Predicting the global structure of indoor environments: A constructive machine learning approach

Consider a mobile robot exploring an initially unknown school building and assume that it has already discovered some corridors, classrooms, offices, and bathrooms. What can the robot infer about the presence and the locations of other classrooms and offices and, more generally, about the structure of the rest of the building? This paper presents a system that makes a step towards providing an answer to the above question. The proposed system is based on a generative model that is able to represent the topological structures and the semantic labeling schemas of buildings and to generate plausible hypotheses for unvisited portions of these environments. We represent the buildings as undirected graphs, whose nodes are rooms and edges are physical connections between them. Given an initial knowledge base of graphs, our approach, relying on constructive machine learning techniques, segments each graph for finding significant subgraphs and clusters them according to their similarity, which is measured using graph kernels. A graph representing a new building or an unvisited part of a building is eventually generated by sampling subgraphs from clusters and connecting them.

[1]  Patric Jensfelt,et al.  Active Visual Object Search in Unknown Environments Using Uncertain Semantics , 2013, IEEE Transactions on Robotics.

[2]  Francesco Amigoni,et al.  Towards more realistic indoor environments for the Virtual Robot Competition , 2014 .

[3]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[4]  Fabrizio Costa,et al.  Fast Neighborhood Subgraph Pairwise Distance Kernel , 2010, ICML.

[5]  Matthew R. Walter,et al.  Learning spatial-semantic representations from natural language descriptions and scene classifications , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Kristoffer Sjöö.  Semantic map segmentation using function-based energy maximization , 2012, 2012 IEEE International Conference on Robotics and Automation.

[8]  Patric Jensfelt,et al.  Large-scale semantic mapping and reasoning with heterogeneous modalities , 2012, 2012 IEEE International Conference on Robotics and Automation.

[9]  Kurt Mehlhorn,et al.  Weisfeiler-Lehman Graph Kernels , 2011, J. Mach. Learn. Res..

[10]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[11]  Alberto Quattrini Li,et al.  A System for Building Semantic Maps of Indoor Environments Exploiting the Concept of Building Typology , 2013, RoboCup.

[12]  Marleen de Bruijne,et al.  Scalable kernels for graphs with continuous attributes , 2013, NIPS.

[13]  John Folkesson,et al.  What can we learn from 38,000 rooms? Reasoning about unexplored space in indoor environments , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Wolfram Burgard,et al.  Supervised semantic labeling of places using information extracted from sensor data , 2007, Robotics Auton. Syst..

[15]  Wolfram Burgard,et al.  Coordinated multi-robot exploration using a segmentation of the environment , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Paolo Frasconi,et al.  Weighted decomposition kernels , 2005, ICML.

[17]  Wolfram Burgard,et al.  Speeding-Up Robot Exploration by Exploiting Background Information , 2016, IEEE Robotics and Automation Letters.

[18]  Cyrill Stachniss,et al.  Predictive exploration considering previously mapped environments , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Wolfram Burgard,et al.  Speeding-up multi-robot exploration by considering semantic place information , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[20]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[21]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[22]  Cipriano Galindo,et al.  Multi-hierarchical semantic maps for mobile robotics , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Francesco Amigoni,et al.  A generative spectral model for semantic mapping of buildings , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Francesco Amigoni,et al.  Exploiting Structural Properties of Buildings Towards General Semantic Mapping Systems , 2014, IAS.

[25]  Agusti Solanas,et al.  Coordinated multi-robot exploration through unsupervised clustering of unknown space , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[26]  Barbara Caputo,et al.  Multi-modal Semantic Place Classification , 2010, Int. J. Robotics Res..

[27]  Thomas Gärtner,et al.  Kernels and Distances for Structured Data , 2004, Machine Learning.

[28]  Wolfram Burgard,et al.  Conceptual spatial representations for indoor mobile robots , 2008, Robotics Auton. Syst..

[29]  Fabrizio Costa,et al.  Learning an efficient constructive sampler for graphs , 2017, Artif. Intell..

[30]  Alberto Quattrini Li,et al.  A semantically-informed multirobot system for exploration of relevant areas in search and rescue settings , 2016, Auton. Robots.

[31]  Luc De Raedt.  Logical and Relational Learning , 2008, SBIA.

[32]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[33]  Hisashi Kashima,et al.  Marginalized Kernels Between Labeled Graphs , 2003, ICML.

[34]  M. Newman,et al.  Mixing patterns in networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[35]  Wolfram Burgard,et al.  Supervised Learning of Places from Range Data using AdaBoost , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.