2024–2027
Project Duration
ERDF
EU Funding
4
Research Focus Areas
ERDF research project
ENABLING
Resilient Human-Robot Collaboration in Mixed-Skill Environments
ENABLING
ENABLING (Resilient Human-Robot Collaboration in Mixed-Skill Environments) addresses the problem area of developing AI methods to complement the skills of robots and humans. It thus enables research innovations in cross-sectional areas of IT and key enabling technologies and forms the basis for future applications in the lead markets. The challenges lie, firstly, at the interface between robotics and AI and, secondly, in the complexity of tasks in a mixed-skill environment and, thirdly, in resilient and responsible collaboration. These are to be achieved by developing the key technologies for 1. robust recording of the affective user state, 2. semantic environment analysis, 3. intention-based interpretation of user actions, 4. and research into generative models for recording complex behavior in mixed-skill environments.
The project is funded by the European Regional Development Fund (ERDF) under grant No. ZS/2023/12/182056 and is planned with a project duration of 4 years (2024 to 2027).
Breakthrough Innovations
01
AI-Based User Perception
Development of AI methods for user perception in real mixed-skill scenarios with high occlusion, changing environments, and complex tasks under distributed attention between the human and the robot's own actions.
02
Social Signal Interpretation
Methods for interpreting social signals and affective states that distinguish between task-directed user actions, interactions with other users, incidental movements, and interactions with the technical system.
03
Semantic Environment Analysis
Development of a semantic environment analysis for recognising user actions in spatial context — a fundamental prerequisite for intentional, anticipatory systems that must understand both environment and action context.
04
Affective State Detection
AI algorithms for determining the user's affective state via gestures, facial expressions, and vital parameters, enabling real-time non-verbal feedback on robot positioning and cooperative action alignment.
05
Generative Behaviour Models
Development of generative models for capturing complex user behaviour in mixed-skill environments, unifying prediction methods across modalities to generate comprehensive situation models using AI.
Latest News
Automating Synthetic Dataset Generation for Image-based 3D Detection: A Literature Review
October 19, 2025
A comprehensive review of synthetic dataset generation approaches for 3D object detection, covering both traditional 3D modeling and neural image...
Automated 3D Dataset Generation for Arbitrary Objects
October 10, 2025
An end-to-end pipeline that automates all aspects of 3D dataset generation by leveraging Radiance Fields for high-quality 3D modeling and...
MobGazeNet: Robust Gaze Estimation Mobile Network Based on Progressive Attention Mechanisms
May 09, 2025
An efficient and lightweight network for gaze estimation that leverages progressive attention mechanisms to emphasize crucial eye features while maintaining...
Multi-Head Attention-Based Framework with Residual Network for Human Action Recognition
May 06, 2025
We propose a novel HAR framework integrating residual networks, Bi-LSTM, and multi-head attention with a motion-based frame selection strategy. It...
IM HERE – Interaction Model for Human Effort-Based Robot Engagement
April 29, 2025
We present IM HERE, a formal effort-based framework for modeling engagement across human–robot, human–human, and robot–robot interaction. It captures relational...
Automating 3D Dataset Generation with Neural Radiance Fields
April 29, 2025
We present a fully automated pipeline that leverages Radiance Field–based universal 3D representations to rapidly generate high-quality models of arbitrary...