A Hybrid Approach to Intricate Motion, Manipulation and Task Planning

  • Authors:
  • Stéphane Cambon;Rachid Alami;Fabien Gravot

  • Affiliations:
  • CNRS, LAAS, 7, avenue du colonel Roche, Université deToulouse, F-31077 Toulouse, France;CNRS, LAAS, 7, avenue du colonel Roche, Université deToulouse, F-31077 Toulouse, France;CNRS, LAAS, 7, avenue du colonel Roche, Université deToulouse, F-31077 Toulouse, France

  • Venue:
  • International Journal of Robotics Research
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a representation and a planning algorithm able todeal with problems integrating task planning as well as motion andmanipulation planning knowledge involving several robots andobjects. Robot plans often include actions where the robot has toplace itself in some position in order to perform some other actionor to "modify" the configuration of its environment by displacingobjects. Our approach aims at establishing a bridge between taskplanning and manipulation planning that allows a rigorous treatmentof geometric preconditions and effects of robot actions inrealistic environments. We show how links can be establishedbetween a symbolic description and its geometric counterpart andhow they can be used in an integrated planning process that is ableto deal with intricate symbolic and geometric constraints. Finally,we describe the main features of an implemented planner and discussseveral examples of its use.