Hierarchical SLAM: real-time accurate mapping of large environments

Estrada, Carlos A.; Neira, José; Tardós, Juan D.

doi:10.1109/tro.2005.844673

Cited by 310 publications

(262 citation statements)

References 24 publications

Supporting

Mentioning

256

Contrasting

Unclassified

Order By: Relevance

“…Simultaneous localization and mapping (SLAM) has been a topic of much interest because it provides an autonomous vehicle with the ability to discern and represent its location in a feature rich environment. Some of the statistical techniques used in SLAM include extended Kalman filters, particle filters (Monte Carlo methods) and scan matching of range data [21]. However, in the context of metric map building, SLAM's performance depends on the accuracy of the environmental sensors and requires very high data processing and also communication between the robots.…”

Section: Localization and Multi-robot Mappingmentioning

confidence: 99%

Multi-robot olfactory search in structured environments

Marjovi

Marques

2011

Robotics and Autonomous Systems

View full text Add to dashboard Cite

This paper presents a cooperative distributed approach for searching odor sources in unknown structured environments with multiple mobile robots . While searching and exploring the environment, the robots independently generate on-line local topological maps and by sharing them with each other they construct a global map. The proposed method is a decentralized frontier based algorithm enhanced by a cost/utility evaluation function that considers the odor concentration and airflow at each frontier. Therefore, frontiers with higher probability of containing an odor source will be searched and explored first. The method also improves path planning of the robots for exploration process by presenting a priority policy. Since there is no global positioning system and each robot has its own coordinate reference system for its localization, this paper uses topological graph matching techniques for map merging. The proposed method was tested in both simulation and real world environments with different number of robots and different scenarios. The search time, exploration time, complexity of the environment and number of double-visited map nodes were investigated in the tests. The experimental results validate the functionality of the method in different configurations.

show abstract

Section: Localization and Multi-robot Mappingmentioning

confidence: 99%

Multi-robot olfactory search in structured environments

Marjovi

Marques

2011

Robotics and Autonomous Systems

View full text Add to dashboard Cite

show abstract

“…Submap methods usually combine both metric and topological representations, in which the nodes of the topological graph point to a metric submap and the edges of the graph represent the connections between submaps, although some methods are primarily topological (Choset & Nagatani, 2001;Kortenkamp & Weymouth, 1994;Remolina & Kuipers, 2004). This metric information is usually represented as feature-based maps, for example, Bosse et al (2004), Estrada et al (2005), Lisien et al (2003), Newman et al (2003), and Tardós et al (2002), but evidence grid-based submaps are not uncommon (Jefferies, Cosgrove, Baker, & Yeap, 2004;Schultz & Adams, 1998;Yamauchi & Langley, 1996).…”

Section: Related Work In Submaps and Large-scale Slammentioning

confidence: 99%

“…There is a group of SLAM methods that explicitly exploit spatial sparsity by segmenting the world into independent submaps. Most of these methods use a combination of metric and topological maps (Bosse, Newman, Leonard, & Teller, 2004;Estrada, Neira, & Tardós, 2005;Jefferies, Cosgrove, Baker, & Yeap, 2004;Lisien et al, 2003;Newman, Leonard, & Rikoski, 2003;Schultz & Adams, 1998;Tardós, Neira, Newman, & Leonard, 2002;Yamauchi & Langley, 1996) in which the nodes of the graph are metric submaps and the relationships between submaps are represented by the edges of a graph. The submap segmentation is usually designed such that their scale is well within the capabilities of a particular SLAM approach.…”

Section: Introductionmentioning

confidence: 99%

Segmented SLAM in three‐dimensional environments

Fairfield¹,

Wettergreen²,

Kantor³

2009

Journal of Field Robotics

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) has been shown to be feasible in many small, two-dimensional, structured domains. The next challenge is to develop real-time SLAM methods that enable robots to explore large, three-dimensional, unstructured environments and allow subsequent operation in these environments over long periods of time. To circumvent the scale limitations inherent in SLAM, the world can be divided up into more manageable pieces. SLAM can be formulated on these pieces by using a combination of metric submaps and a topological map of the relationships between submaps. The contribution of this paper is a realtime, three-dimensional SLAM approach that combines an evidence grid-based volumetric submap representation, a robust Rao-Blackwellized particle filter, and a topologically flexible submap segmentation framework and map representation. We present heuristic methods for deciding how to segment the world and for reconstructing large-scale metric maps for the purpose of closing loops. We demonstrate our method on a mobile robotic platform operating in large, three-dimensional environments. C 2009 Wiley Periodicals, Inc.

show abstract

“…Bosse et al [18] describe a generic framework for SLAM in large-scale environments. They use a graph structure of local maps with relative coordinate frames similar to the work described in [19]. This approach is able to reduce the complexity of the overall problem and it better deals with the linearizations in the context of EKF-SLAM.…”

Section: Related Workmentioning

confidence: 99%

Fast and accurate SLAM with Rao–Blackwellized particle filters

Grisetti

Tipaldi

Stachniss

et al. 2007

Robotics and Autonomous Systems

153

View full text Add to dashboard Cite

Rao-Blackwellized particle filters have become a popular tool to solve the simultaneous localization and mapping problem. This technique applies a particle filter in which each particle carries an individual map of the environment. Accordingly, a key issue is to reduce the number of particles and/or to make use of compact map representations. This paper presents an approximative but highly efficient approach to mapping with Rao-Blackwellized particle filters. Moreover, it provides a compact map model. A key advantage is that the individual particles can share large parts of the model of the environment. Furthermore, they are able to reuse an already computed proposal distribution. Both techniques substantially speed-up the overall filtering process and reduce the memory requirements. Experimental results obtained with mobile robots in large-scale indoor environments and based on published standard datasets illustrate the advantages of our methods over previous mapping approaches using Rao-Blackwellized particle filters.

show abstract

Hierarchical SLAM: real-time accurate mapping of large environments

Cited by 310 publications

References 24 publications

Multi-robot olfactory search in structured environments

Multi-robot olfactory search in structured environments

Segmented SLAM in three‐dimensional environments

Fast and accurate SLAM with Rao–Blackwellized particle filters

Contact Info

Product

Resources

About