Development of neuromorphic technologies for visual inertial odometry

Scientific-Disciplinary Group

09/IINF-05 - Information Processing Systems

Description

Spiking Neural Networks (SNNs) are strongly bio-inspired—also referred to as neuromorphic—neural models that process information in the form of discrete events (spikes). They are considered effective alternatives to conventional artificial neural networks for handling real-time, sparse data streams produced by event-based sensors, such as cameras or other asynchronous sensing modalities. Currently, most implementations of continual learning in SNNs are confined to specialized neuromorphic platforms, such as Intel Loihi or SpiNNaker (see CLP-SNN), and are typically evaluated on relatively simple benchmarks. Porting these approaches to a general-purpose, ultra-low-power, open-source microcontroller architecture and assessing their performance on more realistic robotics benchmarks would significantly broaden their applicability to open-hardware autonomous CPS.

Job posting website

https://bandi.unibo.it/ricerca/incarichi-di-ricerca

Funding body

ALMA MATER STUDIORUM - UNIVERSITA' DI BOLOGNA - - DIPARTIMENTO DI INGEGNERIA DELL'ENERGIA ELETTRICA E DELL'INFORMAZIONE "GUGLIELMO MARCONI"

How to apply

Other

Selection process