Matteo Vaghi

Matteo Vaghi

Auto-generated profile, based on publicly available information

Matteo Vaghi

Università degli Studi di Milano - Bicocca

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2022 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
DCDaniele Cattaneo
Daniele Cattaneo
MVMatteo Vaghi
Matteo Vaghi
AVAbhinav Valada
Abhinav Valada
Loop closure detection is an essential component of simultaneous localization and mapping (SLAM) systems, which reduces the drift accumulated over time. Over the years, several deep learning approaches have been proposed to address this task; however, their performance has been subpar compared to handcrafted techniques, especially while dealing with reverse loops. In this article, we introduce the novel loop closure detection network (LCDNet) that effectively detects loop closures in light detection and ranging (LiDAR) point clouds by simultaneously identifying previously visited places and estimating the six degrees of freedom relative transformation between the current scan and the map. LCDNet is composed of a shared encoder, a place recognition head that extracts global descriptors, and a relative pose head that estimates the transformation between two point clouds. We introduce a novel relative pose head based on the unbalanced optimal transport theory that we implement in a differentiable manner to allow for end-to-end training. Extensive evaluations of LCDNet on multiple real-world autonomous driving datasets show that our approach outperforms state-of-the-art loop closure detection and point cloud registration techniques by a large margin, especially while dealing with reverse loops. Moreover, we integrate our proposed loop closure detection approach into a LiDAR SLAM library to provide a complete mapping system and demonstrate the generalization ability using different sensor setup in an unseen city.

1 June 2021 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
SFSimone Fontana
Simone Fontana
DCDaniele Cattaneo
Daniele Cattaneo
Augusto Luis BallardiniAugusto Luis Ballardini
Augusto Luis Ballardini
MVMatteo Vaghi
Matteo Vaghi
DSDomenico Giorgio Sorrenti
Domenico Giorgio Sorrenti

9 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
MVMatteo Vaghi
Matteo Vaghi
ABAugusto Luis Ballardini
Augusto Luis Ballardini
SFSimone Fontana
Simone Fontana
DSDomenico Giorgio Sorrenti
Domenico Giorgio Sorrenti
Camera localization, i.e., camera pose regression, represents an important task in computer vision since it has many practical applications such as in the context of intelligent vehicles and their localization. Having reliable estimates of the regression uncertainties is also important, as it would allow us to catch dangerous localization failures. In the literature, uncertainty estimation in Deep Neural Networks (DNNs) is often performed through sampling methods, such as Monte Carlo Dropout (MCD) and Deep Ensemble (DE), at the expense of undesirable execution time or an increase in hardware resources. In this work, we considered an uncertainty estimation approach named Deep Evidential Regression (DER) that avoids any sampling technique, providing direct uncertainty estimates. Our goal is to provide a systematic approach to intercept localization failures of camera localization systems based on DNNs architectures, by analyzing the generated uncertainties. We propose to exploit CMRNet, a DNN approach for multi-modal image to LiDAR map registration, by modifying its internal configuration to allow for extensive experimental activity on the KITTI dataset. The experimental section highlights CMRNet's major flaws and proves that our proposal does not compromise the original localization performances but also provides, at the same time, the necessary introspection measures that would allow end-users to act accordingly.

2 November 2023
Verified
Book Chapter
Closed access
PDF file
MVMatteo Vaghi
Matteo Vaghi
FDFabio D’eLia
Fabio D’eLia
ABAugusto Luis Ballardini
Augusto Luis Ballardini
DSDomenico Giorgio Sorrenti
Domenico Giorgio Sorrenti