Abstract
Semantic mapping has received much attention in the recent years due to the fact that more and more robots need to operate in complex environments and co-exist with humans or other robots. This requires contemporary robots not only to be able to navigate safely in their environment, but also to adopt a human-like understanding of their surroundings i.e. to have a semantic apprehension of the mapped environment. This paper at hand, focuses on building successfully semantic maps by combining spatial knowledge on the occupancy grid map with deep learning and computer vision techniques. The presented method exploits the vision based data captured by robot’s perception system, to ease its installation in the operational environment. Unlike previous methods, the proposed one does not require any prior knowledge of the environment concerning the semantics of places, as it is semi-supervised and the labeling of the segmented areas is being performed manually after the process is completed. The method has been evaluated in real indoor environments by measuring the Jaccard and Dice indices for the performed segmentation and exhibited remarkable performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdelrasoul, Y., Saman, A.B.S.H., Sebastian, P.: A quantitative study of tuning ROS gmapping parameters and their effect on performing indoor 2D slam. In: 2016 2nd IEEE international symposium on Robotics and Manufacturing Automation (ROMA), pp. 1–6. IEEE (2016)
Ambruş, R., Claici, S., Wendt, A.: Automatic room segmentation from unstructured 3-D data of indoor environments. IEEE Robot. Autom. Lett. 2(2), 749–756 (2017)
Bogue, R.: Domestic robots: Has their time finally come? Ind. Robot Int. J. (2017)
Fernandez-Chaves, D., Ruiz-Sarmiento, J.R., Petkov, N., Gonzalez-Jimenez, J.: From object detection to room categorization in robotics. In: Proceedings of the 3rd International Conference on Applications of Intelligent Systems, pp. 1–6 (2020)
Frias Nores, E., Balado Frías, J., Díaz Vilariño, L., Lorenzo Cimadevila, H.R., et al.: Point cloud room segmentation based on indoor spaces and 3D mathematical morphology (2020)
Grisetti, G., Stachniss, C., Burgard, W.: Improved techniques for grid mapping with rao-blackwellized particle filters. IEEE Trans. Robot. 23(1), 34–46 (2007)
Hiller, M., Qiu, C., Particke, F., Hofmann, C., Thielecke, J.: Learning topometric semantic maps from occupancy grids. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4190–4197. IEEE (2019)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Hou, J., Yuan, Y., Schwertfeger, S.: Area graph: Generation of topological maps using the voronoi diagram. In: 2019 19th International Conference on Advanced Robotics (ICAR). pp. 509–515. IEEE (2019)
Jung, J., Stachniss, C., Kim, C.: Automatic room segmentation of 3d laser data using morphological processing. ISPRS Int. J. Geo-Inf. 6(7), 206 (2017)
Kostavelis, I., Gasteratos, A.: Semantic mapping for mobile robotics tasks: a survey. Robot. Autonom. Syst. 66, 86–103 (2015)
Kostavelis, I., Gasteratos, A.: Semantic maps from multiple visual cues. Exp. Syst. Appl. 68, 45–57 (2017)
Kostavelis, I., Giakoumis, D., Malassiotis, S., Tzovaras, D.: Human aware robot navigation in semantically annotated domestic environments. In: International Conference on Universal Access in Human-Computer Interaction, pp. 414–423. Springer (2016). https://doi.org/10.1007/978-3-030-49108-6
Kostavelis, I., Kargakos, A., Giakoumis, D., Tzovaras, D.: Robot’s Workspace enhancement with dynamic human presence for socially-aware navigation. In: Liu, M., Chen, H., Vincze, M. (eds.) ICVS 2017. LNCS, vol. 10528, pp. 279–288. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68345-4_25
Kostavelis, I., et al.: Understanding of human behavior with a robotic agent through daily activity analysis. Int. J. Soc. Robot. 11(3), 437–462 (2019)
Lu, V.N., et al.: Service robots, customers and service employees: what can we learn from the academic literature and where are the gaps? J. Ser. Theor. Prac. (2020)
Luperto, M., Amigoni, F.: Predicting the global structure of indoor environments: a constructive machine learning approach. Autonom. Robot. 43(4), 813–835 (2018). https://doi.org/10.1007/s10514-018-9732-7
Manyika, J., Chui, M., Miremadi, M., et al.: A future that works: AI, automation, employment, and productivity. McKinsey Global Institute Research, Tech. Rep. 60 (2017)
Mielle, M., Magnusson, M., Lilienthal, A.J.: A method to segment maps from different modalities using free space layout Maoris: map of ripples segmentation. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4993–4999. IEEE (2018)
Mozos, O.M., Triebel, R., Jensfelt, P., Rottmann, A., Burgard, W.: Supervised semantic labeling of places using information extracted from sensor data. Robot. Autonom. Syst. 55(5), 391–402 (2007)
Qi, X., et al.: Building semantic grid maps for domestic robot navigation. Int. J. Adv. Robot. Syst. 17(1), 1729881419900066 (2020)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Søraa, R.A., Fostervold, M.E.: Social domestication of service robots: the secret lives of automated guided vehicles (AGVs) at a Norwegian hospital. Int. J. Hum-Comput. Stud. 152, 102627 (2021)
Sünderhauf, N., et al.: Place categorization and semantic mapping on a mobile robot. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 5729–5736. IEEE (2016)
Tian, Y., Wang, K., Li, R., Zhao, L.: A fast incremental map segmentation algorithm based on spectral clustering and quadtree. Adv. Mech. Eng. 10(2), 1687814018761296 (2018)
Tsamis, G., Kostavelis, I., Giakoumis, D., Tzovaras, D.: Towards life-long mapping of dynamic environments using temporal persistence modeling. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10480–10485. IEEE (2021)
Yue, Y., Zhao, C., Wu, Z., Yang, C., Wang, Y., Wang, D.: Collaborative semantic understanding and mapping framework for autonomous systems. In: IEEE/ASME Transactions on Mechatronics (2020)
Acknowledgments
This work has been supported from General Secretariat for Research and Technology under Grant agreement no. T6YB-00238 “Q-CONPASS: Dynamic Quality CONtrol on Production lines using intelligent AutonomouS vehicleS”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Theodoridou, C., Kargakos, A., Kostavelis, I., Giakoumis, D., Tzovaras, D. (2021). Spatially-Constrained Semantic Segmentation with Topological Maps and Visual Embeddings. In: Vincze, M., Patten, T., Christensen, H.I., Nalpantidis, L., Liu, M. (eds) Computer Vision Systems. ICVS 2021. Lecture Notes in Computer Science(), vol 12899. Springer, Cham. https://doi.org/10.1007/978-3-030-87156-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-87156-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87155-0
Online ISBN: 978-3-030-87156-7
eBook Packages: Computer ScienceComputer Science (R0)