Using sketch-maps for robot navigation: Interpretation and matching

Mielle, Malcolm; Magnusson, Martin; Lilienthal, Achim J.

doi:10.1109/ssrr.2016.7784307

Cited by 19 publications

(34 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each vertex descriptor represents the topology of the environment around said vertex, relative to the position of anchors in the graph and the size of all other regions. • An improvement of the graph matching algorithm used in our previous work [3] was confirmed.…”

Section: Figuresupporting

confidence: 54%

“…Instead of using a sketch map as an accurate representation of an environment, a person using a sketch map will focus on the topology and points of interest along the trajectory [25], i.e., places that are distinct from the rest of the environment. However, as demonstrated by Mielle et al [3], using the topology of the environment alone is not enough to find correspondences between sketch and metric maps. Indeed, sketch maps can vary greatly from the metric map and, while the topology of both the sketch and the metric map can be correct, the schematization of the sketch can make it hard to find correct correspondences due to the difference in the level of detail.…”

Section: Segmenting the Maps And Building The Anchor Setsmentioning

confidence: 99%

“…They tested their method on maps obtained by multiple robots during the RoboCup Rescue. While their method leads to good matching results on sensor maps, it did not work well with sketch maps due to the multiple parameters that needed tuning on a per map basis [3]. In this article, we propose to use a different similarity measure that needs less parameters and is more robust to large differences in scale or representation between the maps.…”

Section: Related Workmentioning

confidence: 99%

“…In our previous work [3], we matched hand-drawn sketch maps to a ground truth map using the Voronoi diagram trimmed down automatically using the free space in the map. We used that diagram as a graph and performed planar graph matching.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

URSIM: Unique Regions for Sketch Map Interpretation and Matching

2019

Self Cite

View full text Add to dashboard Cite

We present a method for matching sketch maps to a corresponding metric map, with the aim of later using the sketch as an intuitive interface for human-robot interactions. While sketch maps are not metrically accurate and many details, which are deemed unnecessary, are omitted, they represent the topology of the environment well and are typically accurate at key locations. Thus, for sketch map interpretation and matching, one cannot only rely on metric information. Our matching method first finds the most distinguishable, or unique, regions of two maps. The topology of the maps, the positions of the unique regions, and the size of all regions are used to build region descriptors. Finally, a sequential graph matching algorithm uses the region descriptors to find correspondences between regions of the sketch and metric maps. Our method obtained higher accuracy than both a state-of-the-art matching method for inaccurate map matching, and our previous work on the subject. The state of the art was unable to match sketch maps while our method performed only 10% worse than a human expert.

show abstract

Section: Figuresupporting

confidence: 54%

Section: Segmenting the Maps And Building The Anchor Setsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

URSIM: Unique Regions for Sketch Map Interpretation and Matching

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our previous work [12], we developed a method to find correspondences between a sketch map and a ground truth map. To interpret the sketch map, we use a Voronoi diagram, with a thinning parameter, that we extract as a graph and we use an efficient error-tolerant graph matching algorithm to find correspondences.…”

Section: Related Workmentioning

confidence: 99%

SLAM auto-complete: Completing a robot map using an emergency map

Mielle

Magnusson

Andreasson

et al. 2017

2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR)

Self Cite

View full text Add to dashboard Cite

In search and rescue missions, time is an important factor; fast navigation and quickly acquiring situation awareness might be matters of life and death. Hence, the use of robots in such scenarios has been restricted by the time needed to explore and build a map. One way to speed up exploration and mapping is to reason about unknown parts of the environment using prior information. While previous research on using external priors for robot mapping mainly focused on accurate maps or aerial images, such data are not always possible to get, especially indoor. We focus on emergency maps as priors for robot mapping since they are easy to get and already extensively used by firemen in rescue missions. However, those maps can be outdated, information might be missing, and the scales of rooms are typically not consistent.We have developed a formulation of graph-based SLAM that incorporates information from an emergency map. The graph-SLAM is optimized using a combination of robust kernels, fusing the emergency map and the robot map into one map, even when faced with scale inaccuracies and inexact start poses.We typically have more than 50% of wrong correspondences in the settings studied in this paper, and the method we propose correctly handles them. Experiments in an office environment show that we can handle up to 70% of wrong correspondences and still get the expected result. The robot can navigate and explore while taking into account places it has not yet seen. We demonstrate this in a test scenario and also show that the emergency map is enhanced by adding information not represented such as closed doors or new walls.

show abstract

2D map alignment with region decomposition

Shahbandi

Magnusson

2018

Auton Robot

Self Cite

View full text Add to dashboard Cite

In many applications of autonomous mobile robots the following problem is encountered. Two maps of the same environment are available, one a prior map and the other a sensor map built by the robot. To benefit from all available information in both maps, the robot must find the correct alignment between the two maps. There exist many approaches to address this challenge, however, most of the previous methods rely on assumptions such as similar modalities of the maps, same scale, or existence of an initial guess for the alignment. In this work we propose a decomposition-based method for 2D spatial map alignment which does not rely on those assumptions. Our proposed method is validated and compared with other approaches, including generic data association approaches and map alignment algorithms. Real world examples of four different environments with thirty six sensor maps and four layout maps are used for this analysis. The maps, along with an implementation of the method, are made publicly available online.

show abstract

Using sketch-maps for robot navigation: Interpretation and matching

Cited by 19 publications

References 20 publications

URSIM: Unique Regions for Sketch Map Interpretation and Matching

URSIM: Unique Regions for Sketch Map Interpretation and Matching

SLAM auto-complete: Completing a robot map using an emergency map

2D map alignment with region decomposition

Contact Info

Product

Resources

About