Difference between revisions of "Vision-based Navigation and Manipulation"

From Robot Intelligence
Jump to: navigation, search
(Concept)
(Related papers)
 
(11 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
==Concept==
 
==Concept==
 
* As a map representation, we proposed a hybrid map using object-spatial layout-route information.
 
* As a map representation, we proposed a hybrid map using object-spatial layout-route information.
* Global localization is based on object recognition and its pose relationship, and our local localization uses 2D-contour matching by 2D laser scanning data.
+
* Our global localization is based on object recognition and its pose relationship, and the local localization uses 2D-contour matching by 2D laser scanning data.
 
* Our map representation is like this:
 
* Our map representation is like this:
 
::[[File:map-repres.jpg|600px|left]]
 
::[[File:map-repres.jpg|600px|left]]
Line 8: Line 8:
  
 
* The Object-based global localization is as follows:
 
* The Object-based global localization is as follows:
::::[[File:GL.jpg|500px|left]]
+
::::::[[File:GL.jpg|500px|left]]
 
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
 
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
+
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
  
 
==Related papers==
 
==Related papers==
 
+
* S Park, ''Sung-Kee Park'', "Global localization for mobile robots using reference scan matching," International Journal of Control, Automation and Systems 12 (1), 156-168, 2014.
<br/><br/>
+
* S Kim, H Cheong, DH Kim, ''Sung-Kee Park'', "Context-based object recognition for door detection," Advanced Robotics (ICAR), 2011 15th International Conference on, 155-160, 2011.
 +
* S Park, ''Sung-Kee Park'', "pectral scan matching and its application to global localization for mobile robots," Robotics and Automation (ICRA), 2010 IEEE International Conference on, 1361-1366. 2010.
 +
* S Park, S Kim, M Park, ''Sung-Kee Park'', "Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts," Information Sciences 179 (24), 4174-4198, 2009.
 +
<br/>
  
 
=Unknown Objects Grasping=
 
=Unknown Objects Grasping=
 
==Concept==
 
==Concept==
 +
* With a stereo vision(passive 3D sensor) and a Jaw-type hand, we studied a method for any unknown object grasping.
 +
* In the context of perception with only one-shot 3D image, three graspable directions such as lift-up, side and frontal direction are suggested, and an affordance-based grasp, handle graspable, is also proposed.
 +
* Our experimental movie clip : https://www.youtube.com/watch?v=YVfTltLy2w0
 +
* Our grasp directions are as follows:
 +
::[[File:grasp directions.jpg|500px|left]]
 +
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
 +
* The schema of our whole grasping process is like this:
 +
::[[File:grasp-sche.jpg|800px|left]]
 +
<br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/><br/>
  
 
==Related papers==
 
==Related papers==
 +
*RK Ala, DH Kim, SY Shin, CH Kim, ''Sung-Kee Park'', A 3D-grasp synthesis algorithm to grasp unknown objects based on graspable boundary and convex segments," Information Sciences 295, 91-106, 2015

Latest revision as of 21:17, 26 May 2016

Indoor Navigation

Concept

  • As a map representation, we proposed a hybrid map using object-spatial layout-route information.
  • Our global localization is based on object recognition and its pose relationship, and the local localization uses 2D-contour matching by 2D laser scanning data.
  • Our map representation is like this:
Map-repres.jpg





















  • The Object-based global localization is as follows:
GL.jpg





























Related papers

  • S Park, Sung-Kee Park, "Global localization for mobile robots using reference scan matching," International Journal of Control, Automation and Systems 12 (1), 156-168, 2014.
  • S Kim, H Cheong, DH Kim, Sung-Kee Park, "Context-based object recognition for door detection," Advanced Robotics (ICAR), 2011 15th International Conference on, 155-160, 2011.
  • S Park, Sung-Kee Park, "pectral scan matching and its application to global localization for mobile robots," Robotics and Automation (ICRA), 2010 IEEE International Conference on, 1361-1366. 2010.
  • S Park, S Kim, M Park, Sung-Kee Park, "Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts," Information Sciences 179 (24), 4174-4198, 2009.


Unknown Objects Grasping

Concept

  • With a stereo vision(passive 3D sensor) and a Jaw-type hand, we studied a method for any unknown object grasping.
  • In the context of perception with only one-shot 3D image, three graspable directions such as lift-up, side and frontal direction are suggested, and an affordance-based grasp, handle graspable, is also proposed.
  • Our experimental movie clip : https://www.youtube.com/watch?v=YVfTltLy2w0
  • Our grasp directions are as follows:
Grasp directions.jpg

















  • The schema of our whole grasping process is like this:
Grasp-sche.jpg














Related papers

  • RK Ala, DH Kim, SY Shin, CH Kim, Sung-Kee Park, A 3D-grasp synthesis algorithm to grasp unknown objects based on graspable boundary and convex segments," Information Sciences 295, 91-106, 2015