The goal of this paper is to increase the estimation performance of an Extended Kalman Filter for a nonlinear differentially flat system by planning trajectories able to maximize the amount of information gathered by onboard sensors in presence of both process and measurement noises. In a previous work, we presented an online gradient descent method for planning optimal trajectories along which the smallest eigenvalue of the Observability Gramian (OG) is maximized. As the smallest eigenvalue of the OG is inversely proportional to the maximum estimation uncertainty, its maximization reduces the maximum estimation uncertainty of any estimation algorithm employed during motion. However, the OG does not consider the process noise that, instead, in several applications is far from being negligible. For this reason, this paper proposes a novel solution able to cope with non-negligible process noise: this is achieved by minimizing the largest eigenvalue of the a posteriori covariance matrix obtained by solving the Continuous Riccati Equation as a measure of the total available information. This minimization is expected to maximize the information gathered by the outputs while, at the same time, limiting as much as possible the negative effects of the process noise. We apply our method to a unicycle robot. The comparison between the novel method and the one of our previous work (which did not consider process noise) shows significant improvements in the obtained estimation accuracy.

10acontinuous Riccati equation10acovariance matrices10aeigenvalues and eigenfunctions10aEstimation10aestimation algorithm10agradient methods10ainversely proportional10aKalman Filter10aKalman filters10alargest eigenvalue10amaximum estimation uncertainty10ameasurement noise10amobile robots10anoise measurement10anonlinear differentially flat system10anonlinear filters10anonnegligible process noise10aobservability10aobservability gramian10aOG10aonboard sensors10aonline gradient descent method10aoptimal active sensing10aoptimal trajectories10aoptimisation10apath planning10aposteriori covariance matrix10aRiccati equations10aRobot sensing systems10aTrajectory10atrajectory control10aunicycle robot1 aCognetti, M.1 aSalaris, P1 aGiordano, Robuffo uhttps://ieeexplore.ieee.org/document/846047600460nas a2200157 4500008003900000020002200039245004200061210004200103260002900145300001400174100001500188700001400203700002200217700001400239856004900253 2017 d a978-1-5090-4633-100aOnline optimal active sensing control0 aOnline optimal active sensing control aSingaporebIEEEc07/2017 a672–6781 aSalaris, P1 aSpica, R.1 aGiordano, Robuffo1 aRives, P. uhttps://ieeexplore.ieee.org/document/798908300455nas a2200133 4500008004100000245009900041210006900140260001200209490000700221100001500228700001200243700001700255856004900272 2017 eng d00aRobot Choreography: The Use of the Kinetography Laban System to Notate Robot Action and Motion0 aRobot Choreography The Use of the Kinetography Laban System to N c06/20170 v241 aSalaris, P1 aAbe, N.1 aLaumond, J P uhttps://ieeexplore.ieee.org/document/793869901778nas a2200169 4500008004100000245009200041210006900133300001600202490000700218520116900225653002101394653001301415100001501428700001801443700001901461856012801480 2015 eng d00aEpsilon-Optimal Synthesis for Unicycle-like Vehicles with Limited Field-Of-View Sensors0 aEpsilonOptimal Synthesis for Unicyclelike Vehicles with Limited a1404 - 14180 v313 aIn this paper we study the minimum length paths covered by the center of a unicycle equipped with a limited Field–Of–View (FOV) camera, which must keep a given landmark in sight. Previous works on this subject have provided the optimal synthesis for the cases in which the FOV is only limited in the horizontal directions (i.e. left and right bounds) or in the vertical directions (i.e. upper and lower bounds). In this paper we show how to merge previous results and hence obtaining, for a realistic image plane modeled as a rectangle, a finite alphabet of extremal arcs and the overall synthesis. As shown, this objective can not be straightforwardly achieved from previous results but needs further analysis and developments. Moreover, there are initial configurations such that there exists no optimal path. Nonetheless, we are always able to provide an e–optimal path whose length approximates arbitrarily well any other shorter path. As final results, we provide a partition of the motion plane in regions such that the optimal or e–optimal path from each point in thatregion is univocally determined.

10aEmbedded Control10aRobotics1 aSalaris, P1 aCristofaro, A1 aPallottino, L. uhttps://www.centropiaggio.unipi.it/publications/epsilon-optimal-synthesis-unicycle-vehicles-limited-field-view-sensors.html00442nas a2200145 4500008004100000245006300041210005900104260001200163490000700175100001500182700001700197700001600214700001700230856004900247 2015 eng d00aThe geometry of confocal curves for passing through a door0 ageometry of confocal curves for passing through a door c10/20150 v311 aSalaris, P1 aVassallo, C.1 aSouères, P1 aLaumond, J P uhttps://ieeexplore.ieee.org/document/727453100477nas a2200133 4500008003900000245008500039210006900124260003600193100001500229700001700244700001600261700001700277856004900294 2015 d00aImage-based control relying on conic curves foliation for passing through a gate0 aImagebased control relying on conic curves foliation for passing aSeattle, WA, USAbIEEEc07/20151 aSalaris, P1 aVassallo, C.1 aSouères, P1 aLaumond, J P uhttps://ieeexplore.ieee.org/document/713925300504nas a2200145 4500008004100000022002200041245008800063210006900151260001900220490000800239100001500247700001200262700001700274856006700291 2015 eng d a978-3-319-25737-200aA worked-out experience in program- ming humanoid robots via the kinetography laban0 aworkedout experience in program ming humanoid robots via the kin bSpringer, Cham0 v1111 aSalaris, P1 aAbe, N.1 aLaumond, J P uhttps://link.springer.com/chapter/10.1007/978-3-319-25739-6_1601494nas a2200157 4500008004100000245013500041210006900176490000700245520081600252653001301068100002001081700001501101700001801116700001501134856018701149 2013 eng d00aA Complete Observability Analysis of the Planar Bearing Localization and Mapping for Visual Servoing with Known Camera Velocities0 aComplete Observability Analysis of the Planar Bearing Localizati0 v103 aThis paper presents an analysis of planar bearing localization and mapping for visual servoing with known camera velocities. In particular, we investigate what is the subset of camera locations and environmental features that can be retrieved from dynamic observations obtained by a planar bearing sensor (nearly e.g., a pinhole camera). Results assume that the camera’s linear and angular velocities are available, which is equivalent to consider a unicycle vehicle carrying an onboard camera. Results hold if other system inputs are considered, e.g., an omnidirectional vehicle. The theoretical results may guide the design of nonlinear observers to estimate the variables of interest in real time to be applied to visual servoing schemes. An example of such an observer is discussed and simulated.

10aRobotics1 aBelo, F., A. W.1 aSalaris, P1 aFontanelli, D1 aBicchi, A. uhttp://www.intechopen.com/books/international_journal_of_advanced_robotic_systems/a-complete-observability-analysis-of-the-planar-bearing-localization-and-mapping-for-visual-servoing00551nas a2200169 4500008003900000245005400039210005400093260002000147300001600167653001300183100001400196700001800210700001600228700001900244700001500263856010300278 2013 d00aGlobal Path Planning for Competitive Robotic Cars0 aGlobal Path Planning for Competitive Robotic Cars aFlorence, Italy a4510 - 451610aRobotics1 aRizano, T1 aFontanelli, D1 aPalopoli, L1 aPallottino, L.1 aSalaris, P uhttps://www.centropiaggio.unipi.it/publications/global-path-planning-competitive-robotic-cars.html00622nas a2200157 4500008003900000245010200039210006900141260002000210300001600230653001300246100001500259700001800274700001900292700001500311856013800326 2013 d00aShortest paths for wheeled robots with limited Field-Of-View: introducing the vertical constraint0 aShortest paths for wheeled robots with limited FieldOfView intro aFlorence, Italy a5143 - 514910aRobotics1 aSalaris, P1 aCristofaro, A1 aPallottino, L.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/shortest-paths-wheeled-robots-limited-field-view-introducing-vertical-constraint.html00633nas a2200169 4500008003900000245008700039210006900126260002600195653001300221100001500234700001800249700001700267700001600284700001500300700001500315856013300330 2013 d00aSoft-Actuators in Cyclic Motion: Analytical Optimization of Stiffness and Pre-Load0 aSoftActuators in Cyclic Motion Analytical Optimization of Stiffn aAtlanta, Georgia, USA10aRobotics1 aVelasco, A1 aGasparri, G M1 aGarabini, M.1 aMalagia, L.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/soft-actuators-cyclic-motion-analytical-optimization-stiffness-and-pre-load.html01856nas a2200169 4500008004100000024003500041245005800076210005600134300001200190490000700202520130800209653001301517100001601530700001501546700001501561856011001576 2013 eng d ahttp://arxiv.org/abs/1206.055600aSynergy-Based Hand Pose Sensing: Optimal Glove Design0 aSynergyBased Hand Pose Sensing Optimal Glove Design a396-4060 v323 aIn this paper we study the problem of improving human hand pose sensing device performance by exploiting the knowledge on how humans most frequently use their hands in grasping tasks. In a companion paper we studied the problem of maximizing the reconstruction accuracy of the hand pose from partial and noisy data provided by any given pose sensing device (a sensorized "glove") taking into account statistical a priori information. In this paper we consider the dual problem of how to design pose sensing devices, i.e. how and where to place sensors on a glove, to get maximum information about the actual hand posture. We study the continuous case, whereas individual sensing elements in the glove measure a linear combination of joint angles, the discrete case, whereas each measure corresponds to a single joint angle, and the most general hybrid case, whereas both continuous and discrete sensing elements are available. The objective is to provide, for given a priori information and fixed number of measurements, the optimal design minimizing in average the reconstruction error. Solutions relying on the geometrical synergy definition as well as gradient flow-based techniques are provided. Simulations of reconstruction performance show the effectiveness of the proposed optimal design.

10aRobotics1 aBianchi, M.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/synergy-based-hand-pose-sensing-optimal-glove-design.html01809nas a2200157 4500008004100000245006400041210006200105300001300167490000700180520128900187653001301476100001601489700001501505700001501520856011601535 2013 eng d00aSynergy-based Hand Pose Sensing: Reconstruction Enhancement0 aSynergybased Hand Pose Sensing Reconstruction Enhancement a 407-4240 v323 aLow-cost sensing gloves for reconstruction posture provide measurements which are limited under several regards. They are generated through an imperfectly known model, are subject to noise, and may be less than the number of Degrees of Freedom (DoFs) of the hand. Under these conditions, direct reconstruction of the hand posture is an ill-posed problem, and performance can be very poor. This paper examines the problem of estimating the posture of a human hand using(low-cost) sensing gloves, and how to improve their performance by exploiting the knowledge on how humans most frequently use their hands. To increase the accuracy of pose reconstruction without modifying the glove hardware - hence basically at no extra cost - we propose to collect, organize, and exploit information on the probabilistic distribution of human hand poses in common tasks. We discuss how a database of such an a priori information can be built, represented in a hierarchy of correlation patterns or postural synergies, and fused with glove data in a consistent way, so as to provide a good hand pose reconstruction in spite of insufficient and inaccurate sensing data. Simulations and experiments on a low-cost glove are reported which demonstrate the effectiveness of the proposed techniques.

10aRobotics1 aBianchi, M.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/synergy-based-hand-pose-sensing-reconstruction-enhancement.html00628nas a2200169 4500008004100000245007100041210006900112260004900181300001700230653001300247100001400260700001700274700001800291700001500309700001900324856011500343 2012 eng d00aMotion Planning for Two 3D-Dubins Vehicles with Distance Contraint0 aMotion Planning for Two 3DDubins Vehicles with Distance Contrain aVilamoura, Algarve, PortugalcOctober 7 - 12 a4702 - 4707 10aRobotics1 aMarino, H1 aBonizzato, M1 aBartalucci, R1 aSalaris, P1 aPallottino, L. uhttps://www.centropiaggio.unipi.it/publications/motion-planning-two-3d-dubins-vehicles-distance-contraint.html00589nas a2200169 4500008004100000245006100041210006000102260003700162300001700199653001300216100001700229700001700246700002000263700001500283700001500298856010600313 2012 eng d00aOptimality Principles in Stiffness Control: The VSA Kick0 aOptimality Principles in Stiffness Control The VSA Kick aSaint Paul, MN, USAcMay 14 - 18 a3341 - 3346 10aRobotics1 aGarabini, M.1 aPassaglia, A1 aBelo, F., A. W.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/optimality-principles-stiffness-control-vsa-kick.html00566nas a2200145 4500008004100000245009300041210006900134300001300203490000700216653001300223100001500236700001900251700001500270856013500285 2012 eng d00aShortest Paths for Finned, Winged, Legged and Wheeled Vehicles with Side-Looking Sensors0 aShortest Paths for Finned Winged Legged and Wheeled Vehicles wit a997-10170 v3110aRobotics1 aSalaris, P1 aPallottino, L.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/shortest-paths-finned-winged-legged-and-wheeled-vehicles-side-looking-sensors.html00523nas a2200145 4500008004100000245005400041210005300095260004900148300001700197653001300214100001600227700001500243700001500258856010400273 2012 eng d00aSynergy-based Optimal Desing of Hand Pose Sensing0 aSynergybased Optimal Desing of Hand Pose Sensing aVilamoura, Algarve, PortugalcOctober 7 - 12 a3929 - 3935 10aRobotics1 aBianchi, M.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/synergy-based-optimal-desing-hand-pose-sensing.html00639nas a2200181 4500008004100000245007900041210006900120260003500189300001200224653001200236653001300248100001600261700001500277700001300292700001800305700001500323856011900338 2012 eng d00aOn the Use of Postural Synergies to Improve Human Hand Pose Reconstruction0 aUse of Postural Synergies to Improve Human Hand Pose Reconstruct aVancouver, CanadacMarch 4 - 7 a91 - 9810aHaptics10aRobotics1 aBianchi, M.1 aSalaris, P1 aTurco, A1 aCarbonaro, N.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/use-postural-synergies-improve-human-hand-pose-reconstruction.html00455nas a2200121 4500008004100000245005600041210005300097260003300150653001300183100001900196700001500215856010300230 2011 eng d00aOn constrained optimal control problems in robotics0 aconstrained optimal control problems in robotics aPisa, ItalycSeptember 7 - 910aRobotics1 aPallottino, L.1 aSalaris, P uhttps://www.centropiaggio.unipi.it/publications/constrained-optimal-control-problems-robotics.html00592nas a2200169 4500008004100000245006200041210006200103260004000165300001400205653002100219653001300240100001500253700001900268700001800287700001500305856010200320 2011 eng d00aFrom Optimal Planning to Visual Servoing with Limited FOV0 aFrom Optimal Planning to Visual Servoing with Limited FOV aS. Francisco, USAcSeptember 25 - 3 a2817-282410aEmbedded Control10aRobotics1 aSalaris, P1 aPallottino, L.1 aHutchinson, S1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/optimal-planning-visual-servoing-limited-fov.html00468nas a2200109 4500008004100000245007800041210006900119260002300188653001300211100001500224856011900239 2011 eng d00aFrom Optimal Synthesis to Optimal Visual Servoing for Autonomous Vehicles0 aFrom Optimal Synthesis to Optimal Visual Servoing for Autonomous bUniversity of Pisa10aRobotics1 aSalaris, P uhttps://www.centropiaggio.unipi.it/publications/optimal-synthesis-optimal-visual-servoing-autonomous-vehicles.html00527nas a2200133 4500008004100000245007800041210006900119653002100188653001300209100001500222700001900237700001500256856012200271 2011 eng d00aOptimal synthesis for nonholonomic vehicles with constrained side sensors0 aOptimal synthesis for nonholonomic vehicles with constrained sid10aEmbedded Control10aRobotics1 aSalaris, P1 aPallottino, L.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/optimal-synthesis-nonholonomic-vehicles-constrained-side-sensors.html00622nas a2200169 4500008004100000245007200041210006900113260004000182300001600222653001300238100001700251700001700268700002000285700001500305700001500320856011700335 2011 eng d00aOptimality Principles in Variable Stiffness Control: the VSA Hammer0 aOptimality Principles in Variable Stiffness Control the VSA Hamm aS. Francisco, USAcSeptember 25 - 3 a3770 - 377510aRobotics1 aGarabini, M.1 aPassaglia, A1 aBelo, F., A. W.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/optimality-principles-variable-stiffness-control-vsa-hammer.html00485nas a2200157 4500008004100000245003600041210003600077260003100113300001600144653002100160653001300181100001500194700001900209700001500228856008400243 2011 eng d00aShortest Paths With Side Sensor0 aShortest Paths With Side Sensor aShangai, ChinacMay 9 - 13 a4875 - 488210aEmbedded Control10aRobotics1 aSalaris, P1 aPallottino, L.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/shortest-paths-side-sensor.html00730nas a2200217 4500008004100000245007600041210006900117260003400186653001300220100001500233700002000248700001700268700001400285700001400299700001500313700002000328700001500348700001500363700001700378856011700395 2011 eng d00aVariable stiffness actuators: muscles for the next generation of robots0 aVariable stiffness actuators muscles for the next generation of aPisa, ItalycSeptember, 7 - 910aRobotics1 aGrioli, G.1 aCatalano, M. G.1 aGarabini, M.1 aBonomo, F1 aSerio, A.1 aSalaris, P1 aBelo, F., A. W.1 aMancini, M1 aBicchi, A.1 aPassaglia, A uhttps://www.centropiaggio.unipi.it/publications/variable-stiffness-actuators-muscles-next-generation-robots.html00669nas a2200169 4500008004100000024001900041245010200060210006900162260003000231300001500261653002100276653001300297100002000310700001500330700001500345856013900360 2010 eng d ap. 2539 - 254500a3 known landmarks are enough for solving planar bearing SLAM and fully reconstruct unknown inputs0 a3 known landmarks are enough for solving planar bearing SLAM and aSt. Louis MO USAcOctober a2539 -254510aEmbedded Control10aRobotics1 aBelo, F., A. W.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/3-known-landmarks-are-enough-solving-planar-bearing-slam-and-fully-reconstruct-unknown00599nas a2200169 4500008004100000245007900041210006900120300001400189490000700203653002100210653001300231100001500244700001800259700001900277700001500296856011800311 2010 eng d00aShortest Paths for a Robot with Nonholonomic and Field-of-View Constraints0 aShortest Paths for a Robot with Nonholonomic and FieldofView Con a269 - 2810 v2610aEmbedded Control10aRobotics1 aSalaris, P1 aFontanelli, D1 aPallottino, L.1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/shortest-paths-robot-nonholonomic-and-field-view-constraints.html00595nas a2200193 4500008004100000245005100041210005100092260001300143300001400156490000800170653001300178100001800191700001500209700002000224700001500244700002000259700002200279856010000301 2010 eng d00aVisual Servoing via Advanced Numerical Methods0 aVisual Servoing via Advanced Numerical Methods bSpringer a335 - 3600 v40110aRobotics1 aFontanelli, D1 aSalaris, P1 aBelo, F., A. W.1 aBicchi, A.1 aChesi, Graziano1 aHashimoto, Koichi uhttps://www.centropiaggio.unipi.it/publications/visual-servoing-advanced-numerical-methods.html01196nas a2200181 4500008004100000245008000041210006900121260003700190300001600227520054900243653002100792653001300813100001900826700001500845700001800860700001500878856012100893 2009 eng d00aShortest Paths for Non-holonomic Vehicles with Limited Field of View Camera0 aShortest Paths for Nonholonomic Vehicles with Limited Field of V aShangai, ChinacDecember, 16 - 1 a8434 - 84393 aThis paper presents a complete characterization of shortest paths for unicycle-like nonholonomic mobile robots equipped with a pinhole camera rigidly fixed with limited Field-Of-View (FOV). We preliminarily provide an alphabet of optimal control words and then we demonstrate how to obtain the partition induced by shortest path in the vehicle plane. The word univocally associated to a region encodes the shortest path from any starting point in that region to the goal point of the mobile robot without violating the FOV constraints.

10aEmbedded Control10aRobotics1 aPallottino, L.1 aSalaris, P1 aFontanelli, D1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/shortest-paths-non-holonomic-vehicles-limited-field-view-camera.html00681nas a2200205 4500008004100000245006400041210006400105260002300169300001400192490003100206653001300237100001800250700001500268700002000283700001500303700001700318700001400335700001300349856011300362 2009 eng d00aVisual appearance mapping for optimal vision based servoing0 aVisual appearance mapping for optimal vision based servoing bSpringercMarch 28 a353 - 3620 v54 - Experimental Robotics10aRobotics1 aFontanelli, D1 aSalaris, P1 aBelo, F., A. W.1 aBicchi, A.1 aSiciliano, B1 aKhatib, O1 aGroen, F uhttps://www.centropiaggio.unipi.it/publications/visual-appearance-mapping-optimal-vision-based-servoing.html01531nas a2200205 4500008004100000245003300041210003300074260000900107300001400116490000700130520099300137653002101130653001301151100001801164700001401182700002001196700001501216700001501231856007901246 2009 eng d00aVisual Servoing in the Large0 aVisual Servoing in the Large cJune a802 - 8140 v283 aIn this paper we consider the problem of maneuvering an autonomous robot in complex unknown environments using vision. The goal is to accurately servo a wheeled vehicle to a desired posture using only feedback from an on-board camera, taking into account the nonholonomic nature of the vehicle kinematics and the limited field-ofview of the camera. With respect to existing visual servoing schemes, which achieve similar goals locally (i.e. when the desired and actual camera views are sufficiently similar), we propose a method to visually navigate the robot through an extended visual map before eventually reaching the desired goal. The map comprises a set of images, previously stored in an exploratory phase, that convey both topological and metric information regarding the connectivity through feasible robot paths and the geometry of the environment, respectively. Experimental results on a laboratory setup are reported showing the practicality of the proposed approach.

10aEmbedded Control10aRobotics1 aFontanelli, D1 aDanesi, A1 aBelo, F., A. W.1 aSalaris, P1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/visual-servoing-large.html01497nas a2200181 4500008004100000245007800041210006900119260001500188300001400203520088200217653001301099100001501112700002001127700001801147700001301165700001501178856012201193 2008 eng d00aOptimal Paths in a Constrained Image Plane for Purely Image-Based Parking0 aOptimal Paths in a Constrained Image Plane for Purely ImageBased c22-26 Sept a1673-16803 aThis paper presents a correct solution to the optimal feedback control for a nonholonomic vehicle with limited field-of-view. Previous work on this subject has shown that the search for a shortest path can be limited to simple families of trajectories. We preliminarily provide an extension of the alphabet of optimal control words, to cover some regions of the vehicle plane where the synthesis of turns out to be suboptimal. The main contribution of this paper is an algorithm to translate the optimal synthesis to the image plane, thus enabling a purely image-based optimal control scheme. This allows better performance and increases the robustness of the overall process, avoiding the need of slowly-converging and error-prone parameter estimation algorithms. Simulations and experiments are reported which demonstrate the effectiveness of the proposed technique.

10aRobotics1 aSalaris, P1 aBelo, F., A. W.1 aFontanelli, D1 aGreco, L1 aBicchi, A. uhttps://www.centropiaggio.unipi.it/publications/optimal-paths-constrained-image-plane-purely-image-based-parking.html00582nas a2200169 4500008004100000245006700041210006700108300001200175490001200187653001300199100001500212700002000227700001800247700001500265700002000280856011200300 2008 eng d00aVisual SLAM for Servoing for Appearance Based Topological Maps0 aVisual SLAM for Servoing for Appearance Based Topological Maps a277-2860 v39/200810aRobotics1 aSalaris, P1 aBelo, F., A. W.1 aFontanelli, D1 aBicchi, A.1 aSpringer-Verlag uhttps://www.centropiaggio.unipi.it/publications/visual-slam-servoing-appearance-based-topological-maps.html