Large-scale semantic mapping and reasoning with heterogeneous modalities
The DOI matches its Crossref record; 24 of the 27 references it cites were found in a registry or an index.
Abstract
This paper presents a probabilistic framework combining heterogeneous, uncertain, information such as object observations, shape, size, appearance of rooms and human input for semantic mapping. It abstracts multi-modal sensory information and integrates it with conceptual common-sense knowledge in a fully probabilistic fashion. It relies on the concept of spatial properties which make the semantic map more descriptive, and the system more scalable and better adapted for human interaction. A probabilistic graphical model, a chaingraph, is used to represent the conceptual information and perform spatial reasoning. Experimental results from online system tests in a large unstructured office environment highlight the system's ability to infer semantic room categories, predict existence of objects and values of other spatial properties as well as reason about unexplored space.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Speeded-Up Robust Features (SURF)
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.09.014 · Cited by 13,557
Context-based vision system for place and object recognition
Torralba, Murphy, Freeman, & Rubin (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238354 · Cited by 867
The Spatial Semantic Hierarchy
Kuipers, B. (2000) · Artificial Intelligence · doi:10.1016/s0004-3702(00)00017-5 · Cited by 726
Towards semantic maps for mobile robots
Nüchter, A., & Hertzberg, J. (2008) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.08.001 · Cited by 406
Multi-hierarchical semantic maps for mobile robotics
Galindo, C., Saffiotti, A., Coradeschi, S., Buschka, P., Fernandez-Madrigal, J. A., & Gonzalez, J. (2005) · 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2005.1545511 · Cited by 308
Conceptual spatial representations for indoor mobile robots
Zender, H., Martínez Mozos, O., Jensfelt, P., Kruijff, G.-J. M., & Burgard, W. (2008) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.03.007 · Cited by 300
Self-citationHighly scalable appearance-only SLAM - FAB-MAP 2.0
Cummins, M., & Newman, P. (2009) · Robotics: Science and Systems V · doi:10.15607/rss.2009.v.039 · Cited by 282
Chain Graph Models and their Causal Interpretations
Lauritzen, S. L., & Richardson, T. S. (2002) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00340 · Cited by 265
libDAI: A Free and Open Source C++ Library for Discrete Approximate Inference in Graphical Models
Mooij, J. M. (2010) · Max Planck Institute for Plasma Physics · doi:10.5555/1756006.1859925 · Cited by 227
Curious George: An attentive semantic robot
Meger, D., Forssén, P.-E., Lai, K., Helmer, S., McCann, S., Southey, T., Baumann, M., Little, J. J., & Lowe, D. G. (2008) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.03.008 · Cited by 167
Research works printed but not linked: 1
- mo?rwald, 0, BLORT - The blocks world robotic vision toolbox, ICRA Workshop Best Practice in 3D Perc and Model for Mobile Manipul 2010
Cited by
Items 101–200 of 247
SO-MRS: A Multi-robot System Architecture Based on the SOA Paradigm and Ontology
Skarżyński, K., Stępniak, M., Bartyna, W., & Ambroszkiewicz, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96728-8_28 · Cited by 14
Not seeing is also believing: Combining object and metric spatial information
Wong, L. L. S., Kaelbling, L. P., & Lozano‐Pérez, T. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907014 · Cited by 13
“, [4], [5], [6], [7]), where typically the focus is to endow topological regions of space with semantic attributes, such as in the task of place classification.”
BackgroundA Novel Mobile Robot Navigation Method Based on Hand-Drawn Paths
Hou, X., Li, W., Han, Y., Wang, A., Yang, Y., Liu, L., & Tian, Y. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2997055 · Cited by 14
Active Object Search Exploiting Probabilistic Object–Object Relations
Elfring, J., Jansen, S., van de Molengraft, R., & Steinbuch, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44468-9_2 · Cited by 13
“Various works [11,12] use human generated ontologies containing common sense knowledge, e.”
BackgroundDefinition of semantic maps for outdoor robotic tasks
Lang, D., Friedmann, S., Häselich, M., & Paulus, D. W. R. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090724 · Cited by 12
Binding human spatial interactions with mapping for enhanced mobility in dynamic environments
Papadakis, P., & Rives, P. (2016) · Autonomous Robots · doi:10.1007/s10514-016-9581-1 · Cited by 12
“Typically, the problem of environment mapping is treated through a decomposition into layers that each represents a desired abstraction level, ranging from the low-level 2D/3D metric and topological [6] to the semantic [25], object-based and social activity level [24] (we refer the interested reader to [27] and [17] f…”
A Multiview Approach to Learning Articulated Motion Models
Daniele, A. F., Howard, T. M., & Walter, M. R. (2019) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-28619-4_30 · Cited by 14
“Meanwhile, multimodal learning methods have been proposed that use language and vision to formulate spatial-semantic maps of a robot’s environment [15, 40, 49, 56] and to learn object manipulation policies [46].”
BackgroundAn integrated model of autonomous topological spatial cognition
Karaoğuz, H., & Bozma, H. I. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9514-4 · Cited by 12
“…rely on semantic information such as place labels being externally provided (Mozos et al. 2007a,b; Erkent and Bozma 2012; Lim et al. 2012; Pronobis and Jensfelt 2012; Shi et al. 2012; Ursic et al. 2012) In contrast, unsupervised approaches do not rely on exter-nal guidance and aim to…”
BackgroundMethodAutonomous Mobile Robot Intrinsic Navigation Based on Visual Topological Map
Luo, R. C., & Shih, W. (2018) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2018.8433588 · Cited by 11
“[10] proposed a probabilistic framework to”
Veiga, T., Silva, M., Ventura, R., & Lima, P. U. (2021) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v29i1.3546 · Cited by 11
“This way, semantic information from sensors was used for navigation tasks (Galindo et al. 2005) or layered representations of knowledge that consider the uncertainty on the dynamics of the system and build probabilistic conceptual maps (Pronobis et al. 2010; Pronobis and Jensfelt 2012).”
MethodA probabilistic approach for semantic classification using laser range data in indoor environments
Kaleci, B., Şenler, Ç. M., Dutağacı, H., & Parlaktuna, O. (2015) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2015.7251483 · Cited by 11
“Pronobis and Jensfelt [2] used data from different sources such as laser, camera, and people in order to determine the semantic classes.”
MethodUnderwater 3D structures as semantic landmarks in SONAR mapping
Guerneve, T., Subr, K., & Pétillot, Y. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202215 · Cited by 11
“Semantic interpretation in non-underwater domains has been widely investigated but rely mainly on the highlystructured nature of man-made environments [20].”
BackgroundLanguage Understanding for Field and Service Robots in a Priori Unknown Environments
Walter, M. R., Patki, S., Daniele, A. F., Fahnestock, E., Duvallet, F., Hemachandra, S. M., Oh, J., Stentz, A., Roy, N., & Howard, T. M. (2022) · Field Robotics · doi:10.55417/fr.2022040 · Cited by 16
Multi-class Target Tracking Using the Semantic PHD Filter
Chen, J., & Dames, P. (2022) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-95459-8_32 · Cited by 11
Mapping beyond what you can see: Predicting the layout of rooms behind closed doors
Luperto, M., Amadelli, F., Berardino, M. D., & Amigoni, F. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104282 · Cited by 13
Exploiting Structural Properties of Buildings Towards General Semantic Mapping Systems
Luperto, M., & Francesco Amigoni, A. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_28 · Cited by 11
Fukuoka datasets for place categorization
Mozos, Ó. M., Nakashima, K., Jung, H., Iwashita, Y., & Kurazume, R. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919835603 · Cited by 13
“This information can greatly improve other high-level robotic tasks such as communication with humans (Pronobis and Jensfelt, 2012; Rosa et al., 2018; Zender et al., 2008), search and exploration (Aydemir et al.”
BackgroundAutonomous question answering with mobile robots in human-populated environments
Chung, M. J.-Y., Pronobis, A., Çakmak, M., Fox, D., & Rao, R. P. N. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759146 · Cited by 10
“For example, given the question q = “Is Mike Chung in his office?” and the record in W that identifies Mike Chung as person and Mike Chung’s office as cse101, the desired information descriptor z is a tuple (cse101, person).”
BackgroundSelf-citationLiDAR-Based SLAM under Semantic Constraints in Dynamic Environments
Wang, W., You, X., Zhang, X., Chen, L., Zhang, L., & Liu, X. (2021) · Remote Sensing · doi:10.3390/rs13183651 · Cited by 13
Reconstruction and prediction of the layout of indoor environments from two-dimensional metric maps
Luperto, M., & Amigoni, F. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104910 · Cited by 12
Towards generalization of semi-supervised place classification over generalized Voronoi graph
Shi, L., & Kodagoda, S. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.04.013 · Cited by 10
“Typical form s of this information include temporal consistency [7, 29], spatial consistency [1, 18, 20 , 30, 31] and place-object relationships [29, 32].”
BackgroundPlace categorization using sparse and redundant representations
Carrillo, H., Latif, Y., Neira, J., & Castellanos, J. A. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6943266 · Cited by 10
Multiview vision-based human crowd localization for UAV fleet flight safety
Kakaletsis, E., Mademlis, I., Nikolaidis, N., & Pitas, I. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116484 · Cited by 10
Fast hybrid relocation in large scale metric-topologic-semantic map
Drouilly, R., Rives, P., & Morisset, B. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942804 · Cited by 12
“To capture global structure of the scene a common solution is to embed first stage prediction results into a probabilistic graphical model [5].”
BackgroundMethodSafe and Efficient Navigation in Extreme Environments using Semantic Belief Graphs
Ginting, M. F., Kim, S. K., Peltzer, O., Ott, J., Jung, S., Kochenderfer, M. J., & Agha–mohammadi, A. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161056 · Cited by 9
“Some earlier works introduce multi-hierarchical [4] and layered spatial representations [5].”
BackgroundPart-level Scene Reconstruction Affords Robot Interaction
Zhang, Z., Zhang, L., Wang, Z., Jiao, Z., Han, M., Zhu, Y., Zhu, S. C., & Liu, H. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342208 · Cited by 14
“However, traditional scene reconstruction methods primarily focus on generating static scenes, represented by sparse landmarks [1, 2], occupancy grids [3], surfels [4, 5], volumetric voxels [6, 7], or semantic objects [2].”
BackgroundActive robotic search for victims using ensemble deep learning techniques
García-Samartín, J. F., Ulloa, C. C., del Cerro, J., & Barrientos, A. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad33df · Cited by 8
“In [31], the environment is divided into rooms and their category is considered.”
BackgroundAn Inferring Semantic System Based on Relational Models for Mobile Robotics
Crespo, J., Castano, R. I. B., & Mozos, Ó. M. (2015) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2015.22 · Cited by 9
Rule-Based Door Detection Using Laser Range Data in Indoor Environments
Kaleci, B., Şenler, Ç. M., Dutağacı, H., & Parlaktuna, O. (2015) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2015.81 · Cited by 9
“Their method for door detection is based on line extraction.”
MethodBozcan, İ., Oymak, Y., Alemdar, İ. Z., & Kalkan, S. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460828 · Cited by 10
Patterns for Representing Knowledge Graphs to Communicate Situational Knowledge of Service Robots
Zhang, S., Wang, Z., Chen, C., Dai, Y., Ye, L., & Sun, X. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445767 · Cited by 11
“tional knowledge representation for robots[40, 47, 56], situation assessment in human-robot interaction[48, 52], and context-based human-robot collaboration[58, 59].”
BackgroundThe Interactive Urban Robot IURO: Towards Robot Action in Human Environments
Wollherr, D., Khan, S., Landsiedel, C., & BUSS, M. J. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-23778-7_19 · Cited by 9
Survey of 3D Map in SLAM: Localization and Navigation
Yang, A., Luo, Y., Chen, L., & Xu, Y. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6370-1_41 · Cited by 10
A visual place recognition procedure with a Markov chain based filter
dos Santos, F. N., Costa, P., & Moreira, A. P. (2014) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2014.6849808 · Cited by 8
“state of the art, such those presented by [24], [25], [26], [27], and [28].”
BackgroundA generative spectral model for semantic mapping of buildings
Luperto, M., D'Emilio, L., & Francesco Amigoni, A. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354009 · Cited by 8
“For example, the system presented in [15] is a probabilistic semantic mapping framework that applies semantic labels to six kinds of environment features (objects, doorways, room shapes, room size, appearance, and associated spaces).”
BackgroundFrom Perception to Semantics: An Environment Representation Model Based on Human-Robot Interactions
Breux, Y., Druon, S., & Zapata, R. (2018) · IEEE RO-MAN · doi:10.1109/roman.2018.8525527 · Cited by 10
“[7][8] build a multi-layer spatial representation of the world.”
BackgroundSemantic Map Annotation Through UAV Video Analysis Using Deep Learning Models in ROS
Kakaletsis, E., Tzelepi, M., Kaplanoglou, P. I., Symeonidis, C., Nikolaidis, N., Tefas, A., & Pitas, I. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05716-9_27 · Cited by 8
“Recently, the focus of the robotics community has shifted towards semantic representations [19], [16], [15] and object relation modeling in semantic maps [18], [1], [17] to develop autonomous interactive robots that are capable of understanding the semantics and relationships between the objects in…”
BackgroundKnowledge Representation for Robots through Human-Robot InteractionPreprint
Bastianelli, E., Bloisi, D. D., Capobianco, R., Gemignani, G., Iocchi, L., & Nardi, D. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1307.7351 · Cited by 8
“Pronobis and Jensfelt [21] present a multi-layered semantic mapping algo-rithm that combines information about the existence of objects and semantic properties about the space, such as room size, share and appearance.”
BackgroundTopological Map Generation for Intrinsic Visual Navigation of an Intelligent Service Robot
Luo, R. C., & Shih, W. (2019) · International Conference on Consumer Electronics · doi:10.1109/icce.2019.8662062 · Cited by 7
“[11] proposed a probabilistic framework which integrates vision and topological maps to achieve semantic mapping.”
BackgroundSceneSLAM: A SLAM framework combined with scene detection
Tong, Z., Shi, D., & Yang, S. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324464 · Cited by 7
“For example, [7] relies on SURF and CRFH, while [8] and [9] uses dense SIFT and CENTRIST [10], respectively.”
BackgroundMethodTask coordination for multiple mobile robots considering semantic and topological information
Ravankar, A. A., Ravankar, A. A., Peng, C.-C., Kobayashi, Y., & Emaru, T. (2018) · 2018 IEEE International Conference on Applied System Invention (ICASI) · doi:10.1109/icasi.2018.8394468 · Cited by 7
“For topological maps we used the system described in [4, 5, 11].”
MethodSaha, H., Fotouhi, F., Liu, Q., & Sarkar, S. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.930486 · Cited by 14
“Introduction of semantics in graph based maps can provide powerful solutions to encode relative locations of objects of interest in persistent memory [27, 17] and is useful when a higher level understanding of the surrounding is necessary.”
Local N-ary Patterns: a local multi-modal descriptor for place categorization
Jung, H., Mozos, Ó. M., Iwashita, Y., & Kurazume, R. (2016) · Advanced Robotics · doi:10.1080/01691864.2015.1120242 · Cited by 7
“Information on the types of places can greatly improve the communication between robots and humans [1,2] and can allow robots to make decisions with context-based understanding when completing high-level tasks.”
BackgroundPatki, S., & Howard, T. M. (2018) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/w18-5016 · Cited by 9
“…(Miller et al., 2003; Hueb-ner and Kragic, 2008) to more rich representations that model high level semantic properties (Galindo et al., 2005; Pronobis and Jensfelt, 2012), 6 DOF pose of the objects of interest (Hudson et al., 2012) or affordances between objects (Daniele et al., 2017).”
BackgroundSemantic Place Understanding for Human–Robot Coexistence—Toward Intelligent Workplaces
Rosa, S., Patanè, A., Lu, C. X., & Trigoni, N. (2018) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2018.2875079 · Cited by 16
“Using a template-based door detector [18] on laser distance data, the robot is able to group together multiple cells into individual rooms.”
BackgroundMethodInfluentialXu, S., Zuo, Z., Liang, X., & Huaidong, Z. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14796-1 · Cited by 7
“It provides the robot with the ability of complex task planning and intrinsic knowledge reasoning [21].”
BackgroundMethods and Applications of Space Understanding in Indoor Environment—A Decade Survey
Pokuciński, S., & Mrozek, D. (2024) · Applied Sciences · doi:10.3390/app14103974 · Cited by 8
Information Theoretic Question Asking to Improve Spatial Semantic Representations
Hemachandra, S. M., Walter, M. R., & Teller, S. J. (2014) · National Conference on Artificial Intelligence · Cited by 6
Semantic mapping for mobile outdoor robots
Lang, D., Friedmann, S., Hedrich, J., & Paulus, D. W. R. (2015) · Machine Vision Applications · doi:10.1109/mva.2015.7153196 · Cited by 6
“A large-scale semantic mapping approach for autonomous indoor service robots was presented by Pronobis and Jensfelt [7].”
BackgroundInteractive Semantic Mapping: Experimental Evaluation
Gemignani, G., Nardi, D., Bloisi, D. D., Capobianco, R., & Iocchi, L. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-23778-7_23 · Cited by 6
“As an example of “human-in-the-loop” approach, in [12] the authors describe a system for the creation of conceptual representations of indoor environments.”
Unsupervised discovery of object classes with a mobile robot
Mason, J., Marthi, B., & Parr, R. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907301 · Cited by 6
“[10]) and threedimensional features (e.”
Applying rule-based context knowledge to build abstract semantic maps of indoor environments
Liu, Z., & Wichert, G. V. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697100 · Cited by 6
“Pronobis and Jensfelt [16] integrated multi-modal sensory information and human intervention to classify places with semantic types.”
BackgroundRoom Categorization Based on a Hierarchical Representation of Space
Peter, U., Tabernik, D., Boben, M., Skočaj, D., Leonardis, A., & Kristan, M. (2013) · International Journal of Advanced Robotic Systems · doi:10.5772/55534 · Cited by 6
Luperto, M., Riva, A., & Francesco Amigoni, A. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989298 · Cited by 6
“For example, it is in principle easy to extend a framework like that of [4], which assigns labels according to different features derived from camera data, to include also a new feature based on global reasoning, which could propose a new label not based on sensorial data, but on the global structure of the portion of…”
BackgroundMethodInfluentialSemantic classification of mobile robot locations through 2D laser scans
Kaleci, B., Şenler, Ç. M., Dutağacı, H., & Parlaktuna, O. (2019) · Intelligent Service Robotics · doi:10.1007/s11370-019-00295-6 · Cited by 6
“Pronobis and Jensfelt [30] proposed a large-scale semantic mapping method.”
BackgroundBuilding Plannable Representations with Mixed Reality
Rosen, E., Kumar, N., Gopalan, N., Ullman, D. L., Konidaris, G., & Tellex, S. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341627 · Cited by 6
“Various works have made semantic map representations that use a hybrid of metric, topological, and conceptual representations [1], and incorporated human input to improve and teach these representations for the purpose of navigation [12, 15, 16].”
BackgroundInfluentialLuperto, M., Tellaroli, M., Antonazzi, M., & Basilico, N. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.105137 · Cited by 5
Melvin, S. A., Wang, H., & Yazdani, A. (2026) · Robotica · doi:10.1017/s0263574725102518 · Cited by 6
“High-dimensional histograms were used to represent an observed scene and achieved the classification of visual places through SVM [42].”
Semantic potential field for mobile robot navigation using grid maps
Nguyen, T.-S., Cao, H. N., & Pham, M.-T. (2025) · ETRI Journal · doi:10.4218/etrij.2024-0454 · Cited by 6
“For example, Pronobis and Jensfelt [11] demonstrated that distinguishing between different types of obstacles or recognizing areas frequently occupied by humans can significantly improve navigation efficiency and safety.”
Bartoli, E., Argenziano, F., Suriani, V., & Nardi, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-27181-6_17 · Cited by 5
Leveraging User Activities and Mobile Robots for Semantic Mapping and User Localization
Rosa, S., Lu, C. X., Wen, H., & Trigoni, N. (2017) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3029798.3038343 · Cited by 5
“We start from the semantic mapping framework presented in [3] and extend it to a human-robot interaction scenario by adding the presence of a suer and exploiting user activities as room properties.”
BackgroundMethodInfluentialRepresenting and updating objects' identities in semantic SLAM
Tslil, O., Elbaz, A., Feiner, T., & Carmi, A. Y. (2020) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion45008.2020.9190524 · Cited by 5
“In [18] the author used several traits to describe a semantic entities and deterministic objects.”
MethodIndoor Place Categorization Using Co-occurrences of LBPs in Gray and Depth Images from RGB-D Sensors
Jung, H., Mozos, Ó. M., Iwashita, Y., & Kurazume, R. (2014) · International Conference on Emerging Security Technologies · doi:10.1109/est.2014.23 · Cited by 5
“If a robot is able to recognize the category of its surroundings such as the offices, kitchens or laboratories, then it can reduce the ambiguity of the human instructions according to the places, and it can greatly improve its human-robot communication capabilities [1], [2].”
BackgroundZheng, K., Pronobis, A., & Rao, R. P. N. (2017) · arXiv (Cornell University) · Cited by 5
Self-citationSiddiqui, J. R., Andreasson, H., Driankov, D., & Lilienthal, A. J. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487800 · Cited by 4
“[20] topological place associations are taken as basis for developing an abstract representation of the environment.”
BackgroundNakashima, K., Jung, H., Oto, Y., Iwashita, Y., Kurazume, R., & Mozos, Ó. M. (2018) · Advanced Robotics · doi:10.1080/01691864.2018.1501279 · Cited by 4
“Information about the place greatly improves communication between robots and humans [1].”
Completing Robot Maps by Predicting the Layout of Rooms Behind Closed Doors
Luperto, M., Amadelli, F., & Amigoni, F. (2021) · European Conference on Mobile Robots · doi:10.1109/ecmr50962.2021.9568786 · Cited by 4
Designing information gathering robots for human-populated environments
Chung, M. J.-Y., Pronobis, A., Çakmak, M., Fox, D., & Rao, R. P. N. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354194 · Cited by 4
“They could also monitor the state of building and report unusual events (e.g. open office door at 2am) or maintenance needs (e.g. broken lightbulbs).”
BackgroundSelf-citationHierarchical spatial model for 2D range data based room categorization
Peter, U., Leonardis, A., Skočaj, D., & Kristan, M. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487650 · Cited by 4
“In [6] great performance is achieved by combining information about the existence of objects, the appearance, geometry, and topology of space.”
BackgroundRoCKIn@Home: Domestic Robots Challenge
Iocchi, L., Kraetzschmar, G. K., Nardi, D., Lima, P. U., Miraldo, P., Bastianelli, E., & Capobianco, R. (2017) · InTech eBooks · doi:10.5772/intechopen.70015 · Cited by 4
“[23] evaluate their method by comparing the belief of the robot of being in a certain location against the ground truth.”
BackgroundMethodExploration of Indoor Environments Predicting the Layout of Partially Observed RoomsPreprint
Luperto, M., Fochetta, L., & Francesco Amigoni, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.06967 · Cited by 6
“We finally mention some methods that infer the presence and location of spe-cific elements in the unknown part of environments, like emergency exits [7], labels of unseen rooms [23], and portions of environments represented as graphs [5, 18].”
Suriani, V., Musumeci, E., Nardi, D., & Bloisi, D. D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-55015-7_1 · Cited by 3
“To let the robots deal with the semantics of the environments, in [10] a semantic mapping system is divided into four layers on three levels, spanning from a sensory layer, to a categorical and a place layers is presented.”
BackgroundMillimeter-Wave Radar and Vision Fusion-Based Semantic Simultaneous Localization and Mapping
Wang, Y., Wu, Y., Li, D., & Yu, W. (2024) · IEEE Antennas and Wireless Propagation Letters · doi:10.1109/lawp.2024.3389678 · Cited by 8
“Initial semantic mapping approaches semantic labels and segmentation into traditional maps to form hierarchical hybrid maps [14], [15], but specialized solutions are needed for diverse robotic applications due to their complexity.”
Human-Like Room Segmentation for Domestic Cleaning Robots
Fleer, D. (2017) · Robotics · doi:10.3390/robotics6040035 · Cited by 3
“In a subsequent work [11], place types are defined by their properties.”
BackgroundA multi-strategy path planner based on space accessibility
Hang, M., Lin, M., Li, S., Chen, Z., & Ding, R. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324738 · Cited by 3
Planning object informed search for robots in household environments
Gutierrez, M. A., Manso, L. J., Núñez, P., & Bustos, P. (2018) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2018.8374184 · Cited by 3
“In order to speed up this process, robots have to optimize the search process generating hypotheses pointing them to the most-likely object locations [4], [5], [6].”
BackgroundCommonSense: Collaborative learning of scene semantics by robots and humans
Rosa, S., Patanè, A., Lu, C. X., & Trigoni, N. (2018) · doi:10.1145/3215525.3215526 · Cited by 9
“[ 10] presents a conceptual model for semantic map representation, with different levels of abstraction, from sensor data to concepts, such as rooms, with associated appearance, and detected objects.”
BackgroundMethodInfluentialLTC-Mapping, Enhancing Long-Term Consistency of Object-Oriented Semantic Maps in Robotics
Matez-Bandera, J.-L., Fernandez-Chaves, D., Ruiz-Sarmiento, J.-R., Monroy, J., Petkov, N., & González-Jiménez, J. (2022) · Sensors · doi:10.3390/s22145308 · Cited by 3
“Some typical robotic tasks that could benefit from the exploitation of these maps could be object search [6], navigation [7] or human–robot interaction [8], among others [3,9,10].”
BackgroundAutomated Generation of Room Usage Semantics from Point Cloud Data
Cai, G., & Pan, Y. (2023) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi12100427 · Cited by 3
A Semantic Labeling of the Environment Based on What People Do
Crespo, J., Gómez, C., Hernandez, A. C., & Barber, R. (2017) · Sensors · doi:10.3390/s17020260 · Cited by 3
“These features are typically [5] the place appearance, the place geometry, the object information, the topology, the human input, the segmentation, the conceptual map, the uncertain objects, the inferring properties, the concepts acquired, etc.”
BackgroundIncremental Semantic Mapping with Unsupervised On-line Learning
Sousa, Y. C. N., & Bassani, H. F. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489430 · Cited by 3
“However, the place categorization of the mapped environments is usually done by methods with non-incremental supervised learning [1], [6], [7].”
BackgroundMethodInfluentialModeling of a Large Structured Environment
Shahbandi, S. G., & Åstrand, B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10401-0_1 · Cited by 3
“Some others like [5], [14] and [9] proposed spatial maps, enhanced conceptually by object recognition in regions of the map.”
BackgroundLiu, Z., Wang, W., Chen, D., & Wichert, G. V. (2013) · European Conference on Mobile Robots · doi:10.1109/ecmr.2013.6698848 · Cited by 4
“Pronobis and Jensfelt [18] integrated multi-modal sensory information, human intervention and some common-sense knowledge to classify places with semantic types.”
BackgroundLocal map extrapolation in dynamic environments
Drouilly, R., Papadakis, P., Rives, P., & Morisset, B. (2014) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2014.6974405 · Cited by 3
“[8] probably constitutes the most elaborate attempt to account for the static semantic content of an environment in robot mapping using a property-based scheme.”
BackgroundCombining World and Interaction Models for Human-Robot Collaborations
Matuszek, C., Pronobis, A., Zettlemoyer, L., & Fox, D. (2013) · Maryland Shared Open Access Repository (USMAI Consortium) · doi:10.13016/m2mw28j2d · Cited by 4
“As proposed in (Pronobis and Jensfelt 2012), these links (textured vertices in Fig.”
BackgroundMethodInfluentialSelf-citationTransferring knowledge across robots: A risk sensitive approach
Costante, G., Ciarfuglia, T. A., Valigi, P., & Ricci, E. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.12.004 · Cited by 3
“Many works have been proposed in the literature to solve the place categorization problem [1,2].”
BackgroundRoom categorization using local receptive fields-based extreme learning machine
He, X., Liu, H., & Huang, W. (2017) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm.2017.8273234 · Cited by 3
“A pattern of combining multiple messages together at a certain probability is proposed in [11] which could accurately implement the room classification.”
BackgroundHigh-Level MLN-Based Approach for Spatial Context Disambiguation
Adjali, O., & Ramdane-Chérif, A. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460923 · Cited by 3
Chen, H., Su, L., Zhang, B., Sun, F., Yuan, J., & Liu, J. (2020) · IEEE Access · doi:10.1109/access.2020.2985227 · Cited by 3
“These methods use metric maps obtained by SLAM and add semantic information [12], [19].”
MethodLearning part-based spatial models for laser-vision-based room categorization
Peter, U., Leonardis, A., Skočaj, D., & Kristan, M. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364917704707 · Cited by 2
Plane Object-Based High-Level Map Representation for SLAM
Gritsenko, P., Gritsenko, I., Seidakhmet, A., & Kwolek, B. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00692-1_9 · Cited by 2
A Research of Visual-Inertial Simultaneous Localization and Mapping
Li, J., & Hamdulla, A. (2022) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml56267.2022.9882205 · Cited by 2
Text Detection and Recognition for Semantic Mapping in Indoor Navigation
Sami, M., Ayaz, Y., Jamil, M., Gilani, S. O., & Muhammad, N. (2015) · International Conference on IT Convergence and Security (ICITCS) · doi:10.1109/icitcs.2015.7293024 · Cited by 2
“There are also other ways for building a semantic map like using metric maps and injecting semantic information on it [4].”
BackgroundSupervised feature type selection for topological mapping in indoor environments
Özkucur, N. E., & Akın, H. L. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531556 · Cited by 2
“Değişik algılayıcılardan gelen verileri birleştirme yöntemleri [8] ve öznitelik sınıflandırması yöntemleriyle [9] karşılaştırıldığında bizim yöntemimiz ham algılayıcı verisi yerine aynı algılayıcıdan değişik tipte özellik çıkarma yöntemleri ile çalışabilmektedir.”
Shahbandi, S. G., Åstrand, B., & Philippsen, R. (2015) · European Conference on Mobile Robots · doi:10.1109/ecmr.2015.7324207 · Cited by 2
“The last example is the probabilistic framework for semantic inference proposed by [18] which covers a large variety of techniques on different levels.”
BackgroundHuman-centric partitioning of the environment
Karaoğuz, H., Bore, N., Folkesson, J. B., & Jensfelt, P. (2017) · IEEE RO-MAN · doi:10.1109/roman.2017.8172401 · Cited by 2
“The second group consists of global approaches where the aim is to partition a complete floor plan rather than single scenes [9], [10], [11], [12], [13], [14].”
BackgroundMethodSelf-citationMultimodal Object-Based Environment Representation for Assistive Robotics
Breux, Y., & Druon, S. (2019) · International Journal of Social Robotics · doi:10.1007/s12369-019-00600-4 · Cited by 2
“Pronobis et al. [37,38] introduce a multilayer architecture for indoor semantic mapping by reasoning on heterogeneous data such as object occurrences or room dimensions.”
BackgroundDeep understanding of everyday activity commands for household robots
Höffner, S., Porzel, R., Hedblom, M. M., Pomarlan, M., Cangalovic, V. S., Pfau, J., Bateman, J. A., & Malaka, R. (2022) · Semantic Web · doi:10.3233/sw-222973 · Cited by 6
“This makes sense, as the semantic mapping approaches have become very good in creating semantic maps from real world data, grounding them ontologically, and in refining them using CAD models [1,11,16,40].”
MethodObject-Oriented Navigation with a Multi-layer Semantic Map
Song, K., & Kang, L.-R. (2022) · Asian Control Conference (ASCC) · doi:10.23919/ascc56756.2022.9828170 · Cited by 2
Interaction patterns in human augmented mapping
Topp, E. A. (2017) · Advanced Robotics · doi:10.1080/01691864.2017.1281758 · Cited by 2
Metadata
- Authors
- Pronobis, A., & Jensfelt, P.
- Affiliations
- KTH Royal Institute of Technology (SE)
- ORCID
- Jensfelt, Patric
- Venue
- 2012 IEEE International Conference on Robotics and Automation
- Publisher
- IEEE
- Published
- 2012-05
- Pages
- 3515-3522
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2000321478
- Cited by
- 248
- References
- 27
- Citations by year
- 2026: 5 · 2025: 9 · 2024: 6 · 2023: 6 · 2022: 20 · 2021: 17 · 2020: 23 · 2019: 16 · 2018: 34 · 2017: 27 · 2016: 22 · 2015: 23 · 2014: 25 · 2013: 14 · 2012: 1
- FWCI
- 37.56
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Keywords
- semantic mapping, heterogeneous modalities, multimodal sensor fusion, probabilistic graphical models, chain graphs, spatial reasoning, commonsense knowledge, object prediction, spatial characteristics, human-robot interaction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.