A Geometrical Placement Planner For Unknown Sensor-Modelled Objects And Placement Areas

Title data

Baumgartl, Johannes ; Kaminsky, Per ; Henrich, Dominik:
A Geometrical Placement Planner For Unknown Sensor-Modelled Objects And Placement Areas.
In: IEEE International Conference on Robotics and Biomimetics. - Shenzhen, China , 2013 . - pp. 364-371
DOI: https://doi.org/10.1109/ROBIO.2013.6739486

Project information

Abstract in another language

A Personal Robot should be able to handle possible unknown objects in unknown environments. For a manipulation task the question what to do with an object once it had been grasped is one of the most essential ones beside the grasping task itself. We propose a placement planner for sensor-modelled objects in complex environments. The planner computes a stable position and orientation for the object in the environment. The algorithm uses only geometric information, most notably no force or torque sensor is required. In particular, we introduce a novel approach regarding the configuration computation. By means of experiments with various household objects the robustness and performance are validated. Further on, we compare our approach to a configuration computation using a physics simulation framework.