Drawing to get a robot where you want it to be

tl;dr: a method to match a hand drawn map onto an exact map of a building

You might be scared of drawing but to help someone with directions, it is easy to just draw the way for them. What if you could do that with your robot?

So you’re at work/the office/whatever building you’re at right now, and a nice little robot comes to see you, and ask you where to find the room with Bob in it. You tell it that he is in the kitchen, but all the robot has, is its own complex map of the building that he has built, and you just don’t have the time to try to understand it. Why not just show him a drawing of the way to Bob ?

Your building could look something like this to the robot:

obstaclemap.png
What a beautiful building!

So you’re drawing this for the little robot:

obstaclemap.png
And such a beautiful drawing of your building !

And tadaaaam, the robot understood your drawing and can now meet with Bob, if you show him the way on the drawing !

obstaclemap.png
Red links are between places the robot think are the same.

I want to use this

The code is available here under GNU licence and the paper describing the method can be found on IEEE Xplore and on my University page. If you use this work please cite:

@inproceedings{Mielle1054805,
   author = {Mielle, Malcolm and Magnusson, Martin and Lilienthal, Achim J.},
   booktitle = {2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) : },
   institution = {Örebro University, School of Science and Technology, Örebro University, Sweden},
   pages = {252--257},
   title = {Using sketch-maps for robot navigation : interpretation and matching},
   DOI = {10.1109/SSRR.2016.7784307},
   keywords = {sketch, sketch-map, human robot interface, HRI, graph matching},
   abstract = {We present a study on sketch-map interpretation and sketch to robot map matching, where maps have nonuniform scale, different shapes or can be incomplete. For humans, sketch-maps are an intuitive way to communicate navigation information, which makes it interesting to use sketch-maps for human robot interaction; e.g., in emergency scenarios. To interpret the sketch-map, we propose to use a Voronoi diagram that is obtained from the distance image on which a thinning parameter is used to remove spurious branches. The diagram is extracted as a graph and an efficient error-tolerant graph matching algorithm is used to find correspondences, while keeping time and memory complexity low. A comparison against common algorithms for graph extraction shows that our method leads to twice as many good matches. For simple maps, our method gives 95% good matches even for heavily distorted sketches, and for a more complex real-world map, up to 58%. This paper is a first step toward using unconstrained sketch-maps in robot navigation. },
   ISBN = {978-1-5090-4349-1},
   year = {2016}
}
Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s