Giorgio Grisetti

Davide Ceriola, Simone Ferrari, Luca Di Giammarino et al.

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.

Luca Di Giammarino, Emanuele Giacomini, Leonardo Brizi et al.

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.

Luca Di Giammarino, Boyang Sun, Giorgio Grisetti et al.

Accurate localization in diverse environments is a fundamental challenge in computer vision and robotics. The task involves determining a sensor's precise position and orientation, typically a camera, within a given space. Traditional localization methods often rely on passive sensing, which may struggle in scenarios with limited features or dynamic environments. In response, this paper explores the domain of active localization, emphasizing the importance of viewpoint selection to enhance localization accuracy. Our contributions involve using a data-driven approach with a simple architecture designed for real-time operation, a self-supervised data training method, and the capability to consistently integrate our map into a planning framework tailored for real-world robotics applications. Our results demonstrate that our method performs better than the existing one, targeting similar problems and generalizing on synthetic and real data. We also release an open-source implementation to benefit the community.

Krzysztof Ćwian, Luca Di Giammarino, Simone Ferrari et al.

The joint optimization of sensor poses and 3D structure is fundamental for state estimation in robotics and related fields. Current LiDAR systems often prioritize pose optimization, with structure refinement either omitted or treated separately using implicit representations. This paper introduces a framework for simultaneous optimization of sensor poses and 3D map, represented as surfels. A generalized LiDAR uncertainty model is proposed to address less reliable measurements in varying scenarios. Experimental results on public datasets demonstrate improved performance over most comparable state-of-the-art methods. The system is provided as open-source software to support further research.

Gianmarco Roggiolani, Federico Magistri, Tiziano Guadagnino et al.

Agricultural robots have the prospect to enable more efficient and sustainable agricultural production of food, feed, and fiber. Perception of crops and weeds is a central component of agricultural robots that aim to monitor fields and assess the plants as well as their growth stage in an automatic manner. Semantic perception mostly relies on deep learning using supervised approaches, which require time and qualified workers to label fairly large amounts of data. In this paper, we look into the problem of reducing the amount of labels without compromising the final segmentation performance. For robots operating in the field, pre-training networks in a supervised way is already a popular method to reduce the number of required labeled images. We investigate the possibility of pre-training in a self-supervised fashion using data from the target domain. To better exploit this data, we propose a set of domain-specific augmentation strategies. We evaluate our pre-training on semantic segmentation and leaf instance segmentation, two important tasks in our domain. The experimental results suggest that pre-training with domain-specific data paired with our data augmentation strategy leads to superior performance compared to commonly used pre-trainings. Furthermore, the pre-trained networks obtain similar performance to the fully supervised with less labeled data.

Cedric Le Gentil, Leonardo Brizi, Daniil Lisus et al.

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.

Simone Ferrari, Luca Di Giammarino, Leonardo Brizi et al.

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.

Mirco Colosi, Irvin Aloise, Tiziano Guadagnino et al.

Nowadays, SLAM (Simultaneous Localization and Mapping) is considered by the Robotics community to be a mature field. Currently, there are many open-source systems that are able to deliver fast and accurate estimation in typical real-world scenarios. Still, all these systems often provide an ad-hoc implementation that entailed to predefined sensor configurations. In this work, we tackle this issue, proposing a novel SLAM architecture specifically designed to address heterogeneous sensors' configuration and to standardize SLAM solutions. Thanks to its modularity and to specific design patterns, the presented architecture is easy to extend, enhancing code reuse and efficiency. Finally, adopting our solution, we conducted comparative experiments for a variety of sensor configurations, showing competitive results that confirm state-of-the-art performance.

Giorgio Grisetti, Tiziano Guadagnino, Irvin Aloise et al.

Nowadays, Non-Linear Least-Squares embodies the foundation of many Robotics and Computer Vision systems. The research community deeply investigated this topic in the last years, and this resulted in the development of several open-source solvers to approach constantly increasing classes of problems. In this work, we propose a unified methodology to design and develop efficient Least-Squares Optimization algorithms, focusing on the structures and patterns of each specific domain. Furthermore, we present a novel open-source optimization system, that addresses transparently problems with a different structure and designed to be easy to extend. The system is written in modern C++ and can run efficiently on embedded systems. Source code: https://srrg.gitlab.io/srrg2-solver.html. We validated our approach by conducting comparative experiments on several problems using standard datasets. The results show that our system achieves state-of-the-art performances in all tested scenarios.

Ciro Potena, Bartolomeo Della Corte, Daniele Nardi et al.

In this paper, we present a novel solution for real-time, Non-Linear Model Predictive Control (NMPC) exploiting a time-mesh refinement strategy. The proposed controller formulates the Optimal Control Problem (OCP) in terms of flat outputs over an adaptive lattice. In common approximated OCP solutions, the number of discretization points composing the lattice represents a critical upper bound for real-time applications. The proposed NMPC-based technique refines the initially uniform time horizon by adding time steps with a sampling criterion that aims to reduce the discretization error. This enables a higher accuracy in the initial part of the receding horizon, which is more relevant to NMPC, while keeping bounded the number of discretization points. By combining this feature with an efficient Least Square formulation, our solver is also extremely time-efficient, generating trajectories of multiple seconds within only a few milliseconds. The performance of the proposed approach has been validated in a high fidelity simulation environment, by using an UAV platform. We also released our implementation as open source C++ code.

Dominik Schlegel, Giorgio Grisetti

Reliable and efficient Visual Place Recognition is a major building block of modern SLAM systems. Leveraging on our prior work, in this paper we present a Hamming Distance embedding Binary Search Tree (HBST) approach for binary Descriptor Matching and Image Retrieval. HBST allows for descriptor Search and Insertion in logarithmic time by exploiting particular properties of binary Feature descriptors. We support the idea behind our search structure with a thorough analysis on the exploited descriptor properties and their effects on completeness and complexity of search and insertion. To validate our claims we conducted comparative experiments for HBST and several state-of-the-art methods on a broad range of publicly available datasets. HBST is available as a compact open-source C++ header-only library.

Dominik Schlegel, Mirco Colosi, Giorgio Grisetti

In this paper we present ProSLAM, a lightweight stereo visual SLAM system designed with simplicity in mind. Our work stems from the experience gathered by the authors while teaching SLAM to students and aims at providing a highly modular system that can be easily implemented and understood. Rather than focusing on the well known mathematical aspects of Stereo Visual SLAM, in this work we highlight the data structures and the algorithmic aspects that one needs to tackle during the design of such a system. We implemented ProSLAM using the C++ programming language in combination with a minimal set of well known used external libraries. In addition to an open source implementation, we provide several code snippets that address the core aspects of our approach directly in this paper. The results of a thorough validation performed on standard benchmark datasets show that our approach achieves accuracy comparable to state of the art methods, while requiring substantially less computational resources.

Bartolomeo Della Corte, Igor Bogoslavskyi, Cyrill Stachniss et al.

The ability to build maps is a key functionality for the majority of mobile robots. A central ingredient to most mapping systems is the registration or alignment of the recorded sensor data. In this paper, we present a general methodology for photometric registration that can deal with multiple different cues. We provide examples for registering RGBD as well as 3D LIDAR data. In contrast to popular point cloud registration approaches such as ICP our method does not rely on explicit data association and exploits multiple modalities such as raw range and image data streams. Color, depth, and normal information are handled in an uniform manner and the registration is obtained by minimizing the pixel-wise difference between two multi-channel images. We developed a flexible and general framework and implemented our approach inside that framework. We also released our implementation as open source C++ code. The experiments show that our approach allows for an accurate registration of the sensor data without requiring an explicit data association or model-specific adaptations to datasets or sensors. Our approach exploits the different cues in a natural and consistent way and the registration can be done at framerate for a typical range or imaging sensor.

Leonardo Brizi, Emanuele Giacomini, Luca Di Giammarino et al.

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.

Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti et al.

LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times. In this work, we build on recent advancements in Gaussian Splatting methods to develop a novel LiDAR odometry and mapping pipeline that exclusively relies on Gaussian primitives for its scene representation. Leveraging spherical projection, we drive the refinement of the primitives uniquely from LiDAR measurements. Experiments show that our approach matches the current registration performance, while achieving SOTA results for mapping tasks with minimal GPU requirements. This efficiency makes it a strong candidate for further exploration and potential adoption in real-time robotics estimation tasks.

Luca Di Giammarino, Irvin Aloise, Cyrill Stachniss et al.

Robots and autonomous systems need to know where they are within a map to navigate effectively. Thus, simultaneous localization and mapping or SLAM is a common building block of robot navigation systems. When building a map via a SLAM system, robots need to re-recognize places to find loop closure and reduce the odometry drift. Image-based place recognition received a lot of attention in computer vision, and in this work, we investigate how such approaches can be used for 3D LiDAR data. Recent LiDAR sensors produce high-resolution 3D scans in combination with comparably stable intensity measurements. Through a cylindrical projection, we can turn this information into a panoramic image. As a result, we can apply techniques from visual place recognition to LiDAR intensity data. The question of how well this approach works in practice has not been answered so far. This paper provides an analysis of how such visual techniques can be with LiDAR data, and we provide an evaluation on different datasets. Our results suggest that this form of place recognition is possible and an effective means for determining loop closures.

Dominik Schlegel, Giorgio Grisetti

In this paper we propose an approach to embed continuous and selector cues in binary feature descriptors used for visual place recognition. The embedding is achieved by extending each feature descriptor with a binary string that encodes a cue and supports the Hamming distance metric. Augmenting the descriptors in such a way has the advantage of being transparent to the procedure used to compare them. We present two concrete applications of our methodology, demonstrating the two considered types of cues. In addition to that, we conducted on these applications a broad quantitative and comparative evaluation covering five benchmark datasets and several state-of-the-art image retrieval approaches in combination with various binary descriptor types.

Irvin Aloise, Giorgio Grisetti

Pose-Graph optimization is a crucial component of many modern SLAM systems. Most prominent state of the art systems address this problem by iterative non-linear least squares. Both number of iterations and convergence basin of these approaches depend on the error functions used to describe the problem. The smoother and more convex the error function with respect to perturbations of the state variables, the better the least-squares solver will perform. In this paper we propose an alternative error function obtained by removing some non-linearities from the standard used one - i.e. the geodesic error function. Comparative experiments conducted on common benchmarking datasets confirm that our function is more robust to noise that affects the rotational component of the pose measurements and, thus, exhibits a larger convergence basin than the geodesic. Furthermore, its implementation is relatively easy compared to the geodesic distance. This property leads to rather simple derivatives and nice numerical properties of the Jacobians resulting from the effective computation of the quadratic approximation used by Gauss-Newton algorithm.

Marco Imperoli, Ciro Potena, Daniele Nardi et al.

The self-localization capability is a crucial component for Unmanned Ground Vehicles (UGV) in farming applications. Approaches based solely on visual cues or on low-cost GPS are easily prone to fail in such scenarios. In this paper, we present a robust and accurate 3D global pose estimation framework, designed to take full advantage of heterogeneous sensory data. By modeling the pose estimation problem as a pose graph optimization, our approach simultaneously mitigates the cumulative drift introduced by motion estimation systems (wheel odometry, visual odometry, ...), and the noise introduced by raw GPS readings. Along with a suitable motion model, our system also integrates two additional types of constraints: (i) a Digital Elevation Model and (ii) a Markov Random Field assumption. We demonstrate how using these additional cues substantially reduces the error along the altitude axis and, moreover, how this benefit spreads to the other components of the state. We report exhaustive experiments combining several sensor setups, showing accuracy improvements ranging from 37% to 76% with respect to the exclusive use of a GPS sensor. We show that our approach provides accurate results even if the GPS unexpectedly changes positioning mode. The code of our system along with the acquired datasets are released with this paper.

Maurilio Di Cicco, Ciro Potena, Giorgio Grisetti et al.

Selective weeding is one of the key challenges in the field of agriculture robotics. To accomplish this task, a farm robot should be able to accurately detect plants and to distinguish them between crop and weeds. Most of the promising state-of-the-art approaches make use of appearance-based models trained on large annotated datasets. Unfortunately, creating large agricultural datasets with pixel-level annotations is an extremely time consuming task, actually penalizing the usage of data-driven techniques. In this paper, we face this problem by proposing a novel and effective approach that aims to dramatically minimize the human intervention needed to train the detection and classification algorithms. The idea is to procedurally generate large synthetic training datasets randomizing the key features of the target environment (i.e., crop and weed species, type of soil, light conditions). More specifically, by tuning these model parameters, and exploiting a few real-world textures, it is possible to render a large amount of realistic views of an artificial agricultural scenario with no effort. The generated data can be directly used to train the model or to supplement real-world images. We validate the proposed methodology by using as testbed a modern deep learning based image segmentation architecture. We compare the classification results obtained using both real and synthetic images as training data. The reported results confirm the effectiveness and the potentiality of our approach.

Roberto Capobianco, Jacopo Serafin, Johann Dichtl et al.

Semantic mapping is the incremental process of "mapping" relevant information of the world (i.e., spatial information, temporal events, agents and actions) to a formal description supported by a reasoning engine. Current research focuses on learning the semantic of environments based on their spatial location, geometry and appearance. Many methods to tackle this problem have been proposed, but the lack of a uniform representation, as well as standard benchmarking suites, prevents their direct comparison. In this paper, we propose a standardization in the representation of semantic maps, by defining an easily extensible formalism to be used on top of metric maps of the environments. Based on this, we describe the procedure to build a dataset (based on real sensor data) for benchmarking semantic mapping techniques, also hypothesizing some possible evaluation metrics. Nevertheless, by providing a tool for the construction of a semantic map ground truth, we aim at the contribution of the scientific community in acquiring data for populating the dataset.