The Spatial Semantic Hierarchy

By Benjamin Kuipers. Artificial Intelligence, 2000

892 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/59b0aa3ab27bf8f2e6ed683b8b5a6b9197311a09

How researchers see this paper

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

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Robust Mapping and Localization in Indoor Environments Using Sonar Data (2002, methodology): “Popular choices for the map representation include grid-based (Elfes 1987; Schultz and Adams 1998), topological (Kuipers 2000; Choset and Nagatani 2001), featurebased models (Moutarlier and Chatila 1989; Ayache and Faugeras 1989), and sequential Monte Carlo methods (Thrun 2001; Doucet, de Freitas,…”
Do Humans Integrate Routes Into a Cognitive Map? Map- Versus Landmark-Based Navigation of Novel Shortcuts (2005, background): “However, once the landmarks were passed, path corrections ceased, and errors started to accumulate (as may be expected when landmarks are unavailable for corrective sightings; see Kuipers, 2000; Nadel, 1990; Trullier et al., 1997), as in the desert world of Experiment 1. As a consequence, shifting”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, background): “The state space of the robot consists of a set of discrete, locally distinctive locations such as corners or crossings of hallways (Kaelbling, Cassandra, and Kurien 1996; Simmons and Koenig 1995; Kuipers 2000; Hertzberg and Kirchner 1996; Choset and Nagatani 2001; Kuipers and Beeson 2002).”
Learning predictive models of a depth camera & manipulator from raw execution traces (2014, methodology): “Proposed solutions have focused on the topology of the environment [21], the manifold structure of observation space [22], or diffeomorphisms that describe the effect of taking actions [17].”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, background): “, [16, 28, 49, 50, 100, 110]) investigates hierarchical representations but mostly in 2D and assuming static environments; moreover, these works were proposed before the “deep learning revolution”, hence they could not afford advanced semantic understanding.”
Cognitive Mapping and Planning for Visual Navigation (2017, methodology): “[42, 43] introduce a cognitive mapping model using hierarchical abstractions of maps.”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, background): “Early work on map representation in robotics, e.g., (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 ”
RFID in robot-assisted indoor navigation for the visually impaired (2004, background): “Since RG’s objective is to assist the visually impaired in navigating unknown environments, we had to pay close attention to three navigational features.”
Cognition of Geographic Information (2005, background): “Some of the earliest and most influential work of this type is by Kuipers (1978, 2000) .”
Cooperative concurrent mapping and localization (2002, background): “Another possibility is to use a topological representation [24], [ 25 ].”
An Atlas framework for scalable mapping (2003, background): “One of the appealing aspects of a hybrid metrical/topological approach to mapping and localization [1], [9] is that uncertain state estimates do not need to be referenced to a single global reference frame.”
Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization (2022, neutral): “Hierarchical maps have been pervasive in robotics since its inception [12, 28, 29, 62].”
Conceptual spatial representations for indoor mobile robots (2008, background): “Kuipers [7] presents the Spatial Semantic Hierarchy (SSH).”
Learning Semantic Maps from Natural Language Descriptions (2013, background): “Several researchers have augmented lower-level metric maps with higher-level topological and/or semantic information [7, 8, 9, 10, 11].”
Visual Place Recognition: A Survey (2016, background): “However, metric information about the position of landmarks or objects in a place can also be stored within each node [1], [2], [26], [140], [153]–[156].”