Experimental Data-Driven Intelligence for Pneumatic Continuum Robots: Learning Six-Chamber Actuation Pressures Through Sim-to-Real Neural Networks
CBHA-PI-S2R-Net — Python code for the paper “Experimental Data-Driven Intelligence for Pneumatic Continuum Robots: Learning Six-Chamber Actuation Pressures Through Sim-to-Real Neural Networks.” It trains a neural network, first in simulation and then on KUKA-measured data, to give the six chamber pressures of a CBHA continuum robot for a desired tip position in a single pass. The package includes the kinematic model, the proposed network and its ensemble, three baselines (MLP, SVR, random forest), the analyses, and the scripts that reproduce every figure. It requires Python 3 with NumPy, SciPy, scikit-learn and Matplotlib.
Authors
- Abdelhamid Ghoul (ORCID: https://orcid.org/0000-0002-1814-4278)
- Selman Djeffal (ORCID: https://orcid.org/0000-0002-5473-6270)
- Mohamed Razi Morakchi (ORCID: https://orcid.org/0000-0003-3154-1726)
- Atef Chibani (ORCID: https://orcid.org/0000-0002-5861-7498)
- Farhan Lafta Rashid (ORCID: https://orcid.org/0000-0002-7609-6585)
Institutions
- Luleå University of Technology (SE)
- Research Center in Industrial Technologies (DZ)
- University of Kerbala (IQ)
- Mouloud Mammeri University of Tizi-Ouzou (DZ)
- Ecole Nationale Polytechnique de Constantine (DZ)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-14
- DOI
- https://doi.org/10.5281/zenodo.24221547
- Primary Topic
- Soft Robotics and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00