For full functionality of this site it is necessary to enable JavaScript. Here are the instructions how to enable JavaScript in your web browser.

Position within the page tree

Home
Institute
Team
Zhou, Zexu

Zexu Zhou

M.Sc.

Research Assistant "Mechatronic Systems and Processes"
Institute for Control Engineering of Machine Tools and Manufacturing Units

Contact

+49 711 685 82430
Email
Business card (VCF)

Seidenstr. 36
70174 Stuttgart
Germany
Room: 5.088

Office Hours

by appointment

Publications

Publications:

Xu, Haijia ; Hinze, Christoph ; Iannelli, Andrea ; Zhou, Zexu ; Verl, Alexander: Increasing dynamic accuracy of machine tools using predictive feedforward optimization with hybrid modeling. In: Robotics and Computer-Integrated Manufacturing Bd. 98, Elsevier BV (2026), S. 103137
BibTeX
@article{Xu_2026, author = {Xu, Haijia and Hinze, Christoph and Iannelli, Andrea and Zhou, Zexu and Verl, Alexander}, doi = {10.1016/j.rcim.2025.103137}, issn = {0736-5845}, journal = {Robotics and Computer-Integrated Manufacturing}, month = {04}, pages = 103137, publisher = {Elsevier BV}, title = {Increasing dynamic accuracy of machine tools using predictive feedforward optimization with hybrid modeling}, url = {http://dx.doi.org/10.1016/j.rcim.2025.103137}, volume = 98, year = 2026 }
Link
http://dx.doi.org/10.1016/j.rcim.2025.103137
DOI
10.1016/j.rcim.2025.103137
Zeh, Lukas ; Meiwaldt, Johannes ; Zhou, Zexu ; Lechler, Armin ; Verl, Alexander: Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short-Term Memory Learning. In: Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics : SCITEPRESS - Science and Technology Publications, 2025 — ISBN 978-989-758-770-2, S. 47–58
BibTeX
@inproceedings{Zeh_2025, abstract = {The manipulation of Deformable Linear Objects (DLOs) such as cables poses a significant challenge for automation due to their infinite degrees of freedom and non-linear dynamics. In this paper we present a machine learning based optimal control approach for the manipulation of DLOs. This approach is divided into two main components: modeling and control. For modeling the dynamics of the DLO, we propose a learning based approach using a bidirectional Long Short-Term Memory (biLSTM) network. The biLSTM network is trained on synthetic data generated by the MuJoCo physics engine. For manipulating the DLO, a model predictive control strategy that employs Model Predictive Path Integral (MPPI) control is selected. The proposed approach is evaluated through simulation and experiments. The results demonstrate the effectiveness of the proposed method in achieving accurate and efficient manipulation of DLOs.}, author = {Zeh, Lukas and Meiwaldt, Johannes and Zhou, Zexu and Lechler, Armin and Verl, Alexander}, booktitle = {Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics}, doi = {10.5220/0013703800003982}, isbn = {978-989-758-770-2}, issn = {2184-280}, language = {English}, month = {10}, organization = {INSTICC}, pages = {47–58}, publisher = {SCITEPRESS - Science and Technology Publications}, title = {Manipulation of Deformable Linear Objects Using Model Predictive Path Integral Control with Bidirectional Long Short-Term Memory Learning}, url = {http://dx.doi.org/10.5220/0013703800003982}, year = 2025 }
Link
http://dx.doi.org/10.5220/0013703800003982
DOI
10.5220/0013703800003982
Hinze, Christoph ; Zhou, Zexu ; Xu, Haijia ; Lechler, Armin ; Verl, Alexander: RTNNIgen – An Open-Source PLC Library and Python Generator Converting Keras Models to Realtime Capable Structured Text. In: IEEE (Hrsg.) ; IEEE (Hrsg.): IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society, 2024, S. 1–7
- BibTeX
- DOI
BibTeX
@inproceedings{10905775, abstract = {Recent advances in AI research are boosting the relevance of realtime neural networks in automation technology. To facilitate the deployment of trained neural networks for realtime applications, where hard limits on upper cycle time are required, this paper contributed a two-fold approach: A Python library for parsing Keras sequential models to structured text using a single function-call, which can be run directly on industrial PLCs and a structured text library to encapsulate reoccurring code and to provide a readable, tested interface for the generated code. The resulting models are experimentally validated regarding their inference time and precision of the outputs.}, author = {Hinze, Christoph and Zhou, Zexu and Xu, Haijia and Lechler, Armin and Verl, Alexander}, booktitle = {IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society}, doi = {10.1109/IECON55916.2024.10905775}, editor = {IEEE}, month = {11}, pages = {1-7}, title = {RTNNIgen – An Open-Source PLC Library and Python Generator Converting Keras Models to Realtime Capable Structured Text}, year = 2024 }
DOI
10.1109/IECON55916.2024.10905775

Zexu Zhou

Contact

Office Hours

Publications

BibTeX

Link

DOI

BibTeX

Link

DOI

BibTeX

DOI

Audience

Formalities

Services

Organization

Zexu Zhou

Contact

Office Hours

Publications

BibTeX

Link

DOI

BibTeX

Link

DOI

BibTeX

DOI

Here you can reach the ISW

Audience

Formalities

Services

Organization