Home

Implicit mobile human-robot communication for spatial action coordination with action-specific semantic environment modelling

With the increasing use of robots in industrial and everyday contexts, the need for systems that can interact flexibly and cooperatively with humans is growing. Collaborative robots (cobots) in particular, which share a common workspace with humans and can react to complex, dynamic environments, are coming into focus. A central challenge here is the context-related perception of the environment and the appropriate interpretation of human behavior.

Founding

The project SEMIAC - Implicit mobile human-robot communication for spatial action coordination with action-specific semantic environment modelling (Implizite mobile Mensch-Roboter-Kommunikation für die räumliche Handlungskoordination mit aktionsspezifischer semantischer Umgebungsmodellierung) is funded by the German Research Foundation (DFG) under grant No. 502483052 and is planned with a project duration of 3 years (2023 to 2026).

Publications

Automated 3D Dataset Generation for Arbitrary Objects

October 06, 2025

6D pose estimation is a cornerstone of various autonomous systems, including mobile robots and self-driving cars, because it enables fundamental...

IEEE Access PoseEstimation 3DDatasets

Scene-Aware Prediction of Diverse Human Movement Goals

October 01, 2025

Anticipation of human behaviours facilitates autonomous systems in proactive planning. Human behaviour could be stochastic due to varying goals. Human...

MotionPrediction CVAE HumanGoals

Learning Human–Robot Proxemics Models from Experimental Data

September 18, 2025

Humans in a society generally tend to implicitly adhere to the shared social norms established within that culture. Robots operating...

HRI Proxemics SocialNavigation

Robot System Assistant (RoSA) evaluation of touch and speech input modalities for on-site HRI and telerobotics

June 30, 2025

As humans and robots collaborate more in industrial settings, flexible interaction modalities become essential. This study evaluates a hybrid interaction...

HRI Telerobotics Multimodal

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...

Journal HAR Deep Learning

IM HERE – Interaction Model for Human Effort based Robot Engagement

April 29, 2025

We present our novel engagement modeling framework IMHERE, designed to improve human-robot interaction by capturing relational dynamics using a formal...

IEEE Conference

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...

ROBOVIS 2025 Conference

Toward Truly Intelligent Autonomous Systems A Taxonomy of LLM Integration for Everyday Automation

April 28, 2025

With the rapid development of large language models (LLMs), their integration into autonomous systems has become essential. This integration significantly...

ROBOVIS 2025 Conference