Alexander Pawluchin

Alexander Pawluchin

Auto-generated profile, based on publicly available information

Alexander Pawluchin

Compliant Robotics Lab, Berlin University of Applied Sciences and Technology, Berlin, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 November 2025 in Mechatronics
Verified
Journal Article
Open access
APA. Pawluchin
A. Pawluchin
THT.-L. Habich
T.-L. Habich
TST. Seel
T. Seel
IBI. Boblan
I. Boblan

1 May 2024 in at - Automatisierungstechnik
Verified
Journal Article
Closed access
APAlexander Pawluchin
Alexander Pawluchin
MMMichael Meindl
Michael Meindl
IWIve Weygers
Ive Weygers
TSThomas Seel
Thomas Seel
IBIvo Boblan
Ivo Boblan
Highly compliant Pneumatic Soft Actuators (PSAs) have the potential to perform challenging tasks in a broad range of applications that require shape-adaptive capabilities. Achieving accurate tracking control for such actuators with complex geometries and material compositions typically involves many time-consuming and laborious engineering steps. In this work, we propose a data-driven learning-based control approach to address reference tracking tasks, incorporating self-adaptation in situ. We utilize a short interaction maneuver, recorded a priori, to collect the quasi-static data affected by severe hysteresis. Besides a linear feedback controller, we use two Gaussian process models to predict the feedforward control input to compensate for the nonlinearity in a one-shot learning setting. The proposed control approach demonstrates accurate tracking performance even under realistic varying configurations, such as alterations in mass and orientation, without any parameter tuning. Notably, training was achieved with only 25–50 s of experimental interaction, which emphasizes the plug-and-play capabilities in diverse real-world applications.

14 January 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Open access
MWManuel Weiss
Manuel Weiss
APAlexander Pawluchin
Alexander Pawluchin
JEJan-Hendrik Ewering
Jan-Hendrik Ewering
TSThomas Seel
Thomas Seel
IBIvo Boblan
Ivo Boblan
This letter introduces a control framework that leverages Lagrangian neural network (LNN) for computed torque control (CTC) of robotic systems with unknown dynamics. Unlike prior LNN-based controllers that are placed outside the feedback-linearization framework (e.g., feedforward), we embed an LNN inverse-dynamics model within a CTC loop, thereby shaping the closed-loop error dynamics. This strategy, referred to as LNN-CTC, ensures a physically consistent model and improves extrapolation, requiring neither prior model knowledge nor extensive training data. The approach is experimentally validated on a robotic arm with four degrees of freedom and compared with conventional model-based CTC, physics-informed neural network (PINN)-CTC, deep neural network (DNN)-CTC, an LNN-based feedforward controller, and a PID controller. Results demonstrate that LNN-CTC significantly outperforms model-based baselines by up to $30 \,\%$ in tracking accuracy, achieving high performance with minimal training data. In addition, LNN-CTC outperforms all other evaluated baselines in both tracking accuracy and data efficiency, attaining lower joint-space RMSE for the same training data. The findings highlight the potential of physics-informed neural architectures to generalize robustly across various operating conditions and contribute to narrowing the performance gap between learned and classical control strategies.