home links   publications   resources  


Path Planning with Deformable Objects
 

Abstract

The ability to reliably navigate through the environment is an important prerequisite for truly autonomous robots. In our work, we consider the problem of path planning in environments with non-rigid obstacles such as curtains or plants. We combine the probabilistic roadmaps with a physical simulation of object deformations to determine a path that optimizes the trade-off between the deformation cost and the distance to be traveled. Our approach utilizes Finite Element theory for calculating the deformation cost. Since the high computational requirements of the corresponding simulation prevent this method from being applicable online, we approximate a deformation cost function for each object in a preprocessing step. This cost function allows us to estimate the deformation costs of arbitrary paths through the objects. It is used to evaluate the trajectories generated by the roadmap planner online.
 
 

Papers

  Barbara Frank, Markus Becker, Cyrill Stachniss,
Matthias Teschner, and Wolfram Burgard
Efficient Path Planning for Mobile Robots in Environments
with Deformable Objects.
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), Pasadena, CA, USA, 2008.
paper (6 pg, pdf)
 
  Barbara Frank, Markus Becker, Cyrill Stachniss, Matthias Teschner, and Wolfram Burgard
Learning Cost Functions for Mobile Robot Navigation in Environments with Deformable Objects.
Workshop on Path Planning on Cost Maps at the IEEE International Conference on Robotics and Automation (ICRA), Pasadena, CA, USA, 2008.
paper (8 pg, pdf)
 
 

Some Videos

 
  The Robot deforming a curtain on its path since no other path to the goal point exists.
Query Time: 0.05s.
 
  The Robot is deforming curtains on its path which is cheaper than deforming rubberduckies.
Query Time: 0.13s.
 
  The Robot is deforming a cow on its path.
Query Time: 0.09s.
 
 
  Real world experiment: our robot Albert is deforming some plant leaves.
Query Time: 0.23s.