForm (Croatia), https://solidform.hr

SPARTA is an applied research and innovation project focused on the development of advanced predictive analytics solutions for monitoring, diagnostics, and maintenance of industrial turbine systems.

The system integrates Artificial Intelligence, machine learning, and Industrial Internet of Things (IIoT) technologies to enable continuous acquisition and analysis of operational data, including vibration, temperature, pressure, acoustic signals, and performance indicators. By leveraging edge computing and cloud-based analytics, SPARTA provides real-time anomaly detection, Remaining Useful Life (RUL) estimation, and efficiency degradation tracking.

Through integration with digital twin models and industrial control systems, SPARTA introduces a proactive maintenance paradigm, reducing downtime, optimizing operational efficiency, and extending asset lifespan. The project delivers validated predictive maintenance algorithms, a scalable digital platform, and demonstrators in real industrial environments, contributing to the digital transformation of energy and manufacturing sectors.

------------------

AERONAUT – Advancing research capacities for the development of autonomous marine-aerial systems for novel Adriatic applications

Duration: 2025–2029

Programme: Institutional Projects / NPOO

Coordinator: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture (UNIZAG FSB)

AERONAUT is a research and capacity-building project focused on the development of autonomous cooperative maritime-aerial systems through the integration of Unmanned Surface Vehicles (USVs) and UAV-VTOL platforms. The project addresses key technological challenges, including reliable UAV take-off and landing on moving vessels and energy-aware operation through the integration of renewable energy sources for long-endurance autonomy.

Within the project, the LAPIS team contributes to the development of an advanced autonomy stack for cooperative USV–UAV systems. The focus is on Artificial Intelligence, simulation, and digital twin technologies enabling real-time perception, decision-making, and system optimization in dynamic maritime environments. The developed solutions support coordinated multi-agent operation, adaptive mission planning, and simulation-driven validation of autonomous behaviours.

------------------

Nonverbal Communication-Based Adaptive Learning Model for Interactive AI Agents

Duration: 2025–2030

Programme: Croatian Science Foundation (HRZZ), DOK-2023-10, Career Development of Early-Stage Researchers – Training of New PhD Holders

Coordinator: UNIZAG FSB, LAPIS, DOK-NPOO-2023-10-1790

This project develops an agentic AI model and cognitive architecture enabling computational agents to learn and adapt in real time through multimodal, nonverbal human interaction.

The approach combines online learning, reinforcement learning (RL), and agent-based modelling (ABM) to support continuous updating of internal representations, context-aware reasoning, and adaptive decision-making within a dynamic information space. By maintaining a shared and evolving common ground, the system enables mutual understanding and robust interaction in changing environments.

Building on the AMICORC project, the work advances the PLEA platform with real-time adaptive capabilities, positioning it as a next-generation interactive, learning AI agent.

------------------

Virtual - transfer – Technology Transfer of an Affective Virtual Being for Immersive Interaction

Duration: 2025–2026

Programme: NPOO, Technology Transfer Support

Coordinator: CTT - Technology Transfer Centre, www.ctt.hr

This project focuses on the technology transfer and market deployment of PLEA, an affective virtual being designed for immersive, multimodal human–AI interaction.

The objective is to analyse and validate viable pathways for commercialization, including application domains, business models, and integration into real-world environments such as education, healthcare, customer interaction, and digital services. Particular emphasis is placed on translating the underlying AI mechanisms—nonverbal communication, emotion recognition, and adaptive behaviour—into scalable and market-ready solutions.

The project addresses key challenges related to productization, user acceptance, system integration, and intellectual property management, with the goal of positioning PLEA as a next-generation interactive AI system for commercial use.

------------------

AMICORC – Affective Multimodal Interaction based on Constructed Robot Cognition

Duration: 2021–2026 Programme: Croatian Science Foundation (HRZZ)

Coordinator: UNIZAG FSB, LAPIS, UIP-2020-02-7184

AMICORC is a fundamental research project that develops a novel framework for cognitive and affective robotics, based on the Theory of Constructed Robot Cognition (TCRC).

The project investigates how robots can interpret and respond to multimodal social signals, including facial expressions, speech, movement, and environmental context. Moving beyond traditional sensor processing, the system enables context-aware reasoning, anticipation, and adaptive interaction.

The developed methodologies are validated on real and virtual robotic platforms, demonstrating applications in human–robot interaction, education, and embodied AI systems. AMICORC positions LAPIS at the forefront of research in cognitive systems, affective computing, and socially aware robotics.

------------------

ACRON – A New Concept of Applied Cognitive Robotics in Clinical Neuroscience

Duration: 2014–2018

Programme: Croatian Science Foundation (HRZZ), Research Project, IP-2013-11-4192

ACRON develops a new generation of cognitive robotic systems for clinical neuroscience, building on prior results from the RONNA robotic neurosurgical navigation platform.

The project introduces an advanced cognitive architecture enabling context-aware, anticipatory robot behaviour in dynamic surgical environments. Moving beyond traditional sensor-driven approaches, the system leverages AI to model interaction context, anticipate actions, and support adaptive decision-making in real time.

By integrating human, robot, and environment into a shared information space, ACRON enables safe and efficient collaboration, including collision avoidance, task-aware behaviour, and precise execution during medical procedures. This work establishes a foundation for next-generation agentic medical robots operating in complex, real-world clinical settings.