Event- and Frame-Based Visual Odometry for Ultra-Low-Power Neuromorphic Systems

Scientific-Disciplinary Group

09/IINF-01 - Electronics

Description

This Incarico di Ricerca is framed within the RoboMix2 project and focuses on the investigation and development of event- and frame-based visual odometry techniques, targeting deployment on ultra-low-power platforms such as GAP9 and Kraken.The research activity covers three main aspects:Design of hybrid visual odometry pipelines combining event-based processing (SNNs or asynchronous models) and frame-based processing (ANNs), evaluated for accuracy, latency, and robustness.Algorithmic and architectural optimization to meet the memory, power, and throughput constraints of ultra-low-power SoCs.Deployment and validation on GAP9 and Kraken, including sensor integration and experimental evaluation on robotic platforms.This activity advances the RoboMix2 objectives by pushing the state of the art in neuromorphic perception for robotics and delivering concrete solutions for efficient visual odometry on next-generation embedded systems.

Job posting website

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

Funding body

ALMA MATER STUDIORUM - UNIVERSITA' DI BOLOGNA - - CENTRO RICERCA SISTEMI ELETTRONICI INGEGN.INF. E TELECOM."ERCOLE DE CASTRO"

How to apply

Other

Selection process