| Sign In to gain access to subscriptions and/or personal tools. |
A Hybrid Approach to Intricate Motion, Manipulation and Task PlanningCNRS, LAAS, 7, avenue du colonel Roche, Université de Toulouse, F-31077 Toulouse, France, scambon{at}gmail.com
CNRS, LAAS, 7, avenue du colonel Roche, Université de Toulouse, F-31077 Toulouse, France, rachid.alami{at}laas.fr
CNRS, LAAS, 7, avenue du colonel Roche, Université de Toulouse, F-31077 Toulouse, France, fgravot{at}laas.fr We propose a representation and a planning algorithm able to deal with problems integrating task planning as well as motion and manipulation planning knowledge involving several robots and objects. Robot plans often include actions where the robot has to place itself in some position in order to perform some other action or to "modify" the configuration of its environment by displacing objects. Our approach aims at establishing a bridge between task planning and manipulation planning that allows a rigorous treatment of geometric preconditions and effects of robot actions in realistic environments. We show how links can be established between a symbolic description and its geometric counterpart and how they can be used in an integrated planning process that is able to deal with intricate symbolic and geometric constraints. Finally, we describe the main features of an implemented planner and discuss several examples of its use.
Key Words: planning formalism task planning motion planning manipulation planning.
The International Journal of Robotics Research, Vol. 28, No. 1,
104-126 (2009) |
|||