• Jacopo Serafin, and Giorgio Grisetti. Using Extended Measurements and Scene Merging for Efficient and Robust Point Cloud Registration. Robotics and Autonomous Systems (RAS), vol. 92, pp. 91-106, 2017.

    Abstract. Point cloud registration is a fundamental building block of many robotic applications. In this paper we describe a system to solve the registration problem, that
    builds on top of our previous work, and that represents an extension to the well known Iterative Closest Point (ICP) algorithm. Our approach combines recent achievements on optimization by using an extended point representation that captures the surface characteristics around the points. Thanks to an effective strategy to search for correspondences, our method can operate on-line and cope with measurements gathered with an heterogeneous set of range and depth sensors. By using an efficient map-merging procedure our approach can quickly update the tracked scene and handle dynamic aspects. We also introduce an approximated variant of our method that runs at twice the speed of our full implementation. Experiments performed on a large publicly available benchmarking dataset show that our approach performs better with respect to other state-of-the art methods. In most of the tests considered, our algorithm has been able to obtain a translational and rotational relative error of respectively ∼1 cm and ∼1 degree. [pdf] [code]


  • Jacopo Serafin, Edwin Olson and Giorgio Grisetti. Fast and Robust 3D Feature Extraction from Sparse Point Clouds. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Daejeon, Korea, pp. 4105-4112, 2016.

    Abstract. Matching 3D point clouds, a critical operation in map building and localization, is difficult with Velodyne-type sensors due to the sparse and non-uniform point clouds that they produce. Standard methods from dense 3D point clouds are generally not effective. In this paper, we describe a feature-based approach using Principal Components Analysis (PCA) of neighborhoods of points, which results in mathematically principled line and plane features. The key contribution in this work is to show how this type of feature extraction can be done efficiently and robustly even on non-uniformly sampled point clouds. The resulting detector runs in real-time and can be easily tuned to have a low false positive rate, simplifying data association. We evaluate the performance of our algorithm on an autonomous car at the MCity Test Facility using a Velodyne HDL-32E. [pdf] [code]

  • Robert Goeddel, Carl Kershaw, Jacopo Serafin and Edwin Olson. FLAT2D: Fast Localization from Approximate Transformation into 2D. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Daejeon, Korea, pp. 1932-1939, 2016.

    Abstract. Autonomous vehicles require precise localization to support safe and reliable operation. Current systems aim to localize in 6DOF based on observations from a combination of cameras and 3D LiDAR, matching against dense, 3D prior maps. These maps are quite large and complex, presenting both computational and physical challenges in terms of matching, storage, and retrieval. Most of the environments where vehicles operate in contain frequent and distinct vertical structure sufficient for 2D localization, while state-of-the-art IMUs can be used to recover roll and pitch. In this paper, we introduce a fast method for constructing 2D maps summarizing the vertical structure in the environment and demonstrate that it can be used to localize accurately in vehicular and other applications. We also introduce a variation of Graph-SLAM tailored to support localization, allowing us to make use of max mixture representations in our localization estimate. Finally, we present real-world localization results for both an indoor mobile robotic platform and an autonomous golf cart, demonstrating that autonomous vehicles do not need full 3D matching to accurately localize in the environment. [pdf]


  • Jacopo Serafin and Giorgio Grisetti. NICP: Dense Normal Based Point Cloud Registration. In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Hamburg, Germany, pp. 742-749, 2015.

    Abstract. In this paper we present a novel on-line method to recursively align point clouds. By considering each point together with the local features of the surface (normal and curvature), our method takes advantage of the 3D structure around the points for the determination of the data association between two clouds. The algorithm relies on a least squares formulation of the alignment problem, that minimizes an error metric depending on these surface characteristics. We named the approach Normal Iterative Closest Point (NICP in short). Extensive experiments on publicly available benchmark data show that NICP outperforms other state-of-the-art approaches. [pdf] [link] [code]

  • Roberto Capobianco, Jacopo Serafin, Johann Dichtl, Giorgio Grisetti, Luca Iocchi and Daniele Nardi. A Proposal for Semantic Map Representation and Evaluation. In Proc. of the European Conference on Mobile Robots (ECMR), Lincoln, United Kingdom, pp. 1-6, 2015.

    Abstract. 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. [pdf] [link]


  • Jacopo Serafin and Giorgio Grisetti. Using Augmented Measurements to Improve the Convergence of ICP. In Proc. of the Int. Conf. on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR), Springer, Bergamo, Italy, pp. 566-577, 2014.

    Abstract. Point cloud registration is an essential part for many robotics applications and this problem is usually addressed using some of the existing variants of the Iterative Closest Point (ICP) algorithm. In this paper we propose a novel variant of the ICP objective function which is minimized while searching for the registration. We show how this new function, which relies not only on the point distance, but also on the difference between surface normals or surface tangents, improves the registration process. Experiments are performed on synthetic data and real standard benchmark datasets, showing that our approach outperforms other state of the art techniques in terms of convergence speed and robustness. [pdf] [link] [code]


  •  V. A. Ziparo, M. Zaratti, G. Grisetti, T. Bonanni, J. Serafin, M. Di Cicco, M. Proesmans, L. van Gool, O. Vysotska, I. Bogoslavskyi and C. Stachniss. Exploration and Mapping of Catacombs with Mobile Robots. In IEEE Int. Symposium on Safety, Security, and Rescue Robotics (SSRR), Linköping, Sweden, pp. 1-2, 2013.

    Abstract. The conservation of archeological sites and historical buildings is an important goal for both, scientists as well as the general public. Accurate models of such sites is often a prerequisite for conservation, maintenance, restoration, security, and other tasks. Recent technological advancements in information and communication technology as well as artificial intelligence and robotics have the potential to develop valuable tools for mapping and digitally preserving archeological sites. In this work, we focus on archeological sites that are difficult to access by humans, such as catacombs or similar underground sites. These environments are often not open to public because they are not safe and operation within them is difficult and sometimes even hazardous. Therefore, the application of standard digitization techniques, such as static 3D laser scanners operated by humans, is often not feasible. On the other hand, mapping and digitizing such sites is important for both, enlarging their fruition and for maintenance tasks. In these environments, autonomous mobile robots offer a great potential to support these tasks. Our goal is to develop autonomous mobile robots for mapping archeological sites that are difficult or dangerous to access for humans. [pdf] [link]
  • Igor Bogoslavskyi, Olga Vysotska, Jacopo Serafin, Giorgio Grisetti and Cyrill Stachniss. Efficient Traversability Analysis for Mobile Robots using the Kinect Sensor. In Proc. of the European Conference on Mobile Robots (ECMR), Barcelona, Spain, pp. 158-163, 2013.

    Abstract. For autonomous robots, the ability to classify their local surroundings into traversable and non-traversable areas is crucial for navigation. In this paper, we address the problem of online traversability analysis for robots that are only equipped with a Kinect-style sensor. Our approach processes the depth data at 10 fps-25 fps on a standard notebook computer without using the GPU and allows for robustly identifying the areas in front of the sensor that are safe for navigation. The component presented here is one of the building blocks of the EU project ROVINA that aims at the exploration and digital preservation of hazardous archeological sites with mobile robots. Real world evaluations have been conducted in controlled lab environments, in an outdoor scene, as well as in a real, partially unexplored, and roughly 1700 year old Roman catacomb. [pdf]