Výsledky vyhledávání - "Borghese, N. Alberto"

Report

R2SNet: Scalable Domain Adaptation for Object Detection in Cloud-Based Robotic Ecosystems via Proposal Refinement

Autor: Antonazzi, Michele, Luperto, Matteo, Borghese, N. Alberto, Basilico, Nicola

We introduce a novel approach for scalable domain adaptation in cloud robotics scenarios where robots rely on third-party AI inference services powered by large pre-trained deep neural networks. Our method is based on a downstream proposal-refinement

Externí odkaz: http://arxiv.org/abs/2403.11567

Zobrazit plný text záznamu

Report

Development and Adaptation of Robotic Vision in the Real-World: the Challenge of Door Detection

Autor: Antonazzi, Michele, Luperto, Matteo, Borghese, N. Alberto, Basilico, Nicola

Mobile service robots are increasingly prevalent in human-centric, real-world domains, operating autonomously in unconstrained indoor environments. In such a context, robotic vision plays a central role in enabling service robots to perceive high-lev

Externí odkaz: http://arxiv.org/abs/2401.17996

Zobrazit plný text záznamu

Report

Enhancing Door-Status Detection for Autonomous Mobile Robots during Environment-Specific Operational Use

Autor: Antonazzi, Michele, Luperto, Matteo, Basilico, Nicola, Borghese, N. Alberto

Publikováno v: 2023 European Conference on Mobile Robots (ECMR), Coimbra, Portugal, 2023, pp. 1-8

Door-status detection, namely recognizing the presence of a door and its status (open or closed), can induce a remarkable impact on a mobile robot's navigation performance, especially for dynamic settings where doors can enable or disable passages, c

Externí odkaz: http://arxiv.org/abs/2203.03959

Zobrazit plný text záznamu