Anytime merging of appearance-based maps

Erinc, Gorkem; Carpin, Stefano

doi:10.1007/s10514-013-9352-1

Cited by 15 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous directions for future research are possible. First, and similarly to what we did with other map types [7,12], it would be interesting to develop methods that merge, in a principled way, multiple WiFi maps independently developed by multiple mappers operating in a shared environment and occasionally exchanging their data. The clustering strategy could also be improved, with backtracking being an attractive modification (i.e., reconsider clusters that have previously been fixed in order to optimize new data points and new clusters).…”

Section: Discussionmentioning

confidence: 99%

Real-time WiFi localization of heterogeneous robot teams using an online random forest

2015

Self Cite

View full text Add to dashboard Cite

In this paper we present a WiFi-based solution to the localization and mapping problem for teams of heterogeneous robots operating in unknown environments. By exploiting wireless signal strengths broadcast from access points, a robot with a large sensor payload creates a WiFi signal map that can then be shared and utilized for localization by sensor-deprived robots. In our approach, WiFi localization is cast as a classification problem. An online clustering algorithm processes incoming WiFi signals that are then incorporated into an online random forest. The algorithm's robustness is increased by a Monte Carlo Localization algorithm whose sensor model exploits the results of the online random forest classification. The proposed algorithm is shown to run in real-time, allowing the robots to operate in completely unknown environments, where a priori information such as a blue-print or the access points' location is unavailable. A comprehensive set of experiments not only compares our approach with other algorithms, but also validates the results across different scenarios covering both indoor and outdoor environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-time WiFi localization of heterogeneous robot teams using an online random forest

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, the maps may be fused together after the individual mapping processes have terminated. We consider the second approach, which has been solved exclusively for the homogeneous merging of occupancy grid [2], [3], [6], [7], topological [10], and appearance-based maps [4]. Heterogeneous maps in general have scarcely been considered, although never in the context of merging, in [12], [16].…”

Section: Related Workmentioning

confidence: 99%

“…It is important to note that the graphlike appearance-based map structure does not include any metric information. Further details on building appearancebased maps are given in [4]. Figure 1 shows examples of the different types of maps presented herein.…”

Section: Problem Formulationmentioning

confidence: 99%

“…If any Gaussian mixture component's mean (line 7) is located at a distance of more than r max away from i's estimated position, the mixture component ofg i is removed (line 8). Once all GMMs are pruned, a new set of locations is computed by running the regression algorithm on the updated GMMs (line [2][3][4]. This iterative refinement process continues until convergence (i.e., the mean difference between previous and new location estimations drops below a threshold ε).…”

Section: Edge-based Refinementmentioning

confidence: 99%

“…Both explored the first floor of the Engineering building at UC Merced in 3 independent runs covering a total distance of over 1 km. Each robot generated either an appearance-based map using the map building algorithm presented in [4] or an occupancy grid map by employing the SLAM algorithm [8]. Both robots collected WiFi observations Z i from a total of 75 unique APs (a = 75) using their WiFi cards.…”

Section: Edge-based Refinementmentioning

confidence: 99%

See 2 more Smart Citations

Heterogeneous map merging using WiFi signals

Erinc

Balaguer

Carpin

2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a map merging algorithm that is capable of merging together heterogeneous maps independently built by different robots. Heterogeneous map merging is a crucially important problem for scenarios where multiple heterogeneous robots collaborate to provide situational awareness in urban search and rescue, patrolling, and explorations tasks, just to name a few. To remedy the lack of uniform representation between heterogeneous map models, we rely on the ubiquitous presence of WiFi signals in today's environments. Our solution consists of three steps. First, the overlap between the heterogeneous maps being merged is determined. Second, metric correspondences between overlapping parts are established. Third, the merging is improved by exploiting the structural properties inherent to graph-based maps. Our proposed system is validated using various occupancy grid and appearance-based maps built in real-world conditions, the results of which confirm its strengths. To the best of our knowledge, this is the first solution to the heterogeneous map merging problem.

show abstract

Multiple-Robot Simultaneous Localization and Mapping: A Review

et al. 2015

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) in unknown GPS‐denied environments is a major challenge for researchers in the field of mobile robotics. Many solutions for single‐robot SLAM exist; however, moving to a platform of multiple robots adds many challenges to the existing problems. This paper reviews state‐of‐the‐art multiple‐robot systems, with a major focus on multiple‐robot SLAM. Various issues and problems in multiple‐robot SLAM are introduced, current solutions for these problems are reviewed, and their advantages and disadvantages are discussed.

show abstract

Anytime merging of appearance-based maps

Cited by 15 publications

References 44 publications

Real-time WiFi localization of heterogeneous robot teams using an online random forest

Real-time WiFi localization of heterogeneous robot teams using an online random forest

Heterogeneous map merging using WiFi signals

Multiple-Robot Simultaneous Localization and Mapping: A Review

Contact Info

Product

Resources

About