J. Serafin, M. Di Cicco, T. M. Bonanni, G. Grisetti, L. Iocchi, D. Nardi, C. Stachniss and V. A. Ziparo
Robots for Exploration, Digital Preservation and Visualization of Archeological Sites
Artificial Intelligence for Cultural Heritage
2016
Monitoring and conservation of archaeological sites
are important activities necessary to prevent damage or to
perform restoration on cultural heritage. Standard techniques,
like mapping and digitizing, are typically used to document the
status of such sites. While these task are normally accomplished
manually by humans, this is not possible when dealing with
hard-to-access areas. For example, due to the possibility of
structural collapses, underground tunnels like catacombs are
considered highly unstable environments. Moreover, they are full
of radioactive gas radon that limits the presence of people only
for few minutes. The progress recently made in the artificial
intelligence and robotics field opened new possibilities for mobile
robots to be used in locations where humans are not allowed
to enter. The ROVINA project aims at developing autonomous
mobile robots to make faster, cheaper and safer the monitoring of
archaeological sites. ROVINA will be evaluated on the catacombs
of Priscilla (in Rome) and S. Gennaro (in Naples).
Daniel Perea Ström, Igor Bogoslavsky, Cyrill Stachniss
Robust Exploration and Homing for Autonomous Robots
In Press
2016
The ability to explore an unknown environment is an important prerequisite for building truly autonomous robots. Two central capabilities for autonomous exploration are the selection of the next view point(s) for gathering new observations and robust navigation. In this paper, we propose a novel exploration strategy that exploits background knowledge by considering previously seen environments to make better exploration decisions. We furthermore combine this approach with robust homing so that the robot can navigate back to its starting location even if the mapping system fails and does not produce a consistent map. We implemented the proposed approach in ROS and thoroughly evaluated it. The experiments indicate that our method improves the
ability of a robot to explore challenging environments as well as the quality of the resulting maps. Furthermore, the robot is able to navigate back home, even if it cannot rely on its map.
Maurilio Di Cicco, Bartolomeo Della Corte, Giorgio Grisetti
Unsupervised Calibration of Wheeled Mobile Platforms
Proceedings of the IEEE Int. Conf. on Robotics & Automation (ICRA)
2016
This paper describes an unsupervised approach to
retrieve the kinematic parameters of a wheeled mobile robot.
The robot chooses which action to take in order to minimize
the uncertainty in the parameter estimate and to fully explore
the parameter space.
Our method explores the effects of a set of elementary motion
on the platform to dynamically select the best action and to stop
the process when the estimate can be no further improved.
We tested our approach both in simulation and with real
robots. Our method is reported to obtain in shorter time
parameter estimates that are statistically more accurate than
the ones obtained by steering the robot on predefined patterns.
I. Bogoslavskyi, M. Mazuran, and C. Stachniss
Robust Homing for Autonomous Robots
Proceedings of the IEEE Int. Conf. on Robotics & Automation (ICRA)
2016
S. Osswald, M. Bennewitz, W. Burgard, and C. Stachniss
Speeding-Up Robot Exploration by Exploiting Background Information
IEEE Robotics and Automation Letters (RA-L)
2016
Maurilio Di Cicco, Luca Iocchi, Giorgio Grisetti
Non-Parametric Calibration for Depth Sensors
Robotics and Autonomous Systems
2015
RGBD sensors are commonly used in robotics applications for many purposes, including 3D reconstruction
of the environment and mapping. In these tasks, uncalibrated sensors can generate poor quality results. In
this article we propose a quick and easy to use approach to estimate the undistortion function of RGBD
sensors. Our approach does not rely on the knowledge of the sensor model, on the use of a specific calibration
pattern or on external SLAM systems to track the device position. We compute an extensive representation
of the undistortion function as well as its statistics and use machine learning methods for approximation of
the undistortion function. We validated our approach on datasets acquired from different kinds of RGBD
sensors and using a precise 3D ground truth. We also provide a procedure for evaluating the quality of the
calibration using a mobile robot and a 2D laser range finder. The results clearly show the advantages in
using sensor data calibrated with the method described in this article.
Jacopo Serafin and Giorgio Grisetti
NICP: Dense normal based point cloud registration
IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)
2015
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.
The ability to explore an unknown environment is an important
prerequisite for building truly autonomous robots. The central
decision that a robot needs to make when exploring an unknown
environment is to select the next view point(s) for gathering
observations. In this paper, we consider the problem of how to
select view points that support the underlying mapping process. We
propose a novel approach that makes predictions about the structure
of the environments in the unexplored areas by relying on maps
acquired previously. Our approach seeks to find similarities between
the current surroundings of the robot and previously acquired maps
stored in a database in order to predict how the environment may expand
in the unknown areas. This allows us to predict potential future
loop closures early. This knowledge is used in the view point selection to
actively close loops and in this way reduce the uncertainty in the
robot's belief. We implemented and tested the proposed
approach. The experiments indicate that our method improves the
ability of a robot to explore challenging environments and improves
the quality of the resulting maps.
Vittorio Amos Ziparo, Fabio Cottefoglie, Daniele Calisi, Francesca Giannone, Giorgio Grisetti, Bastian Leibe, Marc Proesmans, Paolo Salonia, Luc~Van Gool, Claudia Ventura, and Cyrill Stachniss
A New Approach to Digitalization and Data Management of Cultural Heritage Sites
International Congress on Digital Heritage - Theme 1 - Digitization And Acquisition. IEEE
2015
In this paper, we describe a novel approach for acquiring and managing digital models of archaeological sites. More in detail, we present an approach to digitization based on a robotic platform and a cloud-based information system. Our robot is the result of over two years of efforts by a group of cultural heritage experts, computer scientists and roboticists. Exploiting the large and heterogeneous amount data provided by the robotic platform requires this data to be managed, organized and analyzed. To this extent we developed ARIS (ARchaeological Information System), a software that exploits modern information retrieval and machine learning systems.
Stamatios Georgoulis, Vincent Vanweddingen, Marc Proesmans, Luc Van Gool
A Gaussian process latent variable model for BRDF inference
International conference on Computer Vision, ICCV
2015
The problem of estimating a full BRDF from partial observations has already been studied using either parametric or non-parametric approaches. The goal in each case is to best match this sparse set of input measurements. In this paper we address the problem of inferring higher order reflectance information starting from the minimal input of a single BRDF slice. We begin from the prototypical case of a homogeneous sphere, lit by a head-on light source, which only holds information about less than 0.001% of the whole BRDF domain. We propose a novel method to infer the higher dimensional properties of the
material’s BRDF, based on the statistical distribution of known material characteristics observed in real-life samples.
We evaluated our method based on a large set of experiments generated from real-world BRDFs and newly measured materials. Although inferring higher dimensional BRDFs from such modest training is not a trivial problem, our method performs better than state-of-the-art parametric, semi- parametric and non-parametric approaches. Finally, we discuss interesting applications on material relighting, and flash-based photography.
Stamatios Georgoulis, Marc Proesmans and Luc Van Gool
Tackling Shapes and BRDFs Head-on
International Conference on 3D Vision (3DV)
2014
In this work, we investigate the use of simple flashbased photography to capture an object’s 3D shape and reflectance characteristics at the same time. The presented method is based on the principles of Structure from Motion (SfM) and Photometric Stereo (PS), yet, we make sure not to use more than readily-available consumer equipment, like a camera with flash. Starting from a SfM-generated mesh, we apply PS to refine both geometry and reflectance,
where the latter is expressed in terms of data-driven Bidirectional Reflectance Distribution Function (BRDF) representations.
We also introduce a novel approach to infer complete BRDFs starting from the sparsely sampled datadrivenreflectance information captured with this setup.
Our approach is experimentally validated by modeling several challenging objects, both synthetic and real.
Vittorio Amos Ziparo, Giorgio Grisetti, Luca Iocchi, and Daniele Nardi.
Robots for the digitisation of hard-to-access cultural heritage sites.
Proc. of the Workshop on Artificial Intelligence for Cultural Heritage
2014
In this paper we provide a brief overview the ROVINA project2. ROVINA is a three-year and a half research project that is co-funded by the European Commission in the frame of the FP7 program. The University of Bonn (GE), University Freiburg (GE), University Aachen (GE), University Leuven (BE), Sapienza University of Rome (IT), Algorithmica Srl (IT) and the International Council of Monuments and Sites (IT) compose the ROVINA consortium. ROVINA aims at making surveying of cultural heritage sites faster, cheaper and safer through the use of autonomous robots that will enable 3D reconstructions at a completely new scale and quality. The ROVINA robots can autonomously explore archeological sites. The data collected during the exploration is stored into the Cloud and is used to deliver advanced analysis services for structural engineers, historians and preservation experts. As the models are extremely accurate and visually appealing, ROVINA has created an online museum for the general public that is build on top of a WebGL virtual site viewer.
Vittorio Amos Ziparo, Giordana Castelli, Luc Van Gool, Giorgio Grisetti, Bastian Leibe, Marc Proesmans, and Cyrill Stachniss.
A user perspective on the ROVINA project
Proc. of the 18th ICOMOS General Assembly and Scientific Symposium “Heritage and Landscape as
Human Values”
2014
ROVINA is a research project funded by the EC within FP7. ROVINA will provide tools for mapping and digitizing archeological sites - especially for difficult to access sites - to improve the preservation and dissemination of cultural heritage. Current systems often rely on static 3D lidar, traditional photogrammetry techniques, and are manually operated. This is expensive, time consuming, and can be even dangerous for the operators. ROVINA exploits the strong progress in robotics to efficiently survey hazardous areas and aims at making further progress in the reliability, accuracy, and autonomy of such systems.
T.M. Bonanni, G. Grisetti, L. Iocchi
Merging partially consistent maps
4th International Conference on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR)
2014
Learning maps from sensor data has been addressed since
more than two decades by Simultaneous Localization and Mapping
(SLAM) systems. Modern state-of-the-art SLAM approaches exhibit excellent
performances and are able to cope with environments having the
scale of a city. Usually these methods are entailed for on-line operation,
requiring the data to be acquired in a single run, which is not always
easy to obtain. To gather a single consistent map of a large environment
we therefore integrate data acquired in multiple runs. A possible
solution to this problem consists in merging different submaps. The literature
proposes several approaches for map merging, however very few
of them are able to operate with local maps affected by inconsistencies.
These methods seek to find the global arrangement of a set of rigid bodies,
that maximizes some overlapping criterion. In this paper, we present
an off-line technique for merging maps affected by residual errors into a
single consistent global map. Our method can be applied in combination
with existing map merging approaches, since it requires an initial guess
to operate. However, once this initial guess is provided, our method is
able to substantially lessen the residual error in the final map. We validated
our approach on both real world and simulated datasets to refine
solutions of traditional map merging approaches.
Jacopo Serafin and Giorgio Grisetti
Using Augmented Measurements to Improve the Convergence of ICP
4th International Conference on Simulation, Modeling and Programming for Autonomous Robots (SIMPAR)
2014
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 thedifference 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.
Giorgio Grisetti, Luca Iocchi, Daniele Nardi, and Vittorio Amos Ziparo
Robots for the digitisation of hard-to-access cultural heritage sites.
Proc. of the 2nd International Conference RICH 2014 - Robotics: Innovation for Cultural Heritage, 2014.
2014
Europe has a wealth of cultural heritage sites and, according to UNESCO, Italy is the country that has the largest number in Europe. The conservation of such sites is a very challenging task, as it requires periodical surveys, where teams of experts need to carry heavy equipment on the field.
In this extended abstract we provide a brief overview the EU-FP7 ROVINA project. ROVINA aims at making surveying of cultural heritage sites faster, cheaper and safer through the use of autonomous robots that will enable 3D reconstructions at a completely new scale and quality. The ROVINA robots can autonomously explore archeological sites. The data collected during the exploration is stored into the Cloud and is used to deliver advanced analysis services for structural engineers, historians and preservation experts. As the models are extremely accurate and visually appealing, ROVINA has created an online museum for the general public that is built on top of a WebGL virtual site viewer. The experimental evaluation of the ROVINA system will be performed in the S. Priscilla catacomb in Rome and the S. Gennaro catacomb in Naples selected by the International Council of Monuments and Sites as the most representative sites for this class of cultural heritage, both in terms of archeological impact and of robotic challenges.
F. Nenci, L. Spinello and C. Stachniss
Effective Compression of Range Data Streams for Remote Robot Operations using H.264
IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)
2014
Most robots need the ability to communicate with a base station or with an operator during their mission. Tele-operated and semi-autonomous robots typically communicate continuously through a network connection with an operator. Transmitting raw sensor data over a low bandwidth network such as wireless or HSDPA, however, is problematic as the stream of sensor data is often large. In this paper, we present a method that exploits H.264 compression to reduce the size of range data streams from sensors such as the Kinect camera or the Velodyne 3D laser scanner. We developed a practical and effective solution that exploits the state of the art in video compression to produce high-quality results. Our method is easy to implement and can have practical impact for researchers building robots for the real world. We implemented and thoroughly tested our approach using a large number of range data streams. Furthermore, we analyzed the impact of data compression on the accuracy and size of the transmitted data. We show that even a highly compressed stream of depth images can be used with dense mapping techniques such as KinFu for building environment models.
Alberto Pretto and Giorgio Grisetti
Calibration and performance evaluation of low-cost IMUs
Proc. of the 20th IMEKO TC4 International Symposium, pages 429 - 434
2014
IMUs (Inertial Measurement Units) are extensively used in many robotics applications such as navigation and mapping tasks. In almost all these systems,
inertial measurements are fused with data coming from other sensors (e.g., GPS sensors, range finders, cameras, . . . ). For better results, the IMU should
be carefully calibrated, in order to minimize the propagation of systematic errors. But what happens if for brief periods data coming from the other sensors are missing? Can we trust the IMU in these cases?
In this paper, we present a robust and simple method to calibrate an IMU without any external equipment. We then use the calibration results to analyze the behavior of two types of MEMS based IMUs employed as a single sensor in full 3D orientation and egomotion estimation tasks.
Lieve Watteeuw, Bruno Vandermeulen, Marc Proesmans
See the Surface. Imaging and measuring surface characteristics of medieval library materials by photometric stereo
Arts Digital Humanities Summer School,
Location: Leuven
2014
The RICH project is surveying the possibilities of RTI to detect material characteristics, decorative issues, damages, the effects of old and recent restoration- and conservation treatments on graphic materials: paper, leather, wood, textiles and parchment. The technique is based on polynomial texture mapping, also known as Reflectance Transformation Imaging (RTI), a technique of imaging and interactively displaying objects under varying lighting conditions to reveal surface phenomena. The underlying processing is based on the extraction of surface characteristics using methodologies such as photometric stereo and BRDF analysis (Bidirectional Reflectance Distribution Function). The imaging module is a hemispherical structure dotted on the inside with 260 LED-lamps and a single downward looking video camera (28 million pixels). The RICH mini-dome is specifically adapted to document fragile documentary heritage but can also be used for other materials. After processing the raw data, the software allows the researcher to manipulate the lightning angles interactively to analyze the topography of objects. RTI can create new models of access to study graphic materials and book-archeological features. The presentation will focus on the possibilities of the RICH mini-dome technology for art technical and conservation science applications. The implementation of a scaling and measuring tool in the software enables the researcher to export graphically the dimensions and changes of topographic characteristics. The technology gives precise information during comparison of almost exact copies of artefacts, or comparing alterations before and after interventions or exhibitions. Presented cases will illustrate the imaging of 14th century manuscript illuminations and writing, an early 15th century polychrome leather casket, the KU Leuven University seals and medieval blind tooled book bindings.
Tayyab Naseer, Luciano Spinello, Wolfram Burgard, and Cyrill Stachniss
Robust Visual Robot Localization Across Seasons using Network Flows.
In Proc. of the Conf. on the Association for the Advancement of Artificial Intelligence (AAAI) Quebec, Canada
2014
Filippo Basso, Alberto Pretto and Emanuele Menegatti.
Unsupervised Intrinsic and Extrinsic Calibration of a Camera-Depth Sensor Couple
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
The availability of affordable depth sensors in conjunction with common RGB cameras (even in the same device, e.g. the Microsoft Kinect) provides robots with a complete and instantaneous representation of both the appearance and the 3D structure of the current surrounding environment. This type of information enables robots to safely navigate, perceive and actively interact with other agents inside the working environment.
It is clear that, in order to obtain a reliable and accurate representation, not only the intrinsic parameters of each sensors should be precisely calibrated, but also the extrinsic parameters relating the two sensors should be precisely known.
In this paper, we propose a human-friendly and reliable calibration framework, that enables to easily estimate both the intrinsic and extrinsic parameters of a camera-depth sensor couple.
Real world experiments using a Kinect show improvements for both the 3D structure estimation and the association tasks.
David Tedaldi, Alberto Pretto and Emanuele Menegatti
A Robust and Easy to Implement Method for IMU Calibration without External Equipments
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
Motion sensors as inertial measurement units (IMU) are widely used in robotics, for instance in the navigation and mapping tasks.
Nowadays, many low cost micro electro mechanical systems (MEMS) based IMU are available off the shelf, while smartphones and similar devices are almost always equipped with low-cost embedded IMU sensors. Nevertheless, low cost IMUs are affected by systematic error given by imprecise scaling factors and axes misalignments that decrease accuracy in the position and attitudes estimation.
In this paper, we propose a robust and easy to implement method to calibrate an IMU without any external equipment.
The procedure is based on a multi-position scheme, providing scale and misalignments factors for both the accelerometers and gyroscopes triads, while estimating the sensor biases. Our method only requires the sensor to be moved by hand and placed in a set of different, static positions (attitudes).
We describe a robust and quick calibration protocol that exploits an effective parameterless static filter to reliably detect the static intervals in the sensor measurements, where we assume local stability of the gravity's magnitude and stable temperature. We first calibrate the accelerometers triad taking measurement samples in the static intervals. We then exploit these results to calibrate the gyroscopes, employing a robust numerical integration technique.
The performances of the proposed calibration technique has been successfully evaluated via extensive simulations and real experiments with a commercial IMU provided with a calibration certificate as reference data.
Alexander Hermans, Georgios Floros and Bastian Leibe
Dense 3D Semantic Mapping of Indoor Scenes from RGB-D Images
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), *ICRA'14 Best Vision Paper Award*
2014
Dense semantic segmentation of 3D point clouds is a challenging task. Many approaches deal with 2D semantic segmentation and can obtain impressive results. With the availability of cheap RGB-D sensors the field of indoor semantic segmentation has seen a lot of progress. Still it remains unclear how to deal with 3D semantic segmentation in the best way. We propose a novel 2D-3D label transfer based on Bayesian updates and dense pairwise 3D Conditional Random Fields. This approach allows us to use 2D semantic segmentations to create a consistent 3D semantic reconstruction of indoor scenes. To this end, we also propose a fast 2D semantic segmentation approach based on Randomized Decision Forests. Furthermore, we show that it is not needed to obtain a semantic segmentation for every frame in a sequence in order to create accurate semantic 3D reconstructions. We evaluate our approach on both NYU Depth datasets and show that we can obtain a significant speed-up compared to other methods.
Mladen Mazuran, Gian Diego Tipaldi, Luciano Spinello, Wolfram Burgard, and Cyrill Stachniss
A Statistical Measure for Map Consistency in SLAM
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
Map consistency is an important requirement for applications in which mobile robots need to effectively perform autonomous navigation tasks. While recent SLAM techniques provide an increased robustness even in the context of bad initializations or data association outliers, the question of how to determine whether or not the resulting map is consistent is still an open problem. In this paper, we introduce a novel measure for map consistency. We compute this measure by taking into account the discrepancies in the sensor data and leverage it to address two important problems in SLAM. First, we derive a statistical test for assessing whether a map is consistent or not. Second, we employ it to automatically set the free parameter of dynamic covariance scaling, a robust SLAM back-end. We present an evaluation of our approach on over 50 maps sourced from 16 publicly available datasets and illustrate its capability for the inconsistency detection and the tuning of the parameter of the back-end.
Pratik Agarwal, Giorgio Grisetti, Gian Diego Tipaldi, Luciano Spinello, Wolfram Burgard, and Cyrill Stachniss
Experimental Analysis of Dynamic Covariance Scaling for Robust Map Optimization Under Bad Initial Estimates
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
Non-linear error minimization methods became widespread approaches for solving the simultaneous localization and mapping problem. If the initial guess is far away from the global minimum, converging to the correct solution and not to a local one can be challenging and sometimes even impossible. This paper presents an experimental analysis of dynamic covariance scaling, a recently proposed method for robust optimization of SLAM graphs, in the context of a poor initialization. Our evaluation shows that dynamic covariance scaling is able to mitigate the effects of poor initializations. In contrast to other methods that first aim at finding a good initial guess to seed the optimization, our method is more elegant because it does not require an additional method for initialization. Furthermore, it can robustly handle data association outliers. Experiments performed with real world and simulated datasets show that dynamic covariance scaling outperforms existing methods, both in the presence and absence of data association outliers.
Pratik Agarwal, Wolfram Burgard, and Cyrill Stachniss
Helmert's and Bowie's Geodetic Mapping Methods and Their Relation to Graph-Based SLAM.
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
The problem of simultaneously localization a robot and modeling the environment is a prerequisite for several robotic applications and a large variety of solutions have been proposed allowing robots to build maps and use them for navigation. Also the geodetic community addressed large-scale mapping for centuries, computing maps which span across continents. These mapping processes had to deal with several challenges that are similar to those of the robotics community. In this paper, we explain two key geodetic mapping methods that we believe are relevant for robotics. We also aim at providing a geodetic perspective on current state-of-the-art SLAM methods and at identifying similarities between the solutions proposed by both communities. The central goal of this paper is to bring both fields close together and to enable future synergies.
Eddy Ilg, Rainer Kümmerle, Wolfram Burgard, Thomas Brox
Reconstruction of Rigid Body Models from Motion Distorted Laser Range Data Using Optical Flow
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2014
The setup of tilting a 2D laser range finder up and down is a widespread strategy to acquire 3D point clouds. This setup requires that the scene is static while the robot takes a 3D scan. If an object moves through the scene during the measurement process and one does not take into account these movements, the resulting model will get distorted. This paper presents an approach to reconstruct the 3D model of a moving rigid object from the inconsistent set of 2D measurements by the help of a camera. Our approach utilizes optical flow in the camera images to estimate the motion in the image plane and point-line constraints to compensate the missing information about the motion in depth. We combine multiple sweeps and/or views into to a single consistent model using a point-to-plane ICP approach and optimize single sweeps by smoothing the resulting trajectory. Experiments obtained in real outdoor scenarios with moving cars demonstrate that our approach yields accurate models.
P. Agarwal, W. Burgard and C. Stachniss
A Survey of Geodetic Approaches to Mapping and the Relationship to Graph-Based SLAM
IEEE Robotics & Automation Magazine
2014
The ability to simultaneously localize a robot and build a map of
the environment is central to most robotic applications and the
problem is often referred to as SLAM. Robotics researchers have
proposed a large variety of solutions allowing robots to build maps
and use them for navigation. Also the geodetic community addressed
large-scale map building for centuries, computing maps which span
across continents. These large-scale mapping processes had to deal with
several challenges that are similar to those of the robotics
community. In this paper, we explain key geodetic map building
methods that we believe are relevant for robot mapping. We also aim at
providing a geodetic perspective on current state-of-the-art SLAM
methods and identifying similarities both in terms of challenges
faced as well as in the solutions proposed by both communities. The
central goal of this paper is to connect both fields and to enable
future synergies between them.
Maria T. Lazaro, Lina M. Paz, Pedro Pinies, Jose A. Castellanos and Giorgio Grisetti
Multi-Robot SLAM using Condensed Measurements
In Proc. of Int. Conf. on Intellogent Robots and Systems (IROS)
2013
In this paper we describe a Simultaneous Localization and Mapping (SLAM) approach specifically designed to address the communication and computational issues that affect multi-robot systems. Our method utilizes condensed measurements to exchange map information between the robots. These measurements can effectively compress relevant portions of a map in a few data. This results in a substantial reduction of both the data to be transmitted and processed, that renders the system more robust and efficient. As documented by our simulated and real world experiments, these advantages come with a very little decrease in accuracy compared to ideal (but not realistic) methods that share the full data among all the robots.
Vittorio A. Ziparo, Marco Zaratti, Girogio Grisetti, Taigo Bonanni, Jacopo Serafin, Maurilio Di Cicco, Marc Proesmans, Luc van Gool, Oolga Vysotska, Igor Bogoslavskyi and Cyrill Stachniss
Exploration and Mapping of Catacombs with Mobile Robots
In Proc. for the IEEE International Symposium on Safety Security and Rescue Robotics (SSRR 2013)
2013
This document describes the recent developments in the FP7 project ROVINA. We report on our first inspection in the catacombs of S. Priscilla in Rome, along with the preliminary analysis of the collected data and on the lessons learned for the design of the ROVINA robot.
Maximilian Beinhofer, Henrik Kretzschmar, and Wolfram Burgard
Deploying Artificial Landmarks to Foster Data Association in Simultaneous Localization and Mapping
In Proc. of the IEEE Int. Conf. on Robotics & Automation (ICRA)
2013
Data association is an essential problem in simultaneous localization and mapping. It is hard to solve correctly, especially in ambiguous environments. We consider a scenario where the robot can ease the data association problem by deploying a limited number of uniquely identifiable artificial landmarks along its path and use them afterwards as fixed anchors. Obviously, the choice of the positions where the robot should drop these markers is crucial as poor choices might prevent the robot from establishing accurate data associations. In this paper, we present a novel approach for learning when to drop the landmarks so as to optimize the data association performance. We use Monte Carlo reinforcement learning for computing an optimal policy and apply a statistical convergence test to decide if the policy is converged and the learning process can be stopped. Extensive experiments also carried out with a real robot demonstrate that the data association performance using landmarks deployed according to our learned policies is significantly higher compared to other strategies.
Pratik Agarwal, Gian Diego Tipaldi, Luciano Spinello, Cyrill Stachniss, and Wolfram Burgard
Dynamic Covariance Scaling for Robust Robotic Mapping
In ICRA Workshop on robust and Multimodal Inference in Factor Graphs
2013
Developing the perfect SLAM front-end that produces graphs which are free of outliers is hard to achieve due to perceptual aliasing. Converging to the correct solution is challenging for non-linear error minimization SLAM techniques even in the absence of outliers, if the initial guess is far away from the correct solution. Therefore, optimization back-ends need to be resilient to outliers resulting from an imperfect front-end as well as be robust to bad initialization. In this paper, we present dynamic covariance scaling, a novel approach for effective optimization of constraint networks under the presence of outliers and bad initial guess. The key idea is to use a robust function that generalizes classical gating and down-weights outliers without compromising convergence speed. Compared to recently published state-of-the-art methods, we obtain a substantial speed-up without increasing overheads.
Armin Hornung, Kai M. Wurm, Maren Bennewitz, Cyrill Stachniss, and Wolfram Burgard
OctoMap: An Efficient Probabilistic 3D Mapping Framework Based on Octrees
Autonomous Robots, DOI: 10.1007/s10514-012-9321-0
2013
Three-dimensional models provide a volumetric representation of space which is important for a variety of robotic applications including flying robots and robots that are equipped with manipulators. In this paper, we present an open-source framework to generate volumetric 3D environment models. Our mapping approach is based on octrees and uses probabilistic occupancy estimation. It explicitly represents not only occupied space, but also free and unknown areas. Furthermore, we propose an octree map compression method that keeps the 3D models compact. Our framework is available as an open-source C++ library and has already been successfully applied in several robotics projects. We present a series of experimental results carried out with real robots and on publicly available real-world datasets. The results demonstrate that our approach is able to update the representation efficiently and models the data consistently while keeping the memory requirement at a minimum.
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
2013
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 10fps-25fps 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.
Pratik Agarwal, Gian Diego Tipaldi, Luciano Spinello, Cyrill Stachniss, and Wolfram Burgard
Robust Map Optimization Using Dynamic Covariance Scaling
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA)
2013
Developing the perfect SLAM front-end that produces graphs which are free of outliers is generally impossible due to perceptual aliasing. Therefore, optimization back-ends need to be able to deal with outliers resulting from an imperfect front-end. In this paper, we introduce dynamic covariance scaling, a novel approach for effective optimization of constraint networks under the presence of outliers. The key idea is to use a robust function that generalizes classical gating and dynamically rejects outliers without compromising convergence speed. We implemented and thoroughly evaluated our method on publicly available datasets. Compared to recently published state-of-the-art methods, we obtain a substantial speed up without increasing the number of variables in the optimization process. Our method can be easily integrated in almost any SLAM back-end.
Giorgio Grisetti, Luca Iocchi, Bastian Leibe, Vittorio Amos Ziparo, and Cyrill Stachniss
Digitization of Inaccessible Archeological Sites with Autonomous Mobile Robots
In Proc. of the Conference on Robotics Innovation for Cultural Heritage
2012
The conservation of archeological sites and historical buildings is an important goal for both, scientists as well as the general public. Precisely modeling such sites is often a prerequisite for conservation, maintenance, restoration, security, and other tasks. To this end, technological advancements in information and communication technology and especially in artificial intelligence and robotics have the potential develop valuable tools for mapping and digitally preserving archeological sites.
While intelligent robots have been already applied in applications related to cultural heritage such as robot guides for museums or robot surveillants, there are many other application scenarios that can benefit from the use of intelligent robotics technology.
In this work, we focus on archeological sites that are difficult to be accessed by humans, such as catacombs or other similar underground areas. These environments are often not open to public because they are not safe and operation within them is difficulty and sometimes even risky. Therefore, standard digitizing techniques, such as static 3D laser scanners operated by human operators, may not be feasible. On the other hand, mapping and digitizing such sites is very important for both enlarging their fruition and for their maintenance. In these environments, autonomous mobile robots can assist and sometimes replace human operators for these tasks. Our goal is to develop autonomous mobile robots for mapping archeological sites that are difficult to be accessed by human operators.