Conceptual spatial representations for indoor mobile robots

By Hendrik Zender, Óscar Martínez Mozos, Patric Jensfelt, Geert-Jan M. Kruijff, Wolfram Burgard. Robotics Auton. Syst., 2008

363 citations recorded by the source corpus.

We present an approach for creating conceptual representations of human-made indoor environments using mobile robots. The concepts refer to spatial and functional properties of typical indoor environments. Following different findings in spatial cognition, our model is composed of layers representing maps at different levels of abstraction. The complete system is integrated in a mobile robot endowed with laser and vision sensors for place and object recognition. The system also incorporates a linguistic framework that actively supports the map acquisition process, and which is used for situated dialogue. Finally, we discuss the capabilities of the integrated system.

Subfields: Aerospace Engineering, Automotive Engineering, Geography, Planning and Development

View Paper: https://www.semanticscholar.org/paper/2654665ad0f13c68a16bb01ff583115b0459072d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Automotive Engineering

Citations in the corpus

Semantic mapping for mobile robotics tasks: A survey (2015, methodology): “In a similar fashion, the method described by Zender et al. [4] recognizes places and objects by means of laser and visual data, respectively, with the aim to enhance the metric map constructed.”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, positive): “In [277], a conceptual space representation is proposed based on three different maps: metric (from a SLAM system), navigation (free space) and topological (connections between door-separated areas).”
Learning Semantic Maps from Natural Language Descriptions (2013, background): “[9] describe a framework for office environments in which the semantic layer models room categories and their relationship with the labels of objects within rooms.”
Learning models for following natural language directions in unknown environments (2015, background): “Related to our algorithm’s ability to learn world models, state-of-the-art semantic mapping frameworks exist that focus on using the robot’s sensor observations to update its representation of the world [13], [14].”
Robot task planning and explanation in open and uncertain worlds (2017, background): “Details of the underlying simultaneous localization and mapping techniques and obstacle perception methods are given in [15, 37, 55].”
A review of verbal and non-verbal human-robot interactive communication (2014, background): “…of recent spatial semantics research, the interested reader is referred to [79], and a sampler of important current work in robotics includes [80], [81], [82], and the most recent work of Tellex on grounding with probabilistic graphical models [83], and for learning word meanings from unaligned…”
Robot task planning and explanation in open and uncertain worlds (2015, background): “Details of the underlying simultaneous localization and mapping techniques and obstacle perception methods are given in [15, 37, 55].”
KnowRob: A knowledge processing infrastructure for cognition-enabled robots (2013, background): “, 2008) or the co-occurrence of objects (Vasudevan and Siegwart, 2008) to environment representations in DL (Zender et al., 2008), statistical relational environment models (Limketkai et al.”
A framework for learning semantic maps from grounded natural language descriptions (2014, methodology): “A straightforward automatic strategy is to segment regions based upon distance, placing vertices at a fixed spacing as the robot travels in the environment (Zender et al., 2008).”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, background): “, (Kuipers 2000, 1978; Chatila and Laumond 1985; Vasudevan et al. 2006; Galindo et al. 2005; Zender et al. 2008), investigated hierarchical representations but mostly in 2D and assuming static environments; moreover, these works were proposed before the “deep learning revolution”, hence they could n”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, background): “Note that the spatial hierarchies in [28] and [110] already resemble a scene graph, with less articulated set of nodes and layers.”
Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization (2022, neutral): “Early work focuses on 2D maps and investigates the use of hierarchical maps to resolve the apparent divide between metric and topological representations [18, 52, 70].”
Learning spatial-semantic representations from natural language descriptions and scene classifications (2014, background): “Semantic mapping algorithms [7, 8, 9, 10] extend the metric environment models traditionally employed in robotics to include higher-level concepts, including types and colloquial names for regions, and the presence and use of objects in the environment.”
Simultaneous Plan Recognition and Monitoring (SPRAM) for Robot Assistants (2013, background): “So for a robot interacting in a human-populated environment, it must understand its environment in terms of human spatial concepts [19].”
Place categorization and semantic mapping on a mobile robot (2015, result): “In contrast to the aforementioned purely vision-based methods, Zender et al. [12] combine laser-based place categorization with vision-based object detection and a “commonsense ontology” to build a so called conceptual map of the environment that contains semantic information.”
Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm (2005, neutral): “Moreover, such studies have contributed greatly to a better understanding of intermolecular interactions between liquid-crystal solvent and solute.”