Forward geometric model prediction of a 6-RSU parallel manipulator using a modified NARX Bayesian neural network
Alaa Aldeen Joumah, Assef Jafar, Chadi Albitar · 2024
Read Forward geometric model prediction of a 6-RSU parallel manipulator using a modified NARX Bayesian neural network by Alaa Aldeen Joumah, Assef Jafar, Chadi Albitar (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11696652.txt.
Description
Alaa Aldeen Joumah, Assef Jafar, and Chadi Albitar present a 2024 study of robot modeling with Bayesian neural networks. A 6-RSU parallel manipulator moves a platform with six linked arms. Predicting its forward geometry, where the platform sits for given joint settings, must be exact for safe work. Bayesian networks learn such models and also report their own uncertainty. Earlier learning studies predicted the geometry but gave no confidence range. The team modifies a NARX-style network, which uses past inputs and outputs, into Bayesian form.
The blend pairs strong prediction with honest error bars. Simulation and bench experiments test the model. Robotics engineers get position estimates that know when to distrust themselves. Uncertainty is a safety feature in shared workspaces: a robot unsure of its pose should slow down. Parallel robots are fast but geometrically tricky, so learned models with confidence are a practical advance over fixed formulas.
Catalog record
| CREATOR | Alaa Aldeen Joumah, Assef Jafar, Chadi Albitar |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |