Francesco Verdoja

Iacopo Catalano, Francesco Verdoja, Javier Civera et al.

3D Scene Graphs (3DSGs) provide hierarchical, multi-resolution abstractions that encode the geometric and semantic structure of an environment, yet their treatment of dynamics remains limited to tracking individual agents. Maps of Dynamics (MoDs) complement this by modeling aggregate motion patterns, but rely on uniform grid discretizations that lack semantic grounding and scale poorly. We present Rheos, a framework that explicitly embeds continuous directional motion models into an additional dynamics layer of a hierarchical 3DSG that enhances the navigational properties of the graph. Each dynamics node maintains a semi-wrapped Gaussian mixture model that captures multimodal directional flow as a principled probability distribution with explicit uncertainty, replacing the discrete histograms used in prior work. To enable online operation, Rheos employs reservoir sampling for bounded-memory observation buffers, parallel per-cell model updates and a principled Bayesian Information Criterion (BIC) sweep that selects the optimal number of mixture components, reducing per-update initialization cost from quadratic to linear in the number of samples. Evaluated across four spatial resolutions in a simulated pedestrian environment, Rheos consistently outperforms the discrete baseline under continuous as well as unfavorable discrete metrics. We release our implementation as open source.

Francesco Verdoja, Tomasz Piotr Kucner, Ville Kyrki

Mapping people dynamics is a crucial skill for robots, because it enables them to coexist in human-inhabited environments. However, learning a model of people dynamics is a time consuming process which requires observation of large amount of people moving in an environment. Moreover, approaches for mapping dynamics are unable to transfer the learned models across environments: each model is only able to describe the dynamics of the environment it has been built in. However, the impact of architectural geometry on people's movement can be used to anticipate their patterns of dynamics, and recent work has looked into learning maps of dynamics from occupancy. So far however, approaches based on trajectories and those based on geometry have not been combined. In this work we propose a novel Bayesian approach to learn people dynamics able to combine knowledge about the environment geometry with observations from human trajectories. An occupancy-based deep prior is used to build an initial transition model without requiring any observations of pedestrian; the model is then updated when observations become available using Bayesian inference. We demonstrate the ability of our model to increase data efficiency and to generalize across real large-scale environments, which is unprecedented for maps of dynamics.

Shivam Chaubey, Francesco Verdoja, Shankar Deka et al.

Shared control combines human intention with autonomous decision-making. At the low level, the primary goal is to maintain safety regardless of the user's input to the system. However, existing shared control methods-based on, e.g., Model Predictive Control, Control Barrier Functions, or learning-based control-often face challenges with feasibility, scalability, and mixed constraints. To address these challenges, we propose a Constraint-Aware Assistive Controller that computes control actions online while ensuring recursive feasibility, strict constraint satisfaction, and minimal deviation from the user's intent. It also accommodates a structured class of non-convex constraints common in real-world settings. We leverage Robust Controlled Invariant Sets for recursive feasibility and a Mixed-Integer Quadratic Programming formulation to handle non-convex constraints. We validate the approach through a large-scale user study with 66 participants-one of the most extensive in shared control research-using a simulated environment to assess task load, trust, and perceived control, in addition to performance. The results show consistent improvements across all these aspects without compromising safety and user intent. Additionally, a real-world experiment on a robotic manipulator demonstrates the framework's applicability under bounded disturbances, ensuring safety and collision-free operation.

Jens Lundell, Enric Corona, Tran Nguyen Le et al.

While there exists many methods for manipulating rigid objects with parallel-jaw grippers, grasping with multi-finger robotic hands remains a quite unexplored research topic. Reasoning and planning collision-free trajectories on the additional degrees of freedom of several fingers represents an important challenge that, so far, involves computationally costly and slow processes. In this work, we present Multi-FinGAN, a fast generative multi-finger grasp sampling method that synthesizes high quality grasps directly from RGB-D images in about a second. We achieve this by training in an end-to-end fashion a coarse-to-fine model composed of a classification network that distinguishes grasp types according to a specific taxonomy and a refinement network that produces refined grasp poses and joint angles. We experimentally validate and benchmark our method against a standard grasp-sampling method on 790 grasps in simulation and 20 grasps on a real Franka Emika Panda. All experimental results using our method show consistent improvements both in terms of grasp quality metrics and grasp success rate. Remarkably, our approach is up to 20-30 times faster than the baseline, a significant improvement that opens the door to feedback-based grasp re-planning and task informative grasping. Code is available at https://irobotics.aalto.fi/multi-fingan/.

Yuying Zhang, Kevin Sebastian Luck, Francesco Verdoja et al.

Mobile manipulation is a critical capability for robots operating in diverse, real-world environments. However, manipulating deformable objects and materials remains a major challenge for existing robot learning algorithms. While various benchmarks have been proposed to evaluate manipulation strategies with rigid objects, there is still a notable lack of standardized benchmarks that address mobile manipulation tasks involving deformable objects. To address this gap, we introduce MoDeSuite, the first Mobile Manipulation Deformable Object task suite, designed specifically for robot learning. MoDeSuite consists of eight distinct mobile manipulation tasks covering both elastic objects and deformable objects, each presenting a unique challenge inspired by real-world robot applications. Success in these tasks requires effective collaboration between the robot's base and manipulator, as well as the ability to exploit the deformability of the objects. To evaluate and demonstrate the use of the proposed benchmark, we train two state-of-the-art reinforcement learning algorithms and two imitation learning algorithms, highlighting the difficulties encountered and showing their performance in simulation. Furthermore, we demonstrate the practical relevance of the suite by deploying the trained policies directly into the real world with the Spot robot, showcasing the potential for sim-to-real transfer. We expect that MoDeSuite will open a novel research domain in mobile manipulation involving deformable objects. Find more details, code, and videos at https://sites.google.com/view/modesuite/home.

Jouko Kinnari, Francesco Verdoja, Ville Kyrki

Localization without Global Navigation Satellite Systems (GNSS) is a critical functionality in autonomous operations of unmanned aerial vehicles (UAVs). Vision-based localization on a known map can be an effective solution, but it is burdened by two main problems: places have different appearance depending on weather and season, and the perspective discrepancy between the UAV camera image and the map make matching hard. In this work, we propose a localization solution relying on matching of UAV camera images to georeferenced orthophotos with a trained convolutional neural network model that is invariant to significant seasonal appearance difference (winter-summer) between the camera image and map. We compare the convergence speed and localization accuracy of our solution to six reference methods. The results show major improvements with respect to reference methods, especially under high seasonal variation. We finally demonstrate the ability of the method to successfully localize a real UAV, showing that the proposed method is robust to perspective changes.

Jouko Kinnari, Francesco Verdoja, Ville Kyrki

Localization of low-cost Unmanned Aerial Vehicles (UAVs) often relies on Global Navigation Satellite Systems (GNSS). GNSS are susceptible to both natural disruptions to radio signal and intentional jamming and spoofing by an adversary. A typical way to provide georeferenced localization without GNSS for small UAVs is to have a downward-facing camera and match camera images to a map. The downward-facing camera adds cost, size, and weight to the UAV platform and the orientation limits its usability for other purposes. In this work, we propose a Monte-Carlo localization method for georeferenced localization of an UAV requiring no infrastructure using only inertial measurements, a camera facing an arbitrary direction, and an orthoimage map. We perform orthorectification of the UAV image, relying on a local planarity assumption of the environment, relaxing the requirement of downward-pointing camera. We propose a measure of goodness for the matching score of an orthorectified UAV image and a map. We demonstrate that the system is able to localize globally an UAV with modest requirements for initialization and map resolution.

Krishnananda Prabhu Sivananda, Francesco Verdoja, Ville Kyrki

While 2D occupancy maps commonly used in mobile robotics enable safe navigation in indoor environments, in order for robots to understand and interact with their environment and its inhabitants representing 3D geometry and semantic environment information is required. Semantic information is crucial in effective interpretation of the meanings humans attribute to different parts of a space, while 3D geometry is important for safety and high-level understanding. We propose a pipeline that can generate a multi-layer representation of indoor environments for robotic applications. The proposed representation includes 3D metric-semantic layers, a 2D occupancy layer, and an object instance layer where known objects are replaced with an approximate model obtained through a novel model-matching approach. The metric-semantic layer and the object instance layer are combined to form an augmented representation of the environment. Experiments show that the proposed shape matching method outperforms a state-of-the-art deep learning method when tasked to complete unseen parts of objects in the scene. The pipeline performance translates well from simulation to real world as shown by F1-score analysis, with semantic segmentation accuracy using Mask R-CNN acting as the major bottleneck. Finally, we also demonstrate on a real robotic platform how the multi-layer map can be used to improve navigation safety.

Jens Lundell, Francesco Verdoja, Ville Kyrki

Recent advances in multi-fingered robotic grasping have enabled fast 6-Degrees-Of-Freedom (DOF) single object grasping. Multi-finger grasping in cluttered scenes, on the other hand, remains mostly unexplored due to the added difficulty of reasoning over obstacles which greatly increases the computational time to generate high-quality collision-free grasps. In this work we address such limitations by introducing DDGC, a fast generative multi-finger grasp sampling method that can generate high quality grasps in cluttered scenes from a single RGB-D image. DDGC is built as a network that encodes scene information to produce coarse-to-fine collision-free grasp poses and configurations. We experimentally benchmark DDGC against the simulated-annealing planner in GraspIt! on 1200 simulated cluttered scenes and 7 real world scenes. The results show that DDGC outperforms the baseline on synthesizing high-quality grasps and removing clutter while being 5 times faster. This, in turn, opens up the door for using multi-finger grasps in practical applications which has so far been limited due to the excessive computation time needed by other methods.

Nils Dengler, Tobias Zaenker, Francesco Verdoja et al.

Creating and maintaining an accurate representation of the environment is an essential capability for every service robot. Especially for household robots acting in indoor environments, semantic information is important. In this paper, we present a semantic mapping framework with modular map representations. Our system is capable of online mapping and object updating given object detections from RGB-D data and provides various 2D and 3D~representations of the mapped objects. To undo wrong data associations, we perform a refinement step when updating object shapes. Furthermore, we maintain an existence likelihood for each object to deal with false positive and false negative detections and keep the map updated. Our mapping system is highly efficient and achieves a run time of more than 10 Hz. We evaluated our approach in various environments using two different robots, i.e., a Toyota HSR and a Fraunhofer Care-O-Bot-4. As the experimental results demonstrate, our system is able to generate maps that are close to the ground truth and outperforms an existing approach in terms of intersection over union, different distance metrics, and the number of correct object mappings

Tran Nguyen Le, Francesco Verdoja, Fares J. Abu-Dakka et al.

Accurately modeling local surface properties of objects is crucial to many robotic applications, from grasping to material recognition. Surface properties like friction are however difficult to estimate, as visual observation of the object does not convey enough information over these properties. In contrast, haptic exploration is time consuming as it only provides information relevant to the explored parts of the object. In this work, we propose a joint visuo-haptic object model that enables the estimation of surface friction coefficient over an entire object by exploiting the correlation of visual and haptic information, together with a limited haptic exploration by a robotic arm. We demonstrate the validity of the proposed method by showing its ability to estimate varying friction coefficients on a range of real multi-material objects. Furthermore, we illustrate how the estimated friction coefficients can improve grasping success rate by guiding a grasp planner toward high friction areas.

Francesco Verdoja, Ville Kyrki

Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness. However the quality of the uncertainty estimated through this method varies and choices in architecture design and in training procedures have to be carefully considered and tested to obtain satisfactory results. In this paper we present a study offering a different point of view on the behavior of Monte-Carlo dropout, which enables us to observe a few interesting properties of the technique to keep in mind when considering its use for uncertainty estimation.

Francesco Verdoja, Ville Kyrki

The most common way for robots to handle environmental information is by using maps. At present, each kind of data is hosted on a separate map, which complicates planning because a robot attempting to perform a task needs to access and process information from many different maps. Also, most often correlation among the information contained in maps obtained from different sources is not evaluated or exploited. In this paper, we argue that in robotics a shift from single-source maps to a multi-layer mapping formalism has the potential to revolutionize the way robots interact with knowledge about their environment. This observation stems from the raise in metric-semantic mapping research, but expands to include in its formulation also layers containing other information sources, e.g., people flow, room semantic, or environment topology. Such multi-layer maps, here named hypermaps, not only can ease processing spatial data information but they can bring added benefits arising from the interaction between maps. We imagine that a new research direction grounded in such multi-layer mapping formalism for robots can use artificial intelligence to process the information it stores to present to the robot task-specific information simplifying planning and bringing us one step closer to high-level reasoning in robots.

Tobias Zaenker, Francesco Verdoja, Ville Kyrki

Modern intelligent and autonomous robotic applications often require robots to have more information about their environment than that provided by traditional occupancy grid maps. For example, a robot tasked to perform autonomous semantic exploration has to label objects in the environment it is traversing while autonomously navigating. To solve this task the robot needs to at least maintain an occupancy map of the environment for navigation, an exploration map keeping track of which areas have already been visited, and a semantic map where locations and labels of objects in the environment are recorded. As the number of maps required grows, an application has to know and handle different map representations, which can be a burden. We present the Hypermap framework, which can manage multiple maps of different types. In this work, we explore the capabilities of the framework to handle occupancy grid layers and semantic polygonal layers, but the framework can be extended with new layer types in the future. Additionally, we present an algorithm to automatically generate semantic layers from RGB-D images. We demonstrate the utility of the framework using the example of autonomous exploration for semantic mapping.

Jens Lundell, Francesco Verdoja, Ville Kyrki

Current end-to-end grasp planning methods propose grasps in the order of seconds that attain high grasp success rates on a diverse set of objects, but often by constraining the workspace to top-grasps. In this work, we present a method that allows end-to-end top-grasp planning methods to generate full six-degree-of-freedom grasps using a single RGB-D view as input. This is achieved by estimating the complete shape of the object to be grasped, then simulating different viewpoints of the object, passing the simulated viewpoints to an end-to-end grasp generation method, and finally executing the overall best grasp. The method was experimentally validated on a Franka Emika Panda by comparing 429 grasps generated by the state-of-the-art Fully Convolutional Grasp Quality CNN, both on simulated and real camera images. The results show statistically significant improvements in terms of grasp success rate when using simulated images over real camera images, especially when the real camera viewpoint is angled. Code and video are available at https://irobotics.aalto.fi/beyond-top-grasps-through-scene-completion/.

Jens Lundell, Francesco Verdoja, Ville Kyrki

We present a method for planning robust grasps over uncertain shape completed objects. For shape completion, a deep neural network is trained to take a partial view of the object as input and outputs the completed shape as a voxel grid. The key part of the network is dropout layers which are enabled not only during training but also at run-time to generate a set of shape samples representing the shape uncertainty through Monte Carlo sampling. Given the set of shape completed objects, we generate grasp candidates on the mean object shape but evaluate them based on their joint performance in terms of analytical grasp metrics on all the shape candidates. We experimentally validate and benchmark our method against another state-of-the-art method with a Barrett hand on 90000 grasps in simulation and 200 grasps on a real Franka Emika Panda. All experimental results show statistically significant improvements both in terms of grasp quality metrics and grasp success rate, demonstrating that planning shape-uncertainty-aware grasps brings significant advantages over solely planning on a single shape estimate, especially when dealing with complex or unknown objects.

Francesco Verdoja, Jens Lundell, Ville Kyrki

Most mobile robots for indoor use rely on 2D laser scanners for localization, mapping and navigation. These sensors, however, cannot detect transparent surfaces or measure the full occupancy of complex objects such as tables. Deep Neural Networks have recently been proposed to overcome this limitation by learning to estimate object occupancy. These estimates are nevertheless subject to uncertainty, making the evaluation of their confidence an important issue for these measures to be useful for autonomous navigation and mapping. In this work we approach the problem from two sides. First we discuss uncertainty estimation in deep models, proposing a solution based on a fully convolutional neural network. The proposed architecture is not restricted by the assumption that the uncertainty follows a Gaussian model, as in the case of many popular solutions for deep model uncertainty estimation, such as Monte-Carlo Dropout. We present results showing that uncertainty over obstacle distances is actually better modeled with a Laplace distribution. Then, we propose a novel approach to build maps based on Deep Neural Network uncertainty models. In particular, we present an algorithm to build a map that includes information over obstacle distance estimates while taking into account the level of uncertainty in each estimate. We show how the constructed map can be used to increase global navigation safety by planning trajectories which avoid areas of high uncertainty, enabling higher autonomy for mobile robots in indoor settings.

Jens Lundell, Francesco Verdoja, Ville Kyrki

Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring. In this work, instead of estimating the distance to obstacles from richer sensor readings such as 3D lasers or RGBD sensors, we present a method to estimate the distance directly from raw 2D laser data. To learn a mapping from raw 2D laser distances to obstacle distances we frame the problem as a learning task and train a neural network formed as an autoencoder. A novel configuration of network hyperparameters is proposed for the task at hand and is quantitatively validated on a test set. Finally, we qualitatively demonstrate in real time on a Care-O-bot 4 that the trained network can successfully infer obstacle distances from partial 2D laser readings.

Francesco Verdoja, Marco Grangetto

Reed-Xiaoli detector (RXD) is recognized as the benchmark algorithm for image anomaly detection; however, it presents known limitations, namely the dependence over the image following a multivariate Gaussian model, the estimation and inversion of a high-dimensional covariance matrix, and the inability to effectively include spatial awareness in its evaluation. In this work, a novel graph-based solution to the image anomaly detection problem is proposed; leveraging the graph Fourier transform, we are able to overcome some of RXD's limitations while reducing computational cost at the same time. Tests over both hyperspectral and medical images, using both synthetic and real anomalies, prove the proposed technique is able to obtain significant gains over performance by other algorithms in the state of the art.