arXiv subjects

Leonardo Brizi

Publications and source records attributed to Leonardo Brizi.

15 recordsLinked to original sources

arXiv2026

Breaking Time: A Fully Gaussian Framework for Distributed and Continuous-Time SLAM

Continuous-time SLAM provides a principled framework for fusing heterogeneous sensors while estimating smooth trajectories, and is particularly well-suited for handling heterogeneous, asynchronous sensor streams with non-uniform readout patterns, such as rolling shutter cameras, LiDAR scanners, radar sweeps, or event-based sensors. In this work, we introduce G-solver, a fully Gaussian and distributed framework that combines Gaussian Belief Propagation (GBP) with Gaussian Process (GP) motion priors for continuous-time trajectory estimation. Our GP model provides a probabilistic representation of the trajectory, enabling consistent interpolation and the use of data-driven hyperparameters, while GBP offers a scalable message-passing formulation well-suited for decentralized settings. The resulting solver naturally extends to multi-camera scenarios without specialized synchronization or engineering effort. We evaluate the approach on synthetic and real data, including rolling shutter and distributed multi-camera optimization, demonstrating accurate and stable estimation with runtimes comparable to existing continuous-time methods. An open-source implementation is released.

cs.RO↗

arXiv2026

Dr-PoGO: Direct Radar Pose-Graph Optimization

This paper introduces Dr-PoGO, a method for Simultaneous Localization And Mapping (SLAM) using a 2D spinning radar. Unlike cameras or lidars that require line-of-sight, millimetre-wave radars can `see' through dust, falling snow, rain, etc. Accordingly, it is a great modality for robust perception regardless of the weather conditions. While most existing radar-based SLAM methods rely on the extraction of point clouds or features to perform ego-motion estimation, Dr-PoGO leverages direct registration techniques for odometry (DRO) and loop-closure registration. An off-the-shelf radar-focused place recognition algorithm, RaPlace, provides loop-closure candidates. As RaPlace does not provide relative transformations, Dr-PoGO introduces a coarse-to-fine registration that uses visual features and descriptors to obtain an initial guess for the direct transformation refinement. The global trajectory is optimized in a pose-graph optimization. Dr-PoGO demonstrates state-of-the-art performance over 300km of data in various real-world automotive environments. Our implementation is publicly available: https://github.com/utiasASRL/dr_pogo.

cs.RO↗

arXiv2025

Hardware acceleration for ultra-fast Neural Network training on FPGA for MRF map reconstruction

Magnetic Resonance Fingerprinting (MRF) is a fast quantitative MR Imaging technique that provides multi-parametric maps with a single acquisition. Neural Networks (NNs) accelerate reconstruction but require significant resources for training. We propose an FPGA-based NN for real-time brain parameter reconstruction from MRF data. Training the NN takes an estimated 200 seconds, significantly faster than standard CPU-based training, which can be up to 250 times slower. This method could enable real-time brain analysis on mobile devices, revolutionizing clinical decision-making and telemedicine.

cs.AR↗

arXiv2025

DRO: Doppler-Aware Direct Radar Odometry

A renaissance in radar-based sensing for mobile robotic applications is underway. Compared to cameras or lidars, millimetre-wave radars have the ability to `see' through thin walls, vegetation, and adversarial weather conditions such as heavy rain, fog, snow, and dust. In this paper, we propose a novel SE(2) odometry approach for spinning frequency-modulated continuous-wave radars. Our method performs scan-to-local-map registration of the incoming radar data in a direct manner using all the radar intensity information without the need for feature or point cloud extraction. The method performs locally continuous trajectory estimation and accounts for both motion and Doppler distortion of the radar scans. If the radar possesses a specific frequency modulation pattern that makes radial Doppler velocities observable, an additional Doppler-based constraint is formulated to improve the velocity estimate and enable odometry in geometrically feature-deprived scenarios (e.g., featureless tunnels). Our method has been validated on over 250km of on-road data sourced from public datasets (Boreas and MulRan) and collected using our automotive platform. With the aid of a gyroscope, it outperforms state-of-the-art methods and achieves an average relative translation error of 0.26% on the Boreas leaderboard. When using data with the appropriate Doppler-enabling frequency modulation pattern, the translation error is reduced to 0.18% in similar environments. We also benchmarked our algorithm using 1.5 hours of data collected with a mobile robot in off-road environments with various levels of structure to demonstrate its versatility. Our real-time implementation is publicly available: https://github.com/utiasASRL/dro.

cs.RO↗

arXiv2024

MAD-ICP: It Is All About Matching Data -- Robust and Informed LiDAR Odometry

LiDAR odometry is the task of estimating the ego-motion of the sensor from sequential laser scans. This problem has been addressed by the community for more than two decades, and many effective solutions are available nowadays. Most of these systems implicitly rely on assumptions about the operating environment, the sensor used, and motion pattern. When these assumptions are violated, several well-known systems tend to perform poorly. This paper presents a LiDAR odometry system that can overcome these limitations and operate well under different operating conditions while achieving performance comparable with domain-specific methods. Our algorithm follows the well-known ICP paradigm that leverages a PCA-based kd-tree implementation that is used to extract structural information about the clouds being registered and to compute the minimization metric for the alignment. The drift is bound by managing the local map based on the estimated uncertainty of the tracked pose. To benefit the community, we release an open-source C++ anytime real-time implementation.

cs.RO↗

arXiv2024

VBR: A Vision Benchmark in Rome

This paper presents a vision and perception research dataset collected in Rome, featuring RGB data, 3D point clouds, IMU, and GPS data. We introduce a new benchmark targeting visual odometry and SLAM, to advance the research in autonomous robotics and computer vision. This work complements existing datasets by simultaneously addressing several issues, such as environment diversity, motion patterns, and sensor frequency. It uses up-to-date devices and presents effective procedures to accurately calibrate the intrinsic and extrinsic of the sensors while addressing temporal synchronization. During recording, we cover multi-floor buildings, gardens, urban and highway scenarios. Combining handheld and car-based data collections, our setup can simulate any robot (quadrupeds, quadrotors, autonomous vehicles). The dataset includes an accurate 6-dof ground truth based on a novel methodology that refines the RTK-GPS estimate with LiDAR point clouds through Bundle Adjustment. All sequences divided in training and testing are accessible through our website.

cs.CV↗

arXiv2023

Enhancing LiDAR performance: Robust De-skewing Exclusively Relying on Range Measurements

Most commercially available Light Detection and Ranging (LiDAR)s measure the distances along a 2D section of the environment by sequentially sampling the free range along directions centered at the sensor's origin. When the sensor moves during the acquisition, the measured ranges are affected by a phenomenon known as "skewing", which appears as a distortion in the acquired scan. Skewing potentially affects all systems that rely on LiDAR data, however, it could be compensated if the position of the sensor were known each time a single range is measured. Most methods to de-skew a LiDAR are based on external sensors such as IMU or wheel odometry, to estimate these intermediate LiDAR positions. In this paper, we present a method that relies exclusively on range measurements to effectively estimate the robot velocities which are then used for de-skewing. Our approach is suitable for low-frequency LiDAR where the skewing is more evident. It can be seamlessly integrated into existing pipelines, enhancing their performance at a negligible computational cost.

cs.RO↗

arXiv2023

Ca$^2$Lib: Simple and Accurate LiDAR-RGB Calibration using Small Common Markers

In many fields of robotics, knowing the relative position and orientation between two sensors is a mandatory precondition to operate with multiple sensing modalities. In this context, the pair LiDAR-RGB cameras offer complementary features: LiDARs yield sparse high quality range measurements, while RGB cameras provide a dense color measurement of the environment. Existing techniques often rely either on complex calibration targets that are expensive to obtain, or extracted virtual correspondences that can hinder the estimate's accuracy. In this paper we address the problem of LiDAR-RGB calibration using typical calibration patterns (i.e. A3 chessboard) with minimal human intervention. Our approach exploits the planarity of the target to find correspondences between the sensors measurements, leading to features that are robust to LiDAR noise. Moreover, we estimate a solution by solving a joint non-linear optimization problem. We validated our approach by carrying on quantitative and comparative experiments with other state-of-the-art approaches. Our results show that our simple schema performs on par or better than other approches using complex calibration targets. Finally, we release an open-source C++ implementation at \url{https://github.com/srrg-sapienza/ca2lib}

cs.RO↗

arXiv2023

Photometric LiDAR and RGB-D Bundle Adjustment

The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of Simultaneous Localization and Mapping (SLAM) systems. To achieve this, the gold standard is Bundle Adjustment (BA). Modern 3D LiDARs now retain higher resolutions that enable the creation of point cloud images resembling those taken by conventional cameras. Nevertheless, the typical effective global refinement techniques employed for RGB-D sensors are not widely applied to LiDARs. This paper presents a novel BA photometric strategy that accounts for both RGB-D and LiDAR in the same way. Our work can be used on top of any SLAM/GNSS estimate to improve and refine the initial trajectory. We conducted different experiments using these two depth sensors on public benchmarks. Our results show that our system performs on par or better compared to other state-of-the-art ad-hoc SLAM/BA strategies, free from data association and without making assumptions about the environment. In addition, we present the benefit of jointly using RGB-D and LiDAR within our unified method. We finally release an open-source CUDA/C++ implementation.

cs.CV↗

arXiv2022

MD-SLAM: Multi-cue Direct SLAM

Simultaneous Localization and Mapping (SLAM) systems are fundamental building blocks for any autonomous robot navigating in unknown environments. The SLAM implementation heavily depends on the sensor modality employed on the mobile platform. For this reason, assumptions on the scene's structure are often made to maximize estimation accuracy. This paper presents a novel direct 3D SLAM pipeline that works independently for RGB-D and LiDAR sensors. Building upon prior work on multi-cue photometric frame-to-frame alignment, our proposed approach provides an easy-to-extend and generic SLAM system. Our pipeline requires only minor adaptations within the projection model to handle different sensor modalities. We couple a position tracking system with an appearance-based relocalization mechanism that handles large loop closures. Loop closures are validated by the same direct registration algorithm used for odometry estimation. We present comparative experiments with state-of-the-art approaches on publicly available benchmarks using RGB-D cameras and 3D LiDARs. Our system performs well in heterogeneous datasets compared to other sensor-specific methods while making no assumptions about the environment. Finally, we release an open-source C++ implementation of our system.

cs.RO↗

arXiv2022

MUPen2DTool: a Matlab Tool for 2D Nuclear Magnetic Resonance relaxation data inversion

Accurate and efficient analysis of materials properties from Nuclear Magnetic Resonance (NMR) relaxation data requires robust and efficient inversion procedures. Despite the great variety of applications requiring to process two-dimensional NMR data (2DNMR), a few software tools are freely available. The aim of this paper is to present MUPen2DTool, an open-source MATLAB based software tool for 2DNMR data inversion. The user can choose among several types of NMR experiments, and the software provides codes that can be used and extended easily. Furthermore, a MATLAB interface makes it easier to include users own data. The practical use is demonstrated in the reported examples of both synthetic and real NMR data.

cs.MS↗

arXiv2018

Circumventing the Curse of Dimensionality in Magnetic Resonance Fingerprinting through a Deep Learning Approach

MR fingerprinting (MRF) is a rapid growing approach for fast quantitave MRI. A typical drawback of dictionary-based MRF is its explosion in size as a function of the number of reconstructed parameters, according to the curse of dimensionality. Deep Neural Networks (NNs) have been proposed as a feasible alternative, but these approaches are still in their infancy. We tested different NN pipelines on simulated data: we studied optimal training procedures by including different strategies of noise addition and parameter space sampling, to achieve better accuracy and robustness to noise. Four MRF sequences were considered, two of them designed to be more specific for $B_1^+$ parameter encoding: IR-FISP, IR-FISP-$B_1$, bSSFP and IR-bSSFP-$B_1$. A comparison between NN and the dictionary approaches was performed using a numerical brain phantom. Results demonstrated that training with random sampling and different levels of noise variance yielded the best performance. NN performance was greater or equal than dictionary-based approach in reconstructing MR parameter maps: the difference in performance increased with the number of estimated parameters, because the dictionary method suffers from the coarse resolution of the MR parameter space sampling. The NN approach resulted more efficient in terms of memory and computational burden, and thus has great potential in large-scale MRF problems.

physics.med-ph↗

arXiv2011

The lightest scalar in theories with broken supersymmetry

We study the scalar mass matrix of general supersymmetric theories with local gauge symmetries, and derive an absolute upper bound on the lightest scalar mass. This bound can be saturated by suitably tuning the superpotential, and its positivity therefore represents a necessary and sufficient condition for the existence of metastable vacua. It is derived by looking at the subspace of all those directions in field space for which an arbitrary supersymmetric mass term is not allowed and scalar masses are controlled by supersymmetry-breaking splitting effects. This subspace includes not only the direction of supersymmetry breaking, but also the directions of gauge symmetry breaking and the lightest scalar is in general a linear combination of fields spanning all these directions. We present explicit results for the simplest case of theories with a single local gauge symmetry. For renormalizable gauge theories, the lightest scalar is a combination of the Goldstino partners and its square mass is always positive. For more general non-linear sigma models, on the other hand, the lightest scalar can involve also the Goldstone partner and its square mass is not always positive.

hep-th↗

arXiv2010

Effects of heavy modes on vacuum stability in supersymmetric theories

We study the effects induced by heavy fields on the masses of light fields in supersymmetric theories, under the assumption that the heavy mass scale is much higher than the supersymmetry breaking scale. We show that the square-masses of light scalar fields can get two different types of significant corrections when a heavy multiplet is integrated out. The first is an indirect level-repulsion effect, which may arise from heavy chiral multiplets and is always negative. The second is a direct coupling contribution, which may arise from heavy vector multiplets and can have any sign. We then apply these results to the sGoldstino mass and study the implications for the vacuum metastability condition. We find that the correction from heavy chiral multiplets is always negative and tends to compromise vacuum metastability, whereas the contribution from heavy vector multiplets is always positive and tends on the contrary to reinforce it. These two effects are controlled respectively by Yukawa couplings and gauge charges, which mix one heavy and two light fields respectively in the superpotential and the Kahler potential. Finally we also comment on similar effects induced in soft scalar masses when the heavy multiplets couple both to the visible and the hidden sector.

hep-th↗

arXiv2009

Globally and locally supersymmetric effective theories for light fields

We reconsider the general question of how to characterize most efficiently the low-energy effective theory obtained by integrating out heavy modes in globally and locally supersymmetric theories. We consider theories with chiral and vector multiplets and identify the conditions under which an approximately supersymmetric low-energy effective theory can exist. These conditions translate into the requirements that all the derivatives, fermions and auxiliary fields should be small in units of the heavy mass scale. They apply not only to the matter sector, but also to the gravitational one if present, and imply in that case that the gravitino mass should be small. We then show how to determine the unique exactly supersymmetric theory that approximates this effective theory at the lowest order in the counting of derivatives, fermions and auxiliary fields, by working both at the superfield level and with component fields. As a result we give a simple prescription for integrating out heavy superfields in an algebraic and manifestly supersymmetric way, which turns out to hold in the same form both for globally and locally supersymmetric theories, meaning that the process of integrating out heavy modes commutes with the process of switching on gravity. More precisely, for heavy chiral and vector multiplets one has to impose respectively stationarity of the superpotential and the Kahler potential.

hep-th↗