Back to Top
Andrzej Pronobis

Semantic Mapping with Mobile Robots

A. Pronobis

PhD thesis, KTH Royal Institute of Technology, 2011.


After decades of unrealistic predictions and expectations, robots have finally escaped from industrial workplaces and made their way into our homes, offices, museums and other public spaces. These service robots are increasingly present in our environments and many believe that it is in the area of service and domestic robotics that we will see the largest growth within the next few years. In order to realize the dream of robot assistants performing human-like tasks together with humans in a seamless fashion, we need to provide them with the fundamental capability of understanding complex, dynamic and unstructured environments. More importantly, we need to enable them the sharing of our understanding of space to permit natural cooperation. To this end, this thesis addresses the problem of building internal representations of space for artificial mobile agents populated with human spatial semantics as well as means for inferring that semantics from sensory information. More specifically, an extensible approach to place classification is introduced and used for mobile robot localization as well as categorization and extraction of spatial semantic concepts from general place appearance and geometry. The models can be incrementally adapted to the dynamic changes in the environment and employ efficient ways for cue integration, sensor fusion and confidence estimation. In addition, a system and representational approach to semantic mapping is presented. The system incorporates and integrates semantic knowledge from multiple sources such as the geometry and general appearance of places, presence of objects, topology of the environment as well as human input. A conceptual map is designed and used for modeling and reasoning about spatial concepts and their relations to spatial entities and their semantic properties. Finally, the semantic mapping algorithm is built into an integrated robotic system and shown to substantially enhance the performance of the robot on the complex task of active object search. The presented evaluations show the effectiveness of the system and its underlying components and demonstrate applicability to real-world problems in realistic human settings.

Included Papers


  • Dora, the robot, exploiting probabilistic semantic spatial knowledge under uncertain sensing for efficient object search. The robot is instructed to find cornflakes in a house. Instead of just exhaustively searching everywhere, Dora is equipped with probabilistic reasoning and planning using the probabilistic knowledge captured in the semantic map.

  • Video illustrating the real-time experiments during which the robot constructs a semantic map of a large-scale indoor office environment. The semantic mapping algorithm exploits object information, appearance, geometry and topology. The video is best viewed full screen in HD on the YouTube page.

  • A mobile robot searching for an object in a large-scale unknown indoor environment. The system is based on a tight integration between a domain-independent planning algorithm and a semantic mapping component.

  • Video presenting real-time experiments with multi-modal place classification and semantic annotation of space using vision and laser range data.


  author =       {Pronobis, Andrzej},
  title =        {Semantic Mapping with Mobile Robots},
  school =       {KTH Royal Institute of Technology},
  address =      {Stockholm, Sweden},
  month =        dec,
  year =         2011,
  isbn =         {ISBN 978-91-7501-039-7},
  issn =         {ISSN-1653-5723},
  url =          {}