Vision-informed short-horizon prediction for the squeeze flow of soft materials
Accurate yet computationally efficient models of soft-material deformation are essential for real-time prediction and control in robotic manipulation. Recent advances in machine learning for object detection and image segmentation have made it possible to reliably extract geometric observations from raw RGB data, opening new avenues for vision-based prediction. Building on these advances, this work investigates the feasibility of a vision-informed framework that couples coarse finite element simulations with continuous parameter recalibration to obtain action-responsive models of soft-material flow suitable for model-based planning and control. Leveraging RGB observations of squeeze flow experiments, the framework repeatedly identifies effective viscosity and slip parameters of a Stokes model over short moving windows via Gauss–Newton updates. Synthetic datasets and physical experiments demonstrate that this approach achieves reliable short-horizon predictions of the sample deformation and maintains geometric consistency despite observation noise and partial parameter identifiability.
Authors
- Clemens V. Verhoosel (ORCID: https://orcid.org/0000-0001-9319-1552)
- Nick O. Jaensson (ORCID: https://orcid.org/0000-0002-9477-5047)
- Alessandro Saccon (ORCID: https://orcid.org/0000-0001-5318-1747)
- Soshala Weerathunge
Institutions
- Eindhoven University of Technology (NL)
Publication Details
- Journal
- Finite Elements in Analysis and Design
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1016/j.finel.2026.104670
- Primary Topic
- Soft Robotics and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Technische Universiteit Eindhoven