Neuromorphic robust framework for integrated estimation and control in dynamical systems using spiking neural networks
Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad · 2025
Read Neuromorphic robust framework for integrated estimation and control in dynamical systems using spiking neural networks by Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad (2025) 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-12748578.txt.
Description
Reza Ahmadvand, Sarah Safura Sharif, and Yaser Mike Banad build a neuromorphic framework that jointly estimates state and controls a dynamical system using spiking neural networks. Robots must infer their state from noisy measurements while they steer, and the two jobs feed each other. Their 2025 framework joins a spiking network, whose neurons fire in bursts, with a robust filter and a classic control law. No training is used: the network weights are set from the system's own model.
A firing rule in the network acts like predictive coding drawn from neuroscience. Tests ran on a benchmark task and on a spacecraft rendezvous path. Next to the same pairing without spikes, and to the textbook gold-standard pairing, the spiking framework held its accuracy and robustness. It also ran leaner, which suits constrained craft. The team pitches it for demanding, fast-moving systems.
Catalog record
| CREATOR | Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 205 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |