Search

Title Author Year Keyword Project  include Videos
or and

Publication

3D Collision Detection for Industrial Robots and Unknown Obstacles using Multiple Depth Images
Markus Fischer , Dominik Henrich

Abstract (english)
In current industrial applications without sensor surveillance, the robot workcell needs to be rather static. If the environment of the robot changes in an unplanned manner, e. g. a human enters the workcell and crosses the trajectory, a collision could result. Current research aims at relaxing the separation of robot and human workspaces. We present the first approach that uses multiple 3D depth images for fast collision detection of multiple unknown objects. The depth sensors are placed around the workcell to observe a common surveilled 3D space. The acquired depth images are used to calculate a conservative approximation of all detected obstacles within the surveilled space. Using a robot model and a segment of its future trajectory, these configurations can be checked for collisions with all detected obstacles. If no collision is detected, the minimum distance to any obstacle may be used to limit the maximum velocity. The approach is applicable to a variety of other applications, such as surveillance of tool engines or museum displays.

Publication data

Year: 2009
Publication date: 09. June 2009
Source: German Workshop on Robotics
Project: SIMERO
Referrer: http://www.ai3.uni-bayreuth.de/resypub/?mode=pub_show&pub_ref=fischer2009a

BibTeX

@ARTICLE{fischer2009a,
  TITLE             = "3D Collision Detection for Industrial Robots and Unknown Obstacles using Multiple Depth Images",
  AUTHOR            = "Fischer, Markus and Henrich, Dominik",
  YEAR              = "2009",
  JOURNAL           = "German Workshop on Robotics ",
  HOWPUBLISHED      = "\url{http://www.ai3.uni-bayreuth.de/resypub/?mode=pub_show&pub_ref=fischer2009a}",
}

Download

Filename   Size   Language   Format
fischer2009a.3D.Collision.Detection.for.Industrial.Robots.and.Unknown.Obstacles.using.Multiple.Depth.Images.pdf   785K   english   PDF   download preprint


© LS AI3 Uni-Bayreuth