Sparse-Map: automatic topological map creation via unsupervised learning techniques. (17th September 2022)
- Record Type:
- Journal Article
- Title:
- Sparse-Map: automatic topological map creation via unsupervised learning techniques. (17th September 2022)
- Main Title:
- Sparse-Map: automatic topological map creation via unsupervised learning techniques
- Authors:
- Hernández, Jesús
Savage, Jesús
Negrete, Marco
Contreras, Luis
Sarmiento, Carlos
Fuentes, Oscar
Okada, Hiroyuki - Abstract:
- Abstract : Most robots use 2D occupancy grid maps for navigation, localization, and path-planning. This model is flexible and allows to represent any geometrical shape with finite accuracy. However, this dense representation imposes high memory requirements and does not generalize well to 3D environments. We present a task-based map compression technique useful for path-planning and navigation in indoor environments for service robots where, from a point cloud of 3D map features, we calculate a number of clusters based on their spatial position and generate a sparse 3D representation of the environment. Moreover, we propose several metrics to assess the quality and performance of a map representation, and we tested our proposal using a series of point-cloud benchmarks and clustering techniques where our method has a comparable performance using a fraction of the memory footprint than the baselines. Finally, we have released our system as a Robot Operating System (ROS) based open source library. GRAPHICAL ABSTRACT: UF0001
- Is Part Of:
- Advanced robotics. Volume 36:Number 17/18(2022)
- Journal:
- Advanced robotics
- Issue:
- Volume 36:Number 17/18(2022)
- Issue Display:
- Volume 36, Issue 17/18 (2022)
- Year:
- 2022
- Volume:
- 36
- Issue:
- 17/18
- Issue Sort Value:
- 2022-0036-NaN-0000
- Page Start:
- 825
- Page End:
- 835
- Publication Date:
- 2022-09-17
- Subjects:
- Robot mapping -- mobile robot navigation -- spatial clustering -- unsupervised learning
Robotics -- Periodicals
Robotics -- Japan -- Periodicals
Robotics
Japan
Periodicals
629.89205 - Journal URLs:
- http://www.catchword.com/rpsv/cw/vsp/01691864/contp1.htm ↗
http://catalog.hathitrust.org/api/volumes/oclc/14883000.html ↗
http://www.tandfonline.com/toc/tadr20/current ↗
http://www.tandfonline.com/ ↗
http://firstsearch.oclc.org ↗
http://firstsearch.oclc.org/journal=0169-1864;screen=info;ECOIP ↗
http://www.ingentaselect.com/vl=16659242/cl=11/nw=1/rpsv/cw/vsp/01691864/contp1.htm ↗ - DOI:
- 10.1080/01691864.2022.2114296 ↗
- Languages:
- English
- ISSNs:
- 0169-1864
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 0696.926500
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 24095.xml