跳到正文
Tech.eu· Tamara Djurickovic·· 4 天前AI 評分38

Visage Technologies 啟動獲歐盟資助的 310 萬歐元自適應訓練技術研發項目

Visage Technologies launches €3.1M EU-backed project to develop adaptive training technology

AI 導讀

Visage Technologies 啟動一項總額 310 萬歐元的研發項目,開發用於自適應學習及模擬訓練的情感認知平台。歐盟共同資助 190 萬歐元,項目由 2026 年 4 月至 2029 年 4 月進行,初期聚焦船舶導航模擬訓練。平台將分析攝影機、咪高峯、穿戴式裝置及其他感測器數據,估算學習者的認知與情緒狀態,並提供 ACInsight SDK、ACTutor 和 ACTrainer。

正文

Computer vision and AI company Visage Technologies has launched a €3.1 million research and development project to create an affective-cognitive platform for adaptive learning and simulation-based training. The European Union is co-financing €1.9 million of the project, which runs from April 2026 to April 2029.

The project is led by the company's Visage AI Labs team at Visage Technologies d.o.o., in collaboration with the University of Zagreb's Faculty of Humanities and Social Sciences and the University of Rijeka's Faculty of Maritime Studies. Its initial focus is ship-navigation simulator training, where human error under high mental workload remains a major factor in maritime incidents.

Founded in 2002 and headquartered in Sweden, with R&D operations in Croatia, Visage Technologies develops face-tracking and analysis technology used across automotive, defence, industrial and healthcare applications.

Most e-learning platforms and professional training simulators adapt to users based on their answers or performance scores, without considering cognitive effort or engagement. This limits their ability to respond to individual learning needs and makes it difficult for instructors to assess whether simulated scenarios reflect the pressures trainees would encounter in real-world situations.

Visage Technologies aims to address these limitations by developing machine learning models that analyse data from cameras, microphones, wearable devices and other sensors to assess learners' cognitive and emotional states.

The research will initially focus on cognitive load, engagement, valence and arousal, with the final set of indicators determined by the reliability of the models following data collection.

The main idea behind the project is to help people learn by tracking two signals: stress level and cognitive load. If someone is overloaded with stress, they will have a hard time learning anything. It can also work the other way. If a person is bored, we can make them more engaged in the task. We can integrate any camera and any hardware, and everything we do runs on the edge,

said Hrvoje Šamija, Chief Business Development Officer at Visage Technologies.

The project will deliver a core sensing platform and two applications built on it. ACInsight SDK will combine data from multiple sensors to estimate a person's cognitive-affective state, while ACTutor will integrate with existing e-learning platforms to adapt learning materials to individual needs. ACTrainer will support professional training simulators by assessing how closely simulated scenarios reproduce the cognitive and emotional demands of real-world situations.

According to Bruno Rosan, Senior R&D Engineer at Visage Technologies, the company is developing the entire system internally, from data processing and machine learning models to deployment across devices.

The platform is being developed with privacy, data protection and cybersecurity requirements incorporated into its design, taking into account the GDPR, the EU AI Act and the NIS2 directive, including regulatory limitations on technologies used to monitor cognitive and emotional states.

來源:Tech.eu · tech.eu