Towards semantic maps for mobile robots

By Andreas Nüchter, Joachim Hertzberg. Robotics Auton. Syst., 2008

483 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/1d724690f8e61f66f439a2d858bee4810733b617

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 Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

Dense 3D semantic mapping of indoor scenes from RGB-D images (2014, background): “[3] create 3D maps from laser scan data and reason about planes they find in the scene.”
3D Semantic Parsing of Large-Scale Indoor Spaces (2016, unknown): “3.2).”
Multiple‐Robot Simultaneous Localization and Mapping: A Review (2016, background): “Semantic maps, which contain functionalities and relationships of the objects of the environment, are the most abstract type (Nuchter & Hertzberg, 2008).”
Active vision in robotic systems: A survey of recent developments (2011, background): “Metric maps are supposed to represent the environment geometry quantitatively correctly, up to discretization errors (Nuchter and Hertzberg 2008).”
Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, unknown): “In [275] and [276], the authors take advantage of a 3D laser to identify the ceiling, the ﬂoor and objects.”
Close-range scene segmentation and reconstruction of 3D point cloud maps for mobile manipulation in domestic environments (2009, methodology): “This has the advantage that since the clusters are independent with respect to each other, we can perform the subsequent planar segmentation step in parallel for more than one cluster, thus decreasing the computational requirements of this step considerably.”
Artificial cognition for social human-robot interaction: An implementation (2017, methodology): “Numerous approaches exist, like amodal (in the sense of modality-independent) proxies [54], grounded amodal representations [55], semantic maps [56, 57, 58] or affordance-based planning and object classification [59, 60].”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, background): “Nüchter and Hertzberg (2008) encode relations among planar surfaces (e.g., walls, floor, ceiling) and detect objects in the scene.”
Automatic Reconstruction of As-Built Building Information Models from Laser-Scanned Point Clouds: A Review of Related Techniques | NIST (2010, methodology): “An example of recognition using context (reprinted from [68], © 2008, with permission from Elsevier).”
Automatic Creation of Semantically Rich 3D Building Models from Laser Scanner Data (2011, result): “Context-based building modeling has been studied by several other researchers (N¨uchter and Hertzberg, 2008; N¨uchter et al., 2003; Pu and Vos-selman, 2006; Cantzler, 2003; Rusu et al., 2008).”
Real-Time Plane Segmentation Using RGB-D Cameras (2012, background): “extract environmental structures such as walls, ceilings and drivable surfaces from 3D laser range scans and use trained classifiers to detect objects like, for instance, humans and other robots [8].”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, background): “Nüchter and Hertzberg [75] encode relations among planar surfaces (e.”
Robot Programming by Demonstration (2010, methodology): “Authors of [16] make use of a combination of RANSAC and Iterative Closest Point (ICP) registration to extract planes offline and label them, whereas [19] propose plane fitting as an incremental region growing followed by polygonalization step to exploit the neighborhood relation for proper surface m”
Automatic dense visual semantic mapping from street-level imagery (2012, methodology): “This makes our application unique compared to those that use other modalities for recognition and semantic mapping [4], [9], [17], [18], [19].”