Self-Supervised Path Planning in UAV-aided Wireless Networks based on Active Inference

no code implementations • 6 Mar 2024 • Ali Krayani, Khalid Khan, Lucio Marcenaro, Mario Marchese, Carlo Regazzoni

This paper presents a novel self-supervised path-planning method for UAV-aided networks.

Collective Awareness for Abnormality Detection in Connected Autonomous Vehicles

no code implementations • 28 Oct 2020 • Divya Thekke Kanapram, Fabio Patrone, Pablo Marin-Plaza, Mario Marchese, Eliane L. Bodanese, Lucio Marcenaro, David Martín Gómez, Carlo Regazzoni

A growing neural gas (GNG) algorithm is used to learn the node variables and conditional probabilities linking nodes in the DBN models; a Markov jump particle filter (MJPF) is employed for state estimation and abnormality detection in each agent using learned DBNs as filter parameters.

Anomaly Detection Autonomous Vehicles +1

Dynamic Bayesian Approach for decision-making in Ego-Things

no code implementations • 28 Oct 2020 • Divya Kanapram, Damian Campo, Mohamad Baydoun, Lucio Marcenaro, Eliane L. Bodanese, Carlo Regazzoni, Mario Marchese

The proposed method produces multiple inference models by considering several features of the observed data.

Anomaly Detection Clustering +2