Christian Kowalski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Christian Kowalski has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Hein
Assistance Systems and Medical Device Technology, University of Oldenburg, Oldenburg, Germany
4 shared publications - Anna Brinkmann
Assistance Systems and Medical Device Technology, Carl Von Ossietzky University of Oldenburg, Oldenburg, Germany
1 shared publication - Celia Nieto Agraz
R&D Department Production, OFFIS-Institute for Information Technology, Oldenburg, Germany
1 shared publication - Cletus Brauer
Forschung und Entwicklung, Johanniter-Unfall-Hilfe e. V., Elsfleth, Germany
1 shared publication - Conrad Fifelski-Von Böhlen
Assistance Systems and Medical Device Technology, Carl Von Ossietzky University of Oldenburg, Oldenburg, Germany
1 shared publication Daniel Dorniok
Organisation und Personal, Carl von Ossietzky University of Oldenburg, Oldenburg, Germany
1 shared publication
Latest Publications
- Open Access
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7158-7165
ClaRO: A Cluster-Based Method for Radar Odometry
We present ClaRO, an unsupervised, cluster-based odometry pipeline for 4D imaging radar to improve robustness and reduce long-term drift for radar-only odometry.Our core idea is to utilize density-based clustering to improve ego-motion estimation using per-cluster Doppler-residuals and find a local best result to seed a robust least squares in addition to finding static points for pose estimation. The resulting global inlier mask is used to refine the pose via a weighted iterative closest point (ICP) approach that fuses Doppler and radar cross-section (RCS) cues while down-weighting the radar’s weak elevation axis. The method is fully unsupervised and sensor-agnostic. We compare our method on multiple public datasets (View-of-Delft, HeRCULES, and NTU4DRadLM) and show that our approach provides results that match or exceed recent radar-only odometry baselines (Radar4Motion, EFEAR-4D) and pose graph based 4DRadarSLAM. Our cluster-wise approach significantly reduces long-term drift, achieving a 72.0% improvement in mean absolute trajectory error (ATE) and a 73.2% improvement in absolute rotation error (ARE) compared to state-of-the-art radar odometry methods on the HeRCULES dataset. While remaining competitive in relative pose estimation, our method improves global trajectory consistency and demonstrates robustness across different radar sensors and environments on the VoD and NTU4DRadLM benchmarks.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7158-7165
Open AccessClaRO: A Cluster-Based Method for Radar Odometry
We present ClaRO, an unsupervised, cluster-based odometry pipeline for 4D imaging radar to improve robustness and reduce long-term drift for radar-only odometry.Our core idea is to utilize density-based clustering to improve ego-motion estimation using per-cluster Doppler-residuals and find a local best result to seed a robust least squares in addition to finding static points for pose estimation. The resulting global inlier mask is used to refine the pose via a weighted iterative closest point (ICP) approach that fuses Doppler and radar cross-section (RCS) cues while down-weighting the radar’s weak elevation axis. The method is fully unsupervised and sensor-agnostic. We compare our method on multiple public datasets (View-of-Delft, HeRCULES, and NTU4DRadLM) and show that our approach provides results that match or exceed recent radar-only odometry baselines (Radar4Motion, EFEAR-4D) and pose graph based 4DRadarSLAM. Our cluster-wise approach significantly reduces long-term drift, achieving a 72.0% improvement in mean absolute trajectory error (ATE) and a 73.2% improvement in absolute rotation error (ARE) compared to state-of-the-art radar odometry methods on the HeRCULES dataset. While remaining competitive in relative pose estimation, our method improves global trajectory consistency and demonstrates robustness across different radar sensors and environments on the VoD and NTU4DRadLM benchmarks.
- Open Access
- 5 September 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (9) , 1789-1807
Interdisciplinary Development and Reflection of a Robotic System for Nursing: An Overview of the AdaMeKoR Project
The interdisciplinary AdaMeKoR project (An Adaptive Multi-Component Robot System for Nursing Care) focused on the development, evaluation, and reflection of a robotic system for nursing care. Conducted from 2020 to 2023, its goal was to create solutions that support both care recipients and professional caregivers. The project investigated the potential for physical relief of caregivers and patients’ increased autonomy, guided by the central question of how good care can be supported, while also considering implementation research and ethical implications. This article provides an overview of the project’s theoretical framework, a description of the developed system, and four exemplary empirical studies. The results include quantitative data on the physical relief potential and user experiences with different control formats, as well as qualitative findings from implementation research and ethical analysis. Further, these results are contextualized with respect to the support of good care. Finally, the article discusses broad implications for the research and implementation of robotic systems in nursing care and outlines key overarching insights. The project demonstrates the clear benefits of interdisciplinary collaboration that incorporates the perspectives of all stakeholders involved in care.
- 5 September 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (9) , 1789-1807
Open AccessInterdisciplinary Development and Reflection of a Robotic System for Nursing: An Overview of the AdaMeKoR Project
The interdisciplinary AdaMeKoR project (An Adaptive Multi-Component Robot System for Nursing Care) focused on the development, evaluation, and reflection of a robotic system for nursing care. Conducted from 2020 to 2023, its goal was to create solutions that support both care recipients and professional caregivers. The project investigated the potential for physical relief of caregivers and patients’ increased autonomy, guided by the central question of how good care can be supported, while also considering implementation research and ethical implications. This article provides an overview of the project’s theoretical framework, a description of the developed system, and four exemplary empirical studies. The results include quantitative data on the physical relief potential and user experiences with different control formats, as well as qualitative findings from implementation research and ethical analysis. Further, these results are contextualized with respect to the support of good care. Finally, the article discusses broad implications for the research and implementation of robotic systems in nursing care and outlines key overarching insights. The project demonstrates the clear benefits of interdisciplinary collaboration that incorporates the perspectives of all stakeholders involved in care.
- 4 August 2023
- Published by Springer Nature
- p. 55-71
Potenziale entlastender Assistenzrobotik in der Pflege
- 4 August 2023
- Published by Springer Nature
- p. 55-71
Potenziale entlastender Assistenzrobotik in der Pflege
- Open Access
- 4 November 2022
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 7 (1) , 1-12
A rule-based robotic assistance system providing physical relief for nurses during repositioning tasks at the care bed
In nursing care, physical overload is an important issue that plays a main role in adding to the number of sick days or even causing staff to withdrawal from the profession. In addition to existing physical aids, robotics in particular has the potential to provide general physical relief during extremely stressful care activities provided at the bedside by performing assistance activities. To shed more light on the relief potential offered, we conducted a study involving 12 caregivers who used a lightweight robot attached to a nursing care bed to assist in the repositioning process. We relied on a robot system architecture that enables rule-based movement adjustments in real time using the Robot Operating System and Unity. The study focused on the repositioning of a patient simulator from the supine to the lateral position. The comparison of the measured ground reaction forces and muscle activity data suggests that robotic assistance during the performance of the activity reduces load peaks and generally leads to more attenuated ground reaction force curves, which results overall in a healthier way of working. With robotic assistance, the average back extensor muscle activations were 25.7% lower compared to conventional repositioning. In addition, the measured maximum occurring muscle activations were reduced by 61.2% when the robotic assistance system was deployed.
- 4 November 2022
- Published by Springer Nature in International Journal of Intelligent Robotics and Applications
- Vol. 7 (1) , 1-12
Open AccessA rule-based robotic assistance system providing physical relief for nurses during repositioning tasks at the care bed
In nursing care, physical overload is an important issue that plays a main role in adding to the number of sick days or even causing staff to withdrawal from the profession. In addition to existing physical aids, robotics in particular has the potential to provide general physical relief during extremely stressful care activities provided at the bedside by performing assistance activities. To shed more light on the relief potential offered, we conducted a study involving 12 caregivers who used a lightweight robot attached to a nursing care bed to assist in the repositioning process. We relied on a robot system architecture that enables rule-based movement adjustments in real time using the Robot Operating System and Unity. The study focused on the repositioning of a patient simulator from the supine to the lateral position. The comparison of the measured ground reaction forces and muscle activity data suggests that robotic assistance during the performance of the activity reduces load peaks and generally leads to more attenuated ground reaction force curves, which results overall in a healthier way of working. With robotic assistance, the average back extensor muscle activations were 25.7% lower compared to conventional repositioning. In addition, the measured maximum occurring muscle activations were reduced by 61.2% when the robotic assistance system was deployed.